diff --git a/WandBexperiments/WandB-HousePricePrediction1.ipynb b/WandBexperiments/WandB-HousePricePrediction1.ipynb
index f6eb5ccdde90678d7f2c0a664626bbf9eec0091d..21ef5a647b0b3151d8e07aaf6096de460821363f 100755
--- a/WandBexperiments/WandB-HousePricePrediction1.ipynb
+++ b/WandBexperiments/WandB-HousePricePrediction1.ipynb
@@ -382,7 +382,8 @@
    "source": [
     "#path=\"/Users/maucher/ownCloud/Workshops/Data/Houses-dataset/Houses Dataset/\"  #MacBook\n",
     "#path=\"/Users/johannes/DataSets/Houses-dataset/Houses Dataset/\"\n",
-    "path=\"/Users/johannes/DataSets/Houses-dataset/Houses Dataset/\"\n",
+    "#path=\"/Users/johannes/DataSets/Houses-dataset/Houses Dataset/\"\n",
+    "path=\"../Data/\"\n",
     "file=\"HousesInfo.txt\"\n",
     "cols = [\"bedrooms\", \"bathrooms\", \"area\", \"zipcode\", \"price\"]\n",
     "df = pd.read_csv(path+file, sep=\" \", header=None, names=cols, decimal=\".\")\n",
@@ -1930,7 +1931,7 @@
  "metadata": {
   "celltoolbar": "Slideshow",
   "kernelspec": {
-   "display_name": "py4ds24",
+   "display_name": "python3",
    "language": "python",
    "name": "python3"
   },
@@ -1944,7 +1945,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.9.20"
   },
   "toc": {
    "base_numbering": 1,
diff --git a/WandBexperiments/WandB-HousePricePrediction2.ipynb b/WandBexperiments/WandB-HousePricePrediction2.ipynb
index fbab1cb2bb4bbcb1f509033a5ec39c1cb62f206c..e942b989c8e54f81eaa753b6663b385c1b75b43b 100644
--- a/WandBexperiments/WandB-HousePricePrediction2.ipynb
+++ b/WandBexperiments/WandB-HousePricePrediction2.ipynb
@@ -49,7 +49,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -58,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -67,18 +67,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 3,
    "metadata": {
     "scrolled": true
    },
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Using wandb-core as the SDK backend.  Please refer to https://wandb.me/wandb-core for more information.\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mjohannes-maucher\u001b[0m (\u001b[33miaai-hdm\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
        "True"
       ]
      },
-     "execution_count": 39,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -109,7 +118,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 4,
    "metadata": {
     "slideshow": {
      "slide_type": "skip"
@@ -127,7 +136,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 6,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -216,15 +225,16 @@
        "4         3        4.0  4116    85266  971226"
       ]
      },
-     "execution_count": 41,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "#path=\"/Users/maucher/ownCloud/Workshops/Data/Houses-dataset/Houses Dataset/\"  #MacBook\n",
-    "path=\"/Users/johannes/DataSets/Houses-dataset/Houses Dataset/\"\n",
+    "#path=\"/Users/johannes/DataSets/Houses-dataset/Houses Dataset/\"\n",
     "#path=\"/Users/johannesmaucher/DataSets/Houses-dataset/Houses Dataset/\"\n",
+    "path=\"../Data/\"\n",
     "file=\"HousesInfo.txt\"\n",
     "cols = [\"bedrooms\", \"bathrooms\", \"area\", \"zipcode\", \"price\"]\n",
     "df = pd.read_csv(path+file, sep=\" \", header=None, names=cols, decimal=\".\")\n",
@@ -245,7 +255,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 7,
    "metadata": {
     "scrolled": true,
     "slideshow": {
@@ -259,7 +269,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 8,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -285,7 +295,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 9,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -307,7 +317,7 @@
        "Name: count, dtype: int64"
       ]
      },
-     "execution_count": 44,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -329,7 +339,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 10,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -355,7 +365,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 11,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -384,7 +394,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 12,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -410,7 +420,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 13,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -436,7 +446,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 14,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -472,7 +482,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -490,7 +500,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -511,7 +521,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -539,7 +549,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -557,7 +567,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -606,15 +616,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Create sweep with ID: 004ladd1\n",
-      "Sweep URL: https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1\n"
+      "Create sweep with ID: ahk29776\n",
+      "Sweep URL: https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776\n"
      ]
     }
    ],
@@ -635,7 +645,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -644,13 +654,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 22,
    "metadata": {
     "slideshow": {
      "slide_type": "skip"
     }
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-12-11 14:55:01.895207: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "2024-12-11 14:55:01.895310: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "2024-12-11 14:55:02.150313: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "2024-12-11 14:55:02.721903: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+      "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
+      "2024-12-11 14:55:05.624557: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
+     ]
+    }
+   ],
    "source": [
     "from tensorflow.keras.models import Sequential\n",
     "from tensorflow.keras.layers import BatchNormalization\n",
@@ -690,7 +713,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 23,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -718,7 +741,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -740,7 +763,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -758,7 +781,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -780,7 +803,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 62,
+   "execution_count": 27,
    "metadata": {
     "scrolled": true
    },
@@ -789,20 +812,27 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: u7oycst9 with config:\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 4uzhtvcj with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [32]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -814,7 +844,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161141-u7oycst9</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150118-4uzhtvcj</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -826,7 +856,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/u7oycst9' target=\"_blank\">hardy-sweep-1</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4uzhtvcj' target=\"_blank\">atomic-sweep-1</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -850,7 +880,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -862,7 +892,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/u7oycst9' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/u7oycst9</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4uzhtvcj' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/4uzhtvcj</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -875,55 +905,41 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
+      "2024-12-11 15:01:19.806663: W tensorflow/core/common_runtime/gpu/gpu_device.cc:2256] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n",
+      "Skipping registering GPU devices...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 19ms/step - loss: 2759.8542 - val_loss: 2423.5413\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2875.4868 - val_loss: 2385.3489\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2860.8079 - val_loss: 2347.3474\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2697.5867 - val_loss: 2309.3552\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2667.1052 - val_loss: 2271.4626\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2612.0425 - val_loss: 2233.5037\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2597.3184 - val_loss: 2195.4658\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2706.4834 - val_loss: 2157.0906\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2486.6895 - val_loss: 2119.5134\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2668.2554 - val_loss: 2080.7107\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2325.1807 - val_loss: 2043.7295\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2395.7754 - val_loss: 2005.8209\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 2384.0308 - val_loss: 1967.4633\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2363.0654 - val_loss: 1929.3256\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2156.7346 - val_loss: 1891.8760\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2092.1399 - val_loss: 1854.0458\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2082.8196 - val_loss: 1816.2452\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2134.4465 - val_loss: 1778.0371\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2031.6703 - val_loss: 1740.0992\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1936.3340 - val_loss: 1702.2113\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1950.7296 - val_loss: 1663.7274\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2090.9001 - val_loss: 1625.3477\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1860.2429 - val_loss: 1587.2578\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1823.1553 - val_loss: 1549.3531\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1852.4984 - val_loss: 1511.0885\n"
+      "9/9 [==============================] - 1s 20ms/step - loss: 1891.1802 - val_loss: 1250.2527\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1407.5436 - val_loss: 2442.4919\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1584.3120 - val_loss: 2281.2681\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1570.2732 - val_loss: 2061.5964\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1610.0605 - val_loss: 1071.5280\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1470.8052 - val_loss: 2136.0156\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1533.8818 - val_loss: 975.8481\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1533.6165 - val_loss: 979.9141\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1474.0726 - val_loss: 1747.4868\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1604.2935 - val_loss: 435.2001\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1431.9862 - val_loss: 1719.2701\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1578.4182 - val_loss: 480.3889\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1551.7749 - val_loss: 694.1638\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1584.3223 - val_loss: 439.7896\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1496.6569 - val_loss: 1336.5548\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1373.0160 - val_loss: 1602.8281\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1458.1115 - val_loss: 1374.7841\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1308.7845 - val_loss: 2678.6653\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1356.7808 - val_loss: 2259.7664\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1618.7599 - val_loss: 1112.0277\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1542.1068 - val_loss: 925.4087\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1368.6941 - val_loss: 1385.6324\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1577.1157 - val_loss: 925.8898\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1473.8347 - val_loss: 1402.1488\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1488.4829 - val_loss: 916.8872\n"
      ]
     },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4612e64ba3ec41b9b015f73085aa409f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "VBox(children=(Label(value='0.010 MB of 0.010 MB uploaded\\r'), FloatProgress(value=1.0, max=1.0)))"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "data": {
       "text/html": [
@@ -944,7 +960,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▇▇▆▆▆▅▅▅▅▄▄▄▃▃▃▂▂▂▂▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▇▇▆▆▆▅▅▅▅▄▄▄▃▃▃▂▂▂▂▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>1817.53003</td></tr><tr><td>loss_valid</td><td>1511.0885</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▂▄▄▅▃▄▄▃▅▂▄▄▄▃▂▃▁▂▅▄▂▄▃▃</td></tr><tr><td>loss_valid</td><td>▄▇▇▆▃▆▃▃▅▁▅▁▂▁▄▅▄█▇▃▃▄▃▄▃</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>1488.48291</td></tr><tr><td>loss_valid</td><td>916.88721</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -956,7 +972,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">hardy-sweep-1</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/u7oycst9' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/u7oycst9</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">atomic-sweep-1</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4uzhtvcj' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/4uzhtvcj</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -968,7 +984,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161141-u7oycst9/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150118-4uzhtvcj/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -981,20 +997,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: pp3lj1mo with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 0sobs38z with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16, 16]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1006,7 +1026,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161156-pp3lj1mo</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150128-0sobs38z</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1018,7 +1038,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/pp3lj1mo' target=\"_blank\">cosmic-sweep-2</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0sobs38z' target=\"_blank\">volcanic-sweep-2</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1042,7 +1062,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1054,7 +1074,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/pp3lj1mo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/pp3lj1mo</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0sobs38z' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0sobs38z</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1063,59 +1083,37 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 24ms/step - loss: 578.3661 - val_loss: 337.7431\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 322.8176 - val_loss: 173.2800\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 136.5027 - val_loss: 73.5087\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 80.2104 - val_loss: 69.0064\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 71.1167 - val_loss: 41.7614\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 39.4732 - val_loss: 32.1327\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 30.2914 - val_loss: 32.1467\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 33.4889 - val_loss: 30.4952\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 29.8237 - val_loss: 28.6183\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 27.9714 - val_loss: 28.4032\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 27.2228 - val_loss: 28.2179\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 27.3006 - val_loss: 27.4963\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 24.3075 - val_loss: 27.3778\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 25.5394 - val_loss: 26.7168\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 25.9559 - val_loss: 26.8719\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 27.3130 - val_loss: 26.7066\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 23.3409 - val_loss: 26.3004\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 26.0039 - val_loss: 26.5442\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 24.6015 - val_loss: 26.3593\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 24.2086 - val_loss: 26.2729\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 22.1042 - val_loss: 26.9229\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 23.1797 - val_loss: 26.0574\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 23.1073 - val_loss: 29.4236\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 25.9153 - val_loss: 26.3672\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 21.9749 - val_loss: 27.2403\n"
+      "9/9 [==============================] - 1s 15ms/step - loss: 1147.8884 - val_loss: 849.5481\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 948.5853 - val_loss: 685.3662\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 748.1832 - val_loss: 534.9147\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 567.9847 - val_loss: 401.8350\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 408.3321 - val_loss: 278.8897\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 264.0383 - val_loss: 176.6202\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 141.0853 - val_loss: 126.1012\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 107.9805 - val_loss: 124.3652\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 108.6752 - val_loss: 114.3931\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 98.5184 - val_loss: 109.1369\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 93.4065 - val_loss: 106.8517\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 91.1424 - val_loss: 103.4652\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 87.7010 - val_loss: 100.9468\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 85.2430 - val_loss: 98.4347\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 82.9817 - val_loss: 96.5808\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 81.0896 - val_loss: 94.5754\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 79.6882 - val_loss: 92.7935\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 77.4010 - val_loss: 90.8464\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 76.5521 - val_loss: 89.0268\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 73.9385 - val_loss: 87.0627\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 71.6482 - val_loss: 85.0669\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 70.4278 - val_loss: 83.3195\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 68.4441 - val_loss: 81.4352\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 66.9956 - val_loss: 79.4517\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 64.2162 - val_loss: 77.6309\n"
      ]
     },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "589f41a36d46482fbe87729c3ed35da9",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "VBox(children=(Label(value='0.010 MB of 0.010 MB uploaded\\r'), FloatProgress(value=1.0, max=1.0)))"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "data": {
       "text/html": [
@@ -1136,7 +1134,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▅▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▄▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>23.41969</td></tr><tr><td>loss_valid</td><td>27.24035</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▅▄▃▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▇▅▄▃▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>64.21619</td></tr><tr><td>loss_valid</td><td>77.63093</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1148,7 +1146,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">cosmic-sweep-2</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/pp3lj1mo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/pp3lj1mo</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">volcanic-sweep-2</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0sobs38z' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0sobs38z</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1160,7 +1158,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161156-pp3lj1mo/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150128-0sobs38z/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1173,20 +1171,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: jcwfyox3 with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: z0jkquf1 with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16, 16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.05\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1198,7 +1200,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161207-jcwfyox3</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150139-z0jkquf1</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1210,7 +1212,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/jcwfyox3' target=\"_blank\">wise-sweep-3</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/z0jkquf1' target=\"_blank\">stellar-sweep-3</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1234,7 +1236,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1246,7 +1248,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/jcwfyox3' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/jcwfyox3</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/z0jkquf1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/z0jkquf1</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1255,43 +1257,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 20ms/step - loss: 150.7716 - val_loss: 46.5349\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 59.0086 - val_loss: 38.9189\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 37.3044 - val_loss: 35.1205\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 29.9801 - val_loss: 31.4889\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 33.3131 - val_loss: 34.5654\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 37.4599 - val_loss: 31.2251\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 33.5352 - val_loss: 32.6766\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 34.9990 - val_loss: 44.1248\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 35.6453 - val_loss: 36.3997\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 36.4665 - val_loss: 27.5402\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 27.9014 - val_loss: 29.5241\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 29.6743 - val_loss: 29.0234\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 26.6465 - val_loss: 25.8175\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 27.2432 - val_loss: 29.3234\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 28.7334 - val_loss: 32.7103\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 29.5515 - val_loss: 27.5028\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 28.7319 - val_loss: 29.4702\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 33.2583 - val_loss: 27.9350\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 29.6212 - val_loss: 24.6595\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 26.5488 - val_loss: 25.6328\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 26.9218 - val_loss: 26.7682\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 22.4180 - val_loss: 28.7740\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 27.6697 - val_loss: 28.0655\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 26.0765 - val_loss: 28.8390\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 29.5851 - val_loss: 27.7530\n"
+      "9/9 [==============================] - 0s 16ms/step - loss: 1726.2162 - val_loss: 723.2005\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1323.1525 - val_loss: 2951.3435\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1750.3917 - val_loss: 622.1365\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1419.2416 - val_loss: 2282.8064\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1613.0876 - val_loss: 1183.9199\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1528.2992 - val_loss: 1550.1578\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1449.9829 - val_loss: 78.3510\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1348.7166 - val_loss: 1672.6627\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1573.1493 - val_loss: 1689.4257\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1451.6206 - val_loss: 1266.0914\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1400.8724 - val_loss: 1471.5875\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1382.0697 - val_loss: 2643.8616\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1706.7056 - val_loss: 1624.1178\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1605.2437 - val_loss: 248.7414\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1452.7402 - val_loss: 1986.7676\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1613.1083 - val_loss: 342.4496\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1416.6488 - val_loss: 1687.6793\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1554.1653 - val_loss: 707.4645\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1379.2316 - val_loss: 2382.0791\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1636.5022 - val_loss: 1046.4524\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1363.2037 - val_loss: 2344.9143\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1628.3685 - val_loss: 1315.1383\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1545.8257 - val_loss: 1071.1261\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1396.3854 - val_loss: 2245.4458\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1648.2939 - val_loss: 379.9053\n"
      ]
     },
     {
@@ -1314,7 +1308,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▃▂▁▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▆▄▃▄▃▄▇▅▂▃▂▁▂▄▂▃▂▁▁▂▂▂▂▂</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>28.00254</td></tr><tr><td>loss_valid</td><td>27.75296</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▁█▃▆▄▃▁▅▃▂▂▇▆▃▆▃▅▂▆▂▆▅▂▆</td></tr><tr><td>loss_valid</td><td>▃█▂▆▄▅▁▅▅▄▄▇▅▁▆▂▅▃▇▃▇▄▃▆▂</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>1648.29395</td></tr><tr><td>loss_valid</td><td>379.90527</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1326,7 +1320,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">wise-sweep-3</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/jcwfyox3' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/jcwfyox3</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">stellar-sweep-3</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/z0jkquf1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/z0jkquf1</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1338,7 +1332,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161207-jcwfyox3/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150139-z0jkquf1/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1351,20 +1345,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: mv7puym6 with config:\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: sqavrlrr with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16, 16]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1376,7 +1374,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161217-mv7puym6</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150149-sqavrlrr</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1388,7 +1386,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/mv7puym6' target=\"_blank\">honest-sweep-4</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/sqavrlrr' target=\"_blank\">cool-sweep-4</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1412,7 +1410,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1424,7 +1422,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/mv7puym6' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/mv7puym6</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/sqavrlrr' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/sqavrlrr</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1433,43 +1431,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 22ms/step - loss: 915.3896 - val_loss: 785.8293\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 992.1658 - val_loss: 747.4283\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 829.2825 - val_loss: 709.9245\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 798.9100 - val_loss: 672.0864\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 827.0862 - val_loss: 633.9299\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 744.4014 - val_loss: 596.1848\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 697.4822 - val_loss: 558.7189\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 678.5219 - val_loss: 520.2165\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 608.5138 - val_loss: 482.3406\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 507.0502 - val_loss: 445.3589\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 488.3120 - val_loss: 407.1095\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 486.5622 - val_loss: 368.4887\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 421.0424 - val_loss: 330.4442\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 368.5771 - val_loss: 292.0654\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 312.6353 - val_loss: 254.3003\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 286.5663 - val_loss: 215.6785\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 249.9580 - val_loss: 176.6902\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 183.3012 - val_loss: 139.0856\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 143.9957 - val_loss: 100.7835\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 100.6154 - val_loss: 65.4488\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 61.7153 - val_loss: 47.7645\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 48.3149 - val_loss: 48.8485\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 48.5540 - val_loss: 48.2397\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 48.7213 - val_loss: 47.3747\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 47.9352 - val_loss: 47.3851\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 355.5095 - val_loss: 307.5546\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 326.3152 - val_loss: 284.3075\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 297.4617 - val_loss: 260.6922\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 266.7870 - val_loss: 237.8383\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 239.2161 - val_loss: 214.3134\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 210.8425 - val_loss: 191.5082\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 181.7430 - val_loss: 169.6271\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 155.4272 - val_loss: 148.7702\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 129.4328 - val_loss: 132.7168\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 113.9728 - val_loss: 124.0407\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 107.6082 - val_loss: 116.7857\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 101.9742 - val_loss: 110.9778\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 97.4087 - val_loss: 105.5818\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 92.3389 - val_loss: 101.8698\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 89.2522 - val_loss: 98.7058\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 86.4290 - val_loss: 96.0162\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 83.7309 - val_loss: 93.5133\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 81.3361 - val_loss: 90.8921\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 79.1189 - val_loss: 88.2998\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 76.6413 - val_loss: 86.0135\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 74.6215 - val_loss: 83.8671\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 72.6819 - val_loss: 81.6509\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 70.7074 - val_loss: 79.4341\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 68.8529 - val_loss: 77.0627\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 66.5955 - val_loss: 74.5884\n"
      ]
     },
     {
@@ -1492,7 +1482,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▇▆▆▆▅▅▅▄▄▃▃▃▂▂▂▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▇▆▆▅▅▅▄▄▄▃▃▃▂▂▂▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>47.59102</td></tr><tr><td>loss_valid</td><td>47.3851</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▇▆▅▄▄▃▃▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▇▇▆▅▅▄▃▃▂▂▂▂▂▂▂▂▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>66.59548</td></tr><tr><td>loss_valid</td><td>74.58845</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1504,7 +1494,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">honest-sweep-4</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/mv7puym6' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/mv7puym6</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">cool-sweep-4</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/sqavrlrr' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/sqavrlrr</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1516,7 +1506,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161217-mv7puym6/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150149-sqavrlrr/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1529,20 +1519,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 4j8z6fip with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 6kc1xtre with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.05\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1554,7 +1548,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161228-4j8z6fip</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150200-6kc1xtre</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1566,7 +1560,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j8z6fip' target=\"_blank\">wobbly-sweep-5</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/6kc1xtre' target=\"_blank\">misunderstood-sweep-5</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1590,7 +1584,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1602,7 +1596,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j8z6fip' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j8z6fip</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/6kc1xtre' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/6kc1xtre</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1611,43 +1605,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 18ms/step - loss: 640.3326 - val_loss: 364.6924\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 366.7237 - val_loss: 179.7880\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 155.4926 - val_loss: 73.5603\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 93.0298 - val_loss: 79.3530\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 75.3922 - val_loss: 65.8624\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 63.3776 - val_loss: 59.4639\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 54.1603 - val_loss: 55.6401\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 95ms/step - loss: 53.3917 - val_loss: 50.2720\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 45.7213 - val_loss: 45.9115\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 42.7995 - val_loss: 42.2777\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 36.9942 - val_loss: 38.5001\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 34.8861 - val_loss: 35.1204\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 31.0135 - val_loss: 33.0826\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 27.2195 - val_loss: 31.1558\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 24.0660 - val_loss: 29.7873\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 26.1732 - val_loss: 29.8788\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 21.6881 - val_loss: 28.5558\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 24.1859 - val_loss: 27.9270\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 24.7710 - val_loss: 27.7824\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 25.0143 - val_loss: 27.6104\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 23.2537 - val_loss: 27.3616\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 26.1453 - val_loss: 27.5274\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 23.2554 - val_loss: 28.9591\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 28.6821 - val_loss: 26.7264\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 24.7899 - val_loss: 26.6612\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 1236.3732 - val_loss: 459.7878\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 323.6621 - val_loss: 219.5480\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 342.2203 - val_loss: 357.0531\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 223.4901 - val_loss: 74.4635\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 151.0341 - val_loss: 53.7979\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 97.3754 - val_loss: 88.2104\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 70.0922 - val_loss: 40.7975\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 48.7847 - val_loss: 35.9899\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 81.1770 - val_loss: 122.5103\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 101.6574 - val_loss: 79.6257\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 69.5381 - val_loss: 33.7449\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 45.6767 - val_loss: 29.7867\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 60.6034 - val_loss: 39.8671\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 47.7063 - val_loss: 69.8968\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 81.6379 - val_loss: 32.8841\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 49.1891 - val_loss: 45.3514\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 41.4553 - val_loss: 32.8754\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 57.3864 - val_loss: 28.2843\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 45.5552 - val_loss: 30.4967\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 61.5924 - val_loss: 29.3339\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 70.6334 - val_loss: 92.5559\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 76.7799 - val_loss: 45.7601\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 80.3752 - val_loss: 103.3575\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 67.5554 - val_loss: 51.0681\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 49.7145 - val_loss: 97.5198\n"
      ]
     },
     {
@@ -1670,7 +1656,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▅▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▄▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>23.69945</td></tr><tr><td>loss_valid</td><td>26.66122</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▃▃▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▄▆▂▁▂▁▁▃▂▁▁▁▂▁▁▁▁▁▁▂▁▂▁▂</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>49.71452</td></tr><tr><td>loss_valid</td><td>97.51978</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1682,7 +1668,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">wobbly-sweep-5</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j8z6fip' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j8z6fip</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">misunderstood-sweep-5</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/6kc1xtre' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/6kc1xtre</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1694,7 +1680,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161228-4j8z6fip/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150200-6kc1xtre/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1707,20 +1693,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: o8v0aghz with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 054uzdm7 with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1732,7 +1722,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161238-o8v0aghz</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150210-054uzdm7</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1744,7 +1734,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/o8v0aghz' target=\"_blank\">pretty-sweep-6</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/054uzdm7' target=\"_blank\">swept-sweep-6</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1768,7 +1758,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1780,7 +1770,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/o8v0aghz' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/o8v0aghz</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/054uzdm7' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/054uzdm7</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1789,43 +1779,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 19ms/step - loss: 282.0587 - val_loss: 176.2752\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 189.5626 - val_loss: 169.1232\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 177.1970 - val_loss: 154.5000\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 143.6840 - val_loss: 143.3925\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 148.4143 - val_loss: 131.8391\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 125.1764 - val_loss: 122.4005\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 116.3506 - val_loss: 109.7526\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 105.5075 - val_loss: 98.7082\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 93.2370 - val_loss: 88.3801\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 79.5643 - val_loss: 76.3597\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 76.8113 - val_loss: 70.3656\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 62.5596 - val_loss: 65.3206\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 59.7168 - val_loss: 57.9553\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 45.5206 - val_loss: 54.5789\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 45.5105 - val_loss: 51.8286\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 47.0639 - val_loss: 49.4900\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 38.1292 - val_loss: 46.6160\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 40.4403 - val_loss: 43.5673\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 36.0850 - val_loss: 43.1453\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 41.8795 - val_loss: 39.9203\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 35.1405 - val_loss: 38.5089\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 32.2299 - val_loss: 35.8055\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 30.9118 - val_loss: 34.3995\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 27.6837 - val_loss: 34.1026\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 27.4615 - val_loss: 32.4486\n"
+      "9/9 [==============================] - 1s 16ms/step - loss: 1484.2220 - val_loss: 1147.5433\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1273.2915 - val_loss: 974.8321\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1067.7970 - val_loss: 801.7966\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 858.5078 - val_loss: 631.1265\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 655.0322 - val_loss: 459.6689\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 446.3062 - val_loss: 290.2849\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 242.8248 - val_loss: 120.3387\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 68.1511 - val_loss: 65.2783\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 79.8020 - val_loss: 64.2126\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 49.1131 - val_loss: 48.3860\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 46.1575 - val_loss: 45.8186\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 39.0900 - val_loss: 45.0775\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 36.9503 - val_loss: 44.3185\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 35.3603 - val_loss: 42.8304\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 34.6071 - val_loss: 42.1597\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 33.8534 - val_loss: 41.3339\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 32.8927 - val_loss: 40.5648\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 32.6688 - val_loss: 40.0208\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 32.5813 - val_loss: 39.6721\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 33.7495 - val_loss: 38.7923\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 31.4107 - val_loss: 38.0358\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 30.3548 - val_loss: 37.4280\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 29.6888 - val_loss: 36.8569\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 29.9876 - val_loss: 36.1701\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 28.8383 - val_loss: 35.5598\n"
      ]
     },
     {
@@ -1848,7 +1830,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▆▆▅▅▄▄▃▃▃▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>██▇▆▆▅▅▄▄▃▃▃▂▂▂▂▂▂▂▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>27.61072</td></tr><tr><td>loss_valid</td><td>32.44856</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▆▅▄▃▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▇▆▅▄▃▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>28.83831</td></tr><tr><td>loss_valid</td><td>35.55984</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1860,7 +1842,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">pretty-sweep-6</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/o8v0aghz' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/o8v0aghz</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">swept-sweep-6</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/054uzdm7' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/054uzdm7</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1872,7 +1854,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161238-o8v0aghz/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150210-054uzdm7/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1885,20 +1867,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 46i2ijbw with config:\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 0wtx4phq with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [4, 4]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1910,7 +1896,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161249-46i2ijbw</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150220-0wtx4phq</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1922,7 +1908,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/46i2ijbw' target=\"_blank\">noble-sweep-7</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0wtx4phq' target=\"_blank\">apricot-sweep-7</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1946,7 +1932,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1958,7 +1944,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/46i2ijbw' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/46i2ijbw</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0wtx4phq' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0wtx4phq</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1967,43 +1953,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 859.6828 - val_loss: 1009.3867\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 956.9172 - val_loss: 316.1985\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 694.1760 - val_loss: 1166.5424\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 783.1663 - val_loss: 950.8696\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 823.5640 - val_loss: 646.9088\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 905.2421 - val_loss: 471.5571\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 608.6738 - val_loss: 163.3053\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 513.3535 - val_loss: 304.5610\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 614.4946 - val_loss: 240.9074\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 755.7628 - val_loss: 384.3982\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 602.8826 - val_loss: 786.8628\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 664.2093 - val_loss: 476.9865\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 588.1680 - val_loss: 518.7810\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 620.6293 - val_loss: 376.4174\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 556.6745 - val_loss: 862.7725\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 692.9930 - val_loss: 560.6573\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 516.0991 - val_loss: 683.1836\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 595.2238 - val_loss: 161.7952\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 499.0236 - val_loss: 823.6086\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 674.7516 - val_loss: 455.2907\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 507.8876 - val_loss: 838.9777\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 533.1766 - val_loss: 86.1267\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 388.9120 - val_loss: 302.9249\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 488.3205 - val_loss: 779.7437\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 670.5150 - val_loss: 611.2392\n"
+      "9/9 [==============================] - 1s 14ms/step - loss: 86.1314 - val_loss: 91.7957\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 84.8560 - val_loss: 91.2265\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 84.2377 - val_loss: 90.5896\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 83.6042 - val_loss: 89.6467\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 82.8282 - val_loss: 88.8338\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 82.1731 - val_loss: 87.9625\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 81.5163 - val_loss: 87.1981\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 80.9123 - val_loss: 86.6217\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 80.1592 - val_loss: 85.8226\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 79.5077 - val_loss: 84.9909\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 78.8299 - val_loss: 84.1689\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 78.1212 - val_loss: 83.5400\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 77.4665 - val_loss: 82.6941\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 76.8212 - val_loss: 81.8703\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 76.1295 - val_loss: 81.3081\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 75.4362 - val_loss: 80.5412\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 74.8180 - val_loss: 79.6234\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 74.1112 - val_loss: 78.9580\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 73.3384 - val_loss: 78.3123\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 72.7661 - val_loss: 77.3867\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 72.0785 - val_loss: 76.7590\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 71.3525 - val_loss: 76.1484\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 70.7964 - val_loss: 75.5053\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 70.1698 - val_loss: 74.7255\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 69.3067 - val_loss: 74.2086\n"
      ]
     },
     {
@@ -2026,7 +2004,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>▆█▅▆▇▆▅▃▄▅▃▄▄▄▂▃▃▃▁▃▁▂▁▁▂</td></tr><tr><td>loss_valid</td><td>▇▂█▇▅▃▂▂▂▃▆▄▄▃▆▄▅▁▆▃▆▁▂▅▄</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>522.17102</td></tr><tr><td>loss_valid</td><td>611.2392</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▇▇▇▆▆▆▆▅▅▅▄▄▄▄▃▃▃▂▂▂▂▁▁</td></tr><tr><td>loss_valid</td><td>███▇▇▆▆▆▆▅▅▅▄▄▄▄▃▃▃▂▂▂▂▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>69.30669</td></tr><tr><td>loss_valid</td><td>74.20859</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2038,7 +2016,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">noble-sweep-7</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/46i2ijbw' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/46i2ijbw</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">apricot-sweep-7</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0wtx4phq' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0wtx4phq</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2050,7 +2028,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161249-46i2ijbw/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150220-0wtx4phq/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2063,20 +2041,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 4j1p1n2x with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: e27u0wpq with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [32]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.05\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2088,7 +2070,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161259-4j1p1n2x</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150231-e27u0wpq</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2100,7 +2082,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j1p1n2x' target=\"_blank\">clean-sweep-8</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/e27u0wpq' target=\"_blank\">fanciful-sweep-8</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2124,7 +2106,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2136,7 +2118,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j1p1n2x' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j1p1n2x</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/e27u0wpq' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/e27u0wpq</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2145,43 +2127,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 18ms/step - loss: 710.6155 - val_loss: 434.7530\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 335.2193 - val_loss: 67.6230\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 193.5052 - val_loss: 274.6902\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 242.8148 - val_loss: 75.5993\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 83.2331 - val_loss: 82.7808\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 116.6565 - val_loss: 189.7733\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 161.4111 - val_loss: 114.6942\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 123.5813 - val_loss: 57.1407\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 77.7333 - val_loss: 39.5452\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 67.6817 - val_loss: 51.0388\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 72.7799 - val_loss: 149.3779\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 117.5635 - val_loss: 31.7875\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 52.9925 - val_loss: 55.3359\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 54.0671 - val_loss: 45.7586\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 80.9015 - val_loss: 97.9130\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 78.6048 - val_loss: 49.4142\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 101.9237 - val_loss: 129.7796\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 122.5606 - val_loss: 190.4716\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 137.7752 - val_loss: 39.4932\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 49.9614 - val_loss: 65.2810\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 60.9737 - val_loss: 78.4451\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 69.8207 - val_loss: 44.3058\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 43.9845 - val_loss: 38.0075\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 50.5351 - val_loss: 36.9160\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 72.3470 - val_loss: 161.8863\n"
+      "9/9 [==============================] - 1s 15ms/step - loss: 503.3256 - val_loss: 216.8046\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 190.2127 - val_loss: 133.7662\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 138.9620 - val_loss: 118.2216\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 117.5364 - val_loss: 105.2012\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 84.0904 - val_loss: 92.1928\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 72.1400 - val_loss: 67.0738\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 53.5321 - val_loss: 47.8822\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 38.7840 - val_loss: 41.4203\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 30.7740 - val_loss: 34.9782\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 30.7833 - val_loss: 33.3778\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 26.1598 - val_loss: 31.7238\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 25.9448 - val_loss: 30.0345\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.8804 - val_loss: 29.1687\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.6378 - val_loss: 28.7116\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.7702 - val_loss: 31.1561\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 25.7348 - val_loss: 30.3896\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 26.0713 - val_loss: 31.8366\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 24.1642 - val_loss: 28.9464\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.6832 - val_loss: 28.7727\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.1242 - val_loss: 27.4521\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 24.4565 - val_loss: 25.4555\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 22.5204 - val_loss: 27.0662\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 24.1888 - val_loss: 26.8016\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 24.1484 - val_loss: 25.1395\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.0932 - val_loss: 24.9400\n"
      ]
     },
     {
@@ -2204,7 +2178,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▃▃▁▂▃▂▂▁▂▂▁▁▁▁▂▂▂▁▁▁▁▁▂</td></tr><tr><td>loss_valid</td><td>█▂▅▂▂▄▂▁▁▁▃▁▁▁▂▁▃▄▁▂▂▁▁▁▃</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>87.66037</td></tr><tr><td>loss_valid</td><td>161.88631</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▃▃▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▅▄▄▃▃▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>23.09316</td></tr><tr><td>loss_valid</td><td>24.93999</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2216,7 +2190,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">clean-sweep-8</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j1p1n2x' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/4j1p1n2x</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">fanciful-sweep-8</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/e27u0wpq' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/e27u0wpq</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2228,7 +2202,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161259-4j1p1n2x/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150231-e27u0wpq/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2241,20 +2215,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: cf7g7zuf with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: smeei03z with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [32]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.05\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2266,7 +2244,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161310-cf7g7zuf</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150241-smeei03z</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2278,7 +2256,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/cf7g7zuf' target=\"_blank\">ethereal-sweep-9</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/smeei03z' target=\"_blank\">chocolate-sweep-9</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2302,7 +2280,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2314,7 +2292,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/cf7g7zuf' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/cf7g7zuf</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/smeei03z' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/smeei03z</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2327,46 +2305,31 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m1/9\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 145ms/step - loss: 314.6365"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 1917716.8750 - val_loss: 227406.0000\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 189511.1875 - val_loss: 97888.4922\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 146843.8750 - val_loss: 169465.0469\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 166933.0000 - val_loss: 160264.1406\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 160683.4844 - val_loss: 118272.9922\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 156608.8594 - val_loss: 222929.8281\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 165004.1094 - val_loss: 24280.8691\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 117514.9844 - val_loss: 143088.0938\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 145102.2500 - val_loss: 101049.4609\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 142325.6250 - val_loss: 219704.7969\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 149289.2188 - val_loss: 243267.1719\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 176044.3750 - val_loss: 122214.6953\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 137005.4219 - val_loss: 226834.4844\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 150989.9062 - val_loss: 93588.9609\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 153952.4219 - val_loss: 84395.5625\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 140248.3438 - val_loss: 309009.8750\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 201260.2656 - val_loss: 15985.5781\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 144299.4844 - val_loss: 52958.1094\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 140672.0156 - val_loss: 87040.8516\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 134209.3125 - val_loss: 126480.1641\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 147617.4219 - val_loss: 27426.3340\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 139490.1094 - val_loss: 119880.6641\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 157384.1250 - val_loss: 237197.7500\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 189697.1562 - val_loss: 186405.9219\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 173539.1406 - val_loss: 16848.2031\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 182.2256 - val_loss: 61.0512\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 86.4313 - val_loss: 60.9159\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 76.0114 - val_loss: 60.6590\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 64.5149 - val_loss: 58.3952\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 45.9750 - val_loss: 44.3103\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 43.2404 - val_loss: 40.4589\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 37.2717 - val_loss: 36.6759\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 36.3607 - val_loss: 42.9808\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 38.7111 - val_loss: 33.4052\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 30.8422 - val_loss: 35.7694\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 33.0822 - val_loss: 43.3545\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 49.1796 - val_loss: 34.3707\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 46.0046 - val_loss: 32.5821\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 42.5200 - val_loss: 37.1856\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 38.5361 - val_loss: 43.4650\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 33.0935 - val_loss: 29.6877\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 29.7516 - val_loss: 31.6373\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 30.2245 - val_loss: 33.3446\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 31.1304 - val_loss: 29.7371\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 33.2660 - val_loss: 43.9086\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 48.1135 - val_loss: 49.8834\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 33.5213 - val_loss: 32.8073\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 26.3112 - val_loss: 29.5043\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 24.2099 - val_loss: 32.7431\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 30.9932 - val_loss: 31.0643\n"
      ]
     },
     {
@@ -2389,7 +2352,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>▆▃▅▄▃▆▁▄▃▆▆▄▆▃▃█▁▂▃▄▁▃▆▅▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>158976.03125</td></tr><tr><td>loss_valid</td><td>16848.20312</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▃▃▂▂▂▂▂▁▁▂▂▂▂▁▁▁▁▁▂▁▁▁▁</td></tr><tr><td>loss_valid</td><td>███▇▄▃▃▄▂▂▄▂▂▃▄▁▁▂▁▄▆▂▁▂▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>30.99319</td></tr><tr><td>loss_valid</td><td>31.06427</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2401,7 +2364,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">ethereal-sweep-9</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/cf7g7zuf' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/cf7g7zuf</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">chocolate-sweep-9</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/smeei03z' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/smeei03z</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2413,7 +2376,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161310-cf7g7zuf/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150241-smeei03z/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2426,20 +2389,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 0c1vtp5z with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: o853vtaj with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2451,7 +2418,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161320-0c1vtp5z</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150252-o853vtaj</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2463,7 +2430,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0c1vtp5z' target=\"_blank\">dry-sweep-10</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/o853vtaj' target=\"_blank\">happy-sweep-10</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2487,7 +2454,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2499,7 +2466,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0c1vtp5z' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0c1vtp5z</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/o853vtaj' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/o853vtaj</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2508,43 +2475,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 20ms/step - loss: 324.3716 - val_loss: 185.4156\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 207.9207 - val_loss: 102.7509\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 92.3099 - val_loss: 67.2602\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 69.1157 - val_loss: 57.3020\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 56.3269 - val_loss: 52.2108\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 50.8963 - val_loss: 46.5315\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 47.4731 - val_loss: 43.5988\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 39.1819 - val_loss: 40.8855\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 34.0145 - val_loss: 38.1821\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 34.8407 - val_loss: 36.6000\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 38.1521 - val_loss: 36.7754\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 35.0985 - val_loss: 35.3612\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 34.7266 - val_loss: 34.1707\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 34.4430 - val_loss: 33.7026\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 32.3529 - val_loss: 32.5518\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 32.2569 - val_loss: 31.8911\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 32.5087 - val_loss: 32.8019\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 33.3466 - val_loss: 31.1409\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 29.3387 - val_loss: 30.3979\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 28.2426 - val_loss: 31.4962\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 35.3765 - val_loss: 30.2674\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 32.4399 - val_loss: 30.8097\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 25.3902 - val_loss: 30.7580\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 31.9431 - val_loss: 28.7189\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 31.4206 - val_loss: 28.6705\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 134.6248 - val_loss: 115.6119\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 111.5401 - val_loss: 102.0437\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 96.9879 - val_loss: 84.2438\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 83.7915 - val_loss: 74.6332\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 75.0664 - val_loss: 72.4671\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 66.3846 - val_loss: 64.6259\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 64.3098 - val_loss: 62.9851\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 61.2474 - val_loss: 59.9999\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 55.7895 - val_loss: 55.1418\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 52.1472 - val_loss: 53.7816\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 50.6336 - val_loss: 50.1074\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 47.3574 - val_loss: 48.4923\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 44.7994 - val_loss: 45.9426\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 42.9675 - val_loss: 43.9776\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 40.8342 - val_loss: 42.1575\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 40.0401 - val_loss: 41.1256\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 39.9001 - val_loss: 40.5127\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 38.4745 - val_loss: 39.1210\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 37.2422 - val_loss: 40.2425\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 38.0392 - val_loss: 37.9698\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 36.0518 - val_loss: 37.1795\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 33.9678 - val_loss: 35.4005\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 34.8254 - val_loss: 35.2325\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 33.5225 - val_loss: 34.9767\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 32.5577 - val_loss: 34.8703\n"
      ]
     },
     {
@@ -2567,7 +2526,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▅▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▄▃▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>30.39702</td></tr><tr><td>loss_valid</td><td>28.67052</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▆▅▅▄▃▃▃▃▂▂▂▂▂▂▂▂▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▇▅▄▄▄▃▃▃▃▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>32.5577</td></tr><tr><td>loss_valid</td><td>34.87028</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2579,7 +2538,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">dry-sweep-10</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0c1vtp5z' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0c1vtp5z</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">happy-sweep-10</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/o853vtaj' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/o853vtaj</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2591,7 +2550,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161320-0c1vtp5z/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150252-o853vtaj/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2604,20 +2563,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: fm8vh5dq with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: iv9jyyci with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2629,7 +2592,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161331-fm8vh5dq</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150302-iv9jyyci</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2641,7 +2604,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/fm8vh5dq' target=\"_blank\">sunny-sweep-11</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/iv9jyyci' target=\"_blank\">clean-sweep-11</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2665,7 +2628,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2677,7 +2640,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/fm8vh5dq' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/fm8vh5dq</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/iv9jyyci' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/iv9jyyci</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2686,43 +2649,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 19ms/step - loss: 1298.2161 - val_loss: 948.5744\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1071.6305 - val_loss: 798.4165\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 822.5820 - val_loss: 650.0085\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 711.8972 - val_loss: 500.6856\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 546.1566 - val_loss: 350.7614\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 371.0704 - val_loss: 200.6709\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 171.1623 - val_loss: 90.9850\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 95.7302 - val_loss: 99.5967\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 109.0355 - val_loss: 93.3856\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 91.9548 - val_loss: 85.2717\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 81.7447 - val_loss: 85.7176\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 79.4047 - val_loss: 81.9584\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 77.6422 - val_loss: 80.9984\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 75.0267 - val_loss: 79.0765\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 72.7463 - val_loss: 77.3083\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 69.8783 - val_loss: 75.9190\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 68.6647 - val_loss: 73.6504\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 68.5873 - val_loss: 72.4761\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 64.4400 - val_loss: 71.0084\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 67.9393 - val_loss: 68.3331\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 65.4379 - val_loss: 68.2156\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 59.0358 - val_loss: 65.1902\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 59.7757 - val_loss: 64.1993\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 59.9772 - val_loss: 62.7442\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 57.6122 - val_loss: 60.6141\n"
+      "9/9 [==============================] - 1s 15ms/step - loss: 4378.7520 - val_loss: 2065.0295\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2929.7668 - val_loss: 2929.9114\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2972.5347 - val_loss: 3864.9441\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3214.6484 - val_loss: 2993.1328\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 3118.9783 - val_loss: 1568.0077\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3260.8193 - val_loss: 432.9879\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2722.3191 - val_loss: 5041.5845\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3181.4199 - val_loss: 2195.0332\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3077.1726 - val_loss: 1943.7969\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3106.8447 - val_loss: 1267.8733\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 3045.4438 - val_loss: 533.1691\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 2946.0840 - val_loss: 3131.2654\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3174.9800 - val_loss: 2266.2656\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2808.4392 - val_loss: 4606.2676\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3163.8892 - val_loss: 3261.5898\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3206.3977 - val_loss: 1917.5260\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 3112.2388 - val_loss: 130.6750\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2794.1179 - val_loss: 5027.0938\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3364.4702 - val_loss: 1002.1978\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2972.1831 - val_loss: 3270.0242\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 3179.0071 - val_loss: 2307.0408\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3119.3411 - val_loss: 1957.8633\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 2969.6846 - val_loss: 2614.5886\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 2794.9641 - val_loss: 4848.8604\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2914.9150 - val_loss: 4911.3999\n"
      ]
     },
     {
@@ -2745,7 +2700,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▆▅▄▃▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▇▆▄▃▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>56.48511</td></tr><tr><td>loss_valid</td><td>60.61412</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▂▂▃▃▃▁▃▂▃▂▂▃▁▃▃▃▁▄▂▃▃▂▁▂</td></tr><tr><td>loss_valid</td><td>▄▅▆▅▃▁█▄▄▃▂▅▄▇▅▄▁█▂▅▄▄▅██</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>2914.91504</td></tr><tr><td>loss_valid</td><td>4911.3999</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2757,7 +2712,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">sunny-sweep-11</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/fm8vh5dq' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/fm8vh5dq</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">clean-sweep-11</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/iv9jyyci' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/iv9jyyci</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2769,7 +2724,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161331-fm8vh5dq/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150302-iv9jyyci/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2782,20 +2737,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: l26qqty1 with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: hd7oy53z with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.05\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2807,7 +2766,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161341-l26qqty1</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150313-hd7oy53z</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2819,7 +2778,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/l26qqty1' target=\"_blank\">amber-sweep-12</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/hd7oy53z' target=\"_blank\">lucky-sweep-12</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2843,7 +2802,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2855,7 +2814,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/l26qqty1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/l26qqty1</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/hd7oy53z' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/hd7oy53z</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2864,43 +2823,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 18ms/step - loss: 587.2068 - val_loss: 438.3828\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 526.8121 - val_loss: 418.9698\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 536.6821 - val_loss: 399.7255\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 501.7654 - val_loss: 381.4095\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 468.9122 - val_loss: 363.3062\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 446.6710 - val_loss: 345.7243\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 461.8252 - val_loss: 328.2213\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 389.9725 - val_loss: 311.1593\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 409.7351 - val_loss: 294.6021\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 361.0118 - val_loss: 278.7910\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 331.4192 - val_loss: 263.1263\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 361.0892 - val_loss: 247.5218\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 349.6938 - val_loss: 232.7651\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 304.0981 - val_loss: 219.3485\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 266.3487 - val_loss: 207.0390\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 257.7042 - val_loss: 195.5854\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 241.5112 - val_loss: 184.6792\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 226.7599 - val_loss: 174.0480\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 227.6701 - val_loss: 163.8262\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 223.2001 - val_loss: 153.9372\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 187.9727 - val_loss: 144.5581\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 179.3856 - val_loss: 135.1436\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 161.8893 - val_loss: 126.4170\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 165.7640 - val_loss: 117.9100\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 145.5422 - val_loss: 109.9081\n"
+      "9/9 [==============================] - 1s 16ms/step - loss: 464.1363 - val_loss: 54.4129\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 212.5343 - val_loss: 190.2053\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 178.2732 - val_loss: 177.6351\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 193.3214 - val_loss: 114.1179\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 121.0100 - val_loss: 95.5336\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 114.9005 - val_loss: 87.8179\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 87.5357 - val_loss: 50.9218\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 104.6497 - val_loss: 45.5500\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 130.0013 - val_loss: 109.9192\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 99.8515 - val_loss: 63.7025\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 93.0888 - val_loss: 77.8427\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 127.6400 - val_loss: 170.9808\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 95.3000 - val_loss: 40.3125\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 59.6469 - val_loss: 47.3059\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 57.8376 - val_loss: 86.6706\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 82.0694 - val_loss: 65.6881\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 51.1571 - val_loss: 27.1919\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 72.1668 - val_loss: 86.4272\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 97.6090 - val_loss: 110.5752\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 146.3259 - val_loss: 36.6496\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 190.2774 - val_loss: 109.8470\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 227.9924 - val_loss: 209.7267\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 222.3800 - val_loss: 167.7136\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 129.7643 - val_loss: 33.6116\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 64.5299 - val_loss: 48.5008\n"
      ]
     },
     {
@@ -2923,7 +2874,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▆▆▆▅▅▅▄▄▄▄▃▃▃▃▂▂▂▂▁▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▆▆▆▅▅▅▄▄▄▃▃▃▃▂▂▂▂▂▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>136.85471</td></tr><tr><td>loss_valid</td><td>109.90806</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▃▃▂▂▂▂▂▂▂▂▂▁▁▂▁▁▂▃▃▄▄▂▁</td></tr><tr><td>loss_valid</td><td>▂▇▇▄▄▃▂▂▄▂▃▇▂▂▃▂▁▃▄▁▄█▆▁▂</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>64.52993</td></tr><tr><td>loss_valid</td><td>48.50077</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2935,7 +2886,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">amber-sweep-12</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/l26qqty1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/l26qqty1</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">lucky-sweep-12</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/hd7oy53z' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/hd7oy53z</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2947,7 +2898,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161341-l26qqty1/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150313-hd7oy53z/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2960,20 +2911,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: p4up4t6d with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: x5hhg1zr with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16, 16]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2985,7 +2940,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161352-p4up4t6d</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150323-x5hhg1zr</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2997,7 +2952,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/p4up4t6d' target=\"_blank\">colorful-sweep-13</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/x5hhg1zr' target=\"_blank\">leafy-sweep-13</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3021,7 +2976,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3033,7 +2988,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/p4up4t6d' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/p4up4t6d</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/x5hhg1zr' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/x5hhg1zr</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3042,43 +2997,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 7824.7554 - val_loss: 1226.2252\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3102.1997 - val_loss: 2342.3372\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2878.4421 - val_loss: 2522.6489\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2770.9543 - val_loss: 4421.2207\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3381.7517 - val_loss: 2585.8958\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3331.8831 - val_loss: 4714.9194\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 4421.9863 - val_loss: 2189.0481\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2804.4478 - val_loss: 4904.5894\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2836.3618 - val_loss: 4845.9370\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3569.0369 - val_loss: 3605.7139\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3146.0593 - val_loss: 2334.4895\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2873.6816 - val_loss: 5242.1855\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3506.2302 - val_loss: 3973.1807\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3444.0525 - val_loss: 605.3839\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2661.6194 - val_loss: 2055.0508\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 3179.7700 - val_loss: 4889.7261\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3384.4131 - val_loss: 2378.3894\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2658.6655 - val_loss: 6189.5493\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 4454.4082 - val_loss: 1671.2178\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2625.5544 - val_loss: 1420.7589\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2923.0703 - val_loss: 126.7614\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2208.6287 - val_loss: 4737.5059\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 4952.0483 - val_loss: 3636.5715\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3168.8425 - val_loss: 3622.1855\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3548.9341 - val_loss: 4146.5054\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 1416.1085 - val_loss: 1166.6643\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1389.5973 - val_loss: 1144.1519\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1362.9189 - val_loss: 1121.8099\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1336.1927 - val_loss: 1099.5861\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1309.3197 - val_loss: 1077.5060\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1282.4744 - val_loss: 1055.5093\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1256.1124 - val_loss: 1033.3278\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1228.9962 - val_loss: 1011.4455\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1203.3595 - val_loss: 988.9909\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1176.6733 - val_loss: 966.7068\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1150.3483 - val_loss: 944.3718\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1123.0308 - val_loss: 922.5994\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1096.7266 - val_loss: 900.6536\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1070.4700 - val_loss: 878.5329\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1044.2632 - val_loss: 856.2209\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1017.3789 - val_loss: 834.1889\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 991.2131 - val_loss: 811.9651\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 964.3066 - val_loss: 790.0649\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 938.0523 - val_loss: 768.0018\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 911.7107 - val_loss: 745.8767\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 885.5224 - val_loss: 723.6335\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 859.0729 - val_loss: 701.4993\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 831.9573 - val_loss: 679.8730\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 806.2525 - val_loss: 657.7964\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 779.5346 - val_loss: 635.9777\n"
      ]
     },
     {
@@ -3101,7 +3048,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▂▂▂▃▂▃▂▁▃▃▂▂▃▂▂▃▂▃▂▂▂▃▂▂</td></tr><tr><td>loss_valid</td><td>▂▄▄▆▄▆▃▇▆▅▄▇▅▂▃▆▄█▃▂▁▆▅▅▆</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>3024.58862</td></tr><tr><td>loss_valid</td><td>4146.50537</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▇▇▆▆▆▅▅▅▄▄▄▄▃▃▃▂▂▂▂▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▇▇▆▆▆▅▅▅▄▄▄▄▃▃▃▂▂▂▂▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>779.53461</td></tr><tr><td>loss_valid</td><td>635.97772</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3113,7 +3060,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">colorful-sweep-13</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/p4up4t6d' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/p4up4t6d</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">leafy-sweep-13</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/x5hhg1zr' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/x5hhg1zr</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3125,7 +3072,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161352-p4up4t6d/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150323-x5hhg1zr/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3138,20 +3085,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: mtnvgdzn with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: wqt2hi04 with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3163,7 +3114,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161402-mtnvgdzn</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150334-wqt2hi04</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3175,7 +3126,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/mtnvgdzn' target=\"_blank\">peachy-sweep-14</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/wqt2hi04' target=\"_blank\">blooming-sweep-14</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3199,7 +3150,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3211,7 +3162,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/mtnvgdzn' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/mtnvgdzn</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/wqt2hi04' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/wqt2hi04</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3224,46 +3175,31 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m1/9\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 145ms/step - loss: 645.7991"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 424.7822 - val_loss: 64.6647\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 337.1082 - val_loss: 159.9111\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 315.8720 - val_loss: 281.4530\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 307.1326 - val_loss: 439.6873\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 385.2063 - val_loss: 95.4206\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 266.6476 - val_loss: 91.2067\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 288.0881 - val_loss: 46.8704\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 215.7114 - val_loss: 563.7726\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 373.9373 - val_loss: 546.3391\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 388.2932 - val_loss: 277.5331\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 297.2371 - val_loss: 335.8599\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 308.9108 - val_loss: 536.0425\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 373.2271 - val_loss: 263.2348\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 246.7830 - val_loss: 463.2313\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 309.1783 - val_loss: 77.9094\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 254.6305 - val_loss: 385.2910\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 379.2323 - val_loss: 110.1454\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 253.8185 - val_loss: 418.4862\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 312.1200 - val_loss: 482.3463\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 298.4646 - val_loss: 212.5504\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 259.0457 - val_loss: 111.7292\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 282.6472 - val_loss: 222.8334\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 287.1844 - val_loss: 266.9925\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 296.4413 - val_loss: 499.8533\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 292.9655 - val_loss: 409.5724\n"
+      "9/9 [==============================] - 0s 16ms/step - loss: 340.2229 - val_loss: 255.5646\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 286.2777 - val_loss: 440.6091\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 300.2810 - val_loss: 280.0630\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 283.0472 - val_loss: 306.8029\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 316.4843 - val_loss: 214.1524\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 309.6173 - val_loss: 213.7857\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 296.2384 - val_loss: 167.2949\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 304.1089 - val_loss: 139.3616\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 275.9325 - val_loss: 50.2121\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 280.0994 - val_loss: 197.5048\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 316.6144 - val_loss: 78.7066\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 285.7551 - val_loss: 155.3288\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 296.0186 - val_loss: 165.2241\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 282.7524 - val_loss: 267.3242\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 306.9360 - val_loss: 257.5963\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 258.9131 - val_loss: 409.4301\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 308.7785 - val_loss: 288.0735\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 311.6999 - val_loss: 261.3217\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 245.3143 - val_loss: 499.3595\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 317.2582 - val_loss: 317.7361\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 278.9190 - val_loss: 49.2516\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 274.3944 - val_loss: 174.2083\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 275.4539 - val_loss: 217.3394\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 271.4798 - val_loss: 236.8789\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 273.7498 - val_loss: 501.4944\n"
      ]
     },
     {
@@ -3286,7 +3222,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▄▃▅▃▄▁▄▄▄▃▄▁▄▃▅▃▃▂▄▄▂▃▁</td></tr><tr><td>loss_valid</td><td>▁▃▄▆▂▂▁██▄▅█▄▇▁▆▂▆▇▃▂▃▄▇▆</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>245.26967</td></tr><tr><td>loss_valid</td><td>409.57239</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▅▄▆▆▅▅▃▄▆▄▅▄▆▂▆▆▁▆▃▃▃▃▃</td></tr><tr><td>loss_valid</td><td>▄▇▅▅▄▄▃▂▁▃▁▃▃▄▄▇▅▄█▅▁▃▄▄█</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>273.74979</td></tr><tr><td>loss_valid</td><td>501.49435</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3298,7 +3234,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">peachy-sweep-14</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/mtnvgdzn' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/mtnvgdzn</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">blooming-sweep-14</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/wqt2hi04' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/wqt2hi04</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3310,7 +3246,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161402-mtnvgdzn/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150334-wqt2hi04/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3323,20 +3259,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 98ydxsy7 with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 82zfciuj with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3348,7 +3288,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161413-98ydxsy7</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150344-82zfciuj</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3360,7 +3300,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/98ydxsy7' target=\"_blank\">true-sweep-15</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/82zfciuj' target=\"_blank\">comic-sweep-15</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3384,7 +3324,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3396,7 +3336,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/98ydxsy7' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/98ydxsy7</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/82zfciuj' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/82zfciuj</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3409,46 +3349,31 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m1/9\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 137ms/step - loss: 363.8943"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 3222.5435 - val_loss: 695.0153\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2636.0886 - val_loss: 4830.2935\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3794.0537 - val_loss: 2320.8508\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2969.2729 - val_loss: 378.4598\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2596.2341 - val_loss: 2670.1189\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3151.5615 - val_loss: 2180.0557\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3064.6494 - val_loss: 3230.8274\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2958.2649 - val_loss: 4558.2466\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3272.7292 - val_loss: 276.9205\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2417.0020 - val_loss: 6132.3403\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 3791.3264 - val_loss: 469.2088\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2933.5190 - val_loss: 3608.0178\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3618.5320 - val_loss: 3586.4705\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3182.6711 - val_loss: 2849.1008\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3326.2881 - val_loss: 3371.8086\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3280.0776 - val_loss: 71.8883\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1597.4025 - val_loss: 2181.5029\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3365.4971 - val_loss: 406.1263\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2417.7395 - val_loss: 1061.9474\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2938.9941 - val_loss: 3489.5254\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3567.7239 - val_loss: 2484.0352\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 3228.2288 - val_loss: 122.9615\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2337.1914 - val_loss: 2080.6697\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2930.5198 - val_loss: 4363.7993\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3157.1675 - val_loss: 2541.9485\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 1775.5865 - val_loss: 212.9229\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1325.0610 - val_loss: 1910.5658\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1431.0277 - val_loss: 2630.2888\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1584.8265 - val_loss: 1708.8634\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1600.3977 - val_loss: 907.0630\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1507.8402 - val_loss: 1202.8027\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1487.3904 - val_loss: 1752.0260\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1565.4801 - val_loss: 1528.3051\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1373.5411 - val_loss: 605.9454\n",
+      "9/9 [==============================] - 0s 6ms/step - loss: 1443.6289 - val_loss: 557.3875\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1538.8958 - val_loss: 186.3431\n",
+      "9/9 [==============================] - 0s 6ms/step - loss: 1476.9052 - val_loss: 1600.5238\n",
+      "9/9 [==============================] - 0s 6ms/step - loss: 1431.2986 - val_loss: 764.3406\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1386.4648 - val_loss: 704.8547\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1520.6582 - val_loss: 1015.2394\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1463.4663 - val_loss: 1800.7314\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1555.2891 - val_loss: 1086.7931\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1455.2649 - val_loss: 1851.6246\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1610.2255 - val_loss: 129.6011\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1409.1372 - val_loss: 1452.6572\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1502.2260 - val_loss: 1384.4186\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1569.5087 - val_loss: 783.2419\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1448.2529 - val_loss: 664.7383\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1518.3577 - val_loss: 308.1707\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1337.0015 - val_loss: 1250.0302\n"
      ]
     },
     {
@@ -3471,7 +3396,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>▇▄▇▅▅▅▅▅▆▂█▄▅▆▅▆▁▆▄▄▆▆▄▄▆</td></tr><tr><td>loss_valid</td><td>▂▆▄▁▄▃▅▆▁█▁▅▅▄▅▁▃▁▂▅▄▁▃▆▄</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>3185.83936</td></tr><tr><td>loss_valid</td><td>2541.94849</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▁▃▅▅▄▄▅▂▃▄▃▃▂▄▃▅▃▅▂▄▅▃▄▁</td></tr><tr><td>loss_valid</td><td>▁▆█▅▃▄▆▅▂▂▁▅▃▃▃▆▄▆▁▅▅▃▂▁▄</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>1337.00146</td></tr><tr><td>loss_valid</td><td>1250.03015</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3483,7 +3408,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">true-sweep-15</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/98ydxsy7' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/98ydxsy7</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">comic-sweep-15</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/82zfciuj' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/82zfciuj</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3495,7 +3420,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161413-98ydxsy7/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150344-82zfciuj/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3508,20 +3433,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 7omo5xok with config:\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: caw4g4rh with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [32]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3533,7 +3462,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161423-7omo5xok</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150354-caw4g4rh</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3545,7 +3474,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/7omo5xok' target=\"_blank\">classic-sweep-16</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/caw4g4rh' target=\"_blank\">sparkling-sweep-16</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3569,7 +3498,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3581,7 +3510,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/7omo5xok' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/7omo5xok</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/caw4g4rh' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/caw4g4rh</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3590,43 +3519,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 19ms/step - loss: 776.9525 - val_loss: 419.3740\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 463.8072 - val_loss: 259.1781\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 229.1677 - val_loss: 178.7094\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 211.4162 - val_loss: 147.5159\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 138.1571 - val_loss: 144.5393\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 141.6267 - val_loss: 124.3249\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 118.8517 - val_loss: 114.4890\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 100.4970 - val_loss: 106.5323\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 95.2132 - val_loss: 94.4101\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 86.9878 - val_loss: 86.6472\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 78.6432 - val_loss: 74.0624\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 62.9509 - val_loss: 67.0217\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 57.9831 - val_loss: 57.9165\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 47.8815 - val_loss: 52.4611\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 44.1477 - val_loss: 48.5587\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 40.7590 - val_loss: 45.2228\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 42.2255 - val_loss: 43.6521\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 36.8945 - val_loss: 41.5284\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 33.4650 - val_loss: 38.3364\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 33.6773 - val_loss: 36.8611\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 30.1412 - val_loss: 36.1191\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 31.9031 - val_loss: 35.1495\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 28.6114 - val_loss: 34.3492\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 30.1934 - val_loss: 33.1793\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 30.2377 - val_loss: 34.2540\n"
+      "9/9 [==============================] - 1s 16ms/step - loss: 503.9124 - val_loss: 405.1614\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 488.9148 - val_loss: 393.0966\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 474.0952 - val_loss: 380.9736\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 459.4289 - val_loss: 368.9129\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 444.9851 - val_loss: 357.2564\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 430.1153 - val_loss: 345.8494\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 416.2661 - val_loss: 334.5264\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 402.4757 - val_loss: 323.5302\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 389.8123 - val_loss: 312.9063\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 377.4542 - val_loss: 302.5687\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 364.3325 - val_loss: 292.8970\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 352.8612 - val_loss: 283.0870\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 340.8424 - val_loss: 273.7668\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 329.7314 - val_loss: 264.3601\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 318.5490 - val_loss: 255.0399\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 307.2315 - val_loss: 245.9619\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 296.7904 - val_loss: 236.6333\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 285.7776 - val_loss: 227.5199\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 274.3496 - val_loss: 218.9519\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 264.4104 - val_loss: 210.2247\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 253.6656 - val_loss: 201.8203\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 243.2184 - val_loss: 193.5212\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 232.6031 - val_loss: 185.5086\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 222.6473 - val_loss: 177.2361\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 212.2661 - val_loss: 169.0941\n"
      ]
     },
     {
@@ -3649,7 +3570,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▆▄▃▂▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▅▄▃▃▃▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>29.14783</td></tr><tr><td>loss_valid</td><td>34.25398</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▇▆▆▆▅▅▅▄▄▄▄▃▃▃▂▂▂▂▁▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▇▆▆▆▅▅▅▄▄▄▄▃▃▃▂▂▂▂▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>212.26613</td></tr><tr><td>loss_valid</td><td>169.09407</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3661,7 +3582,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">classic-sweep-16</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/7omo5xok' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/7omo5xok</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">sparkling-sweep-16</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/caw4g4rh' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/caw4g4rh</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3673,7 +3594,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161423-7omo5xok/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150354-caw4g4rh/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3686,20 +3607,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 4mzibci6 with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 0dds4njq with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16, 16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.05\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3711,7 +3636,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161434-4mzibci6</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150405-0dds4njq</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3723,7 +3648,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4mzibci6' target=\"_blank\">dry-sweep-17</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0dds4njq' target=\"_blank\">fearless-sweep-17</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3747,7 +3672,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3759,7 +3684,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4mzibci6' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/4mzibci6</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0dds4njq' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0dds4njq</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3768,43 +3693,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 678438.6250 - val_loss: 494415.7500\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 471810.3750 - val_loss: 388044.9062\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 361053.8750 - val_loss: 300443.5625\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 382366.8750 - val_loss: 620594.1250\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 601410.9375 - val_loss: 67541.5547\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 444973.6562 - val_loss: 487480.4062\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 586559.0000 - val_loss: 345316.4375\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 422604.8438 - val_loss: 313456.0625\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 472884.6875 - val_loss: 307393.5938\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 446539.0312 - val_loss: 611511.6875\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 409621.5938 - val_loss: 37223.4258\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 242077.0781 - val_loss: 483454.8438\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 416155.9688 - val_loss: 12561.3984\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 231374.9062 - val_loss: 314007.2812\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 320001.3125 - val_loss: 382974.5000\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 345407.6250 - val_loss: 47865.0312\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 264183.1875 - val_loss: 278945.9688\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 294459.9688 - val_loss: 53850.1680\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 259584.6094 - val_loss: 622761.6875\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 414078.9375 - val_loss: 57047.0000\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 277337.5938 - val_loss: 330709.0938\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 315440.9688 - val_loss: 496415.0000\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 386066.5938 - val_loss: 407590.4062\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 306392.4062 - val_loss: 194400.5000\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 267527.3125 - val_loss: 266536.4062\n"
+      "9/9 [==============================] - 1s 16ms/step - loss: 852.1276 - val_loss: 672.5136\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 815.6807 - val_loss: 641.3681\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 779.0399 - val_loss: 610.4362\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 742.4093 - val_loss: 579.6814\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 704.4721 - val_loss: 549.5867\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 668.5213 - val_loss: 518.9301\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 633.1281 - val_loss: 487.8568\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 594.7737 - val_loss: 458.0145\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 559.1194 - val_loss: 427.7760\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 522.5599 - val_loss: 397.7332\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 486.5255 - val_loss: 367.7312\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 450.8992 - val_loss: 337.8377\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 414.0050 - val_loss: 308.6716\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 379.0825 - val_loss: 279.4884\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 343.4365 - val_loss: 251.6024\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 309.3128 - val_loss: 224.7099\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 276.6270 - val_loss: 199.5034\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 245.8956 - val_loss: 177.5155\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 219.8790 - val_loss: 160.6387\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 197.5172 - val_loss: 148.9114\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 181.3682 - val_loss: 139.1193\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 165.8832 - val_loss: 130.7077\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 153.8352 - val_loss: 122.9295\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 143.2040 - val_loss: 115.8734\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 132.8476 - val_loss: 109.9754\n"
      ]
     },
     {
@@ -3827,7 +3744,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▅▄▅▄▅▄▄▄▃▁▂▂▂▂▂▂▁▃▂▂▂▂▂</td></tr><tr><td>loss_valid</td><td>▇▅▄█▂▆▅▄▄█▁▆▁▄▅▁▄▁█▂▅▇▆▃▄</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>295885.5625</td></tr><tr><td>loss_valid</td><td>266536.40625</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▇▆▆▅▅▅▄▄▄▃▃▃▂▂▂▂▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▆▆▆▅▅▅▄▄▃▃▃▂▂▂▂▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>132.84761</td></tr><tr><td>loss_valid</td><td>109.9754</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3839,7 +3756,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">dry-sweep-17</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/4mzibci6' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/4mzibci6</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">fearless-sweep-17</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0dds4njq' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0dds4njq</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3851,7 +3768,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161434-4mzibci6/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150405-0dds4njq/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3864,20 +3781,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: tmyoshyc with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 8sr3f0kk with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [32]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3889,7 +3810,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161444-tmyoshyc</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150415-8sr3f0kk</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3901,7 +3822,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/tmyoshyc' target=\"_blank\">rare-sweep-18</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/8sr3f0kk' target=\"_blank\">curious-sweep-18</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3925,7 +3846,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3937,7 +3858,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/tmyoshyc' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/tmyoshyc</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/8sr3f0kk' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/8sr3f0kk</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -3950,46 +3871,31 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m1/9\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 146ms/step - loss: 505.3449"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 4275.9512 - val_loss: 5800.0879\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3915.2783 - val_loss: 2218.3640\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2779.5493 - val_loss: 787.2540\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2518.2083 - val_loss: 3206.4863\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2975.9211 - val_loss: 3565.0039\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 3281.4321 - val_loss: 2113.6619\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 2965.2827 - val_loss: 2091.0305\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2866.8330 - val_loss: 99.3997\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2121.4202 - val_loss: 5238.6660\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 3748.6650 - val_loss: 678.8575\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 1976.5513 - val_loss: 4246.3936\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 3426.9988 - val_loss: 1219.7250\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2742.0791 - val_loss: 4639.4683\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 3251.2625 - val_loss: 2717.6650\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2983.6851 - val_loss: 4068.7336\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 3592.4167 - val_loss: 1800.7910\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2943.9609 - val_loss: 1366.3209\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2928.8083 - val_loss: 1989.8276\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 3419.8794 - val_loss: 2067.1145\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2703.5266 - val_loss: 2416.2434\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 3020.5142 - val_loss: 3042.9973\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2815.0220 - val_loss: 1493.4325\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2516.2490 - val_loss: 4281.8193\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 3161.7698 - val_loss: 2053.7039\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2762.2402 - val_loss: 2258.5203\n"
+      "9/9 [==============================] - 0s 16ms/step - loss: 600.5334 - val_loss: 307.2912\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 374.8353 - val_loss: 494.3730\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 382.8915 - val_loss: 153.5323\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 308.9454 - val_loss: 121.7756\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 282.7542 - val_loss: 181.0820\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 282.7488 - val_loss: 225.3146\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 304.5121 - val_loss: 310.0079\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 319.7950 - val_loss: 212.2890\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 310.8981 - val_loss: 68.9957\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 303.4077 - val_loss: 122.7710\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 259.9594 - val_loss: 235.2485\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 308.7617 - val_loss: 310.4258\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 300.2032 - val_loss: 411.2645\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 325.1382 - val_loss: 245.3293\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 289.2499 - val_loss: 163.1462\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 298.5631 - val_loss: 154.5992\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 318.6054 - val_loss: 48.6682\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 288.6451 - val_loss: 178.2157\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 320.0498 - val_loss: 58.7533\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 289.8860 - val_loss: 253.7471\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 246.2849 - val_loss: 467.9240\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 292.2888 - val_loss: 201.0847\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 301.5031 - val_loss: 199.2490\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 309.1552 - val_loss: 90.9594\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 280.9821 - val_loss: 245.9010\n"
      ]
     },
     {
@@ -4012,7 +3918,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▅▄▅▆▅▆▁▇▁▆▃▆▄▆▅▅▅▅▄▆▄▄▅</td></tr><tr><td>loss_valid</td><td>█▄▂▅▅▃▃▁▇▂▆▂▇▄▆▃▃▃▃▄▅▃▆▃▄</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>3031.73315</td></tr><tr><td>loss_valid</td><td>2258.52026</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▄▂▂▂▂▂▂▂▁▂▂▃▂▂▂▂▂▂▁▂▂▂▂</td></tr><tr><td>loss_valid</td><td>▅█▃▂▃▄▅▄▁▂▄▅▇▄▃▃▁▃▁▄█▃▃▂▄</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>280.98212</td></tr><tr><td>loss_valid</td><td>245.901</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4024,7 +3930,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">rare-sweep-18</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/tmyoshyc' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/tmyoshyc</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">curious-sweep-18</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/8sr3f0kk' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/8sr3f0kk</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4036,7 +3942,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161444-tmyoshyc/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150415-8sr3f0kk/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4049,20 +3955,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: iwnhujgr with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: vvfmajn3 with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [4, 4]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.05\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4074,7 +3984,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161454-iwnhujgr</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150426-vvfmajn3</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4086,7 +3996,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/iwnhujgr' target=\"_blank\">still-sweep-19</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/vvfmajn3' target=\"_blank\">eager-sweep-19</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4110,7 +4020,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4122,7 +4032,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/iwnhujgr' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/iwnhujgr</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/vvfmajn3' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/vvfmajn3</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4131,43 +4041,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 229482.3906 - val_loss: 413273.1562\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 349307.8438 - val_loss: 298527.1875\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 298460.4688 - val_loss: 225252.1250\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 285522.5938 - val_loss: 151068.3594\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 240933.0625 - val_loss: 537856.3125\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 389680.3125 - val_loss: 33800.8281\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 268735.7812 - val_loss: 338092.9062\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 321505.8125 - val_loss: 49977.4258\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 247540.7969 - val_loss: 410847.5000\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 332877.0938 - val_loss: 366619.9062\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 359356.1875 - val_loss: 186389.8125\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 275436.4375 - val_loss: 270459.9062\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 317433.4688 - val_loss: 137176.8594\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 251714.3125 - val_loss: 346629.0938\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 364108.9062 - val_loss: 318364.2188\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 309983.2812 - val_loss: 324248.9688\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 364039.5938 - val_loss: 227127.9844\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 356759.6875 - val_loss: 356964.2500\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 299683.7500 - val_loss: 262372.4688\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 360757.9062 - val_loss: 228359.6406\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 313544.9062 - val_loss: 412449.8438\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 322191.5312 - val_loss: 94682.6328\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 248634.2812 - val_loss: 422752.7500\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 287986.1562 - val_loss: 95410.6797\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 262649.4375 - val_loss: 154305.6562\n"
+      "9/9 [==============================] - 0s 16ms/step - loss: 3148.4978 - val_loss: 2535.0813\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 2366.6133 - val_loss: 971.7056\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1746.4822 - val_loss: 2909.7209\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1926.1281 - val_loss: 1653.1875\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1729.8412 - val_loss: 1543.1758\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1765.4174 - val_loss: 415.6458\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1501.2441 - val_loss: 469.5464\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1662.2227 - val_loss: 792.9412\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1610.0768 - val_loss: 826.4561\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1351.5383 - val_loss: 1827.0820\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1743.1255 - val_loss: 599.4491\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1480.2855 - val_loss: 2152.6433\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1378.6628 - val_loss: 2148.2515\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1693.5198 - val_loss: 1526.7289\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1476.5173 - val_loss: 2453.7397\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1680.4030 - val_loss: 1521.5616\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1480.2275 - val_loss: 2002.4893\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1558.8591 - val_loss: 833.5742\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1395.5190 - val_loss: 1865.2445\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1490.8618 - val_loss: 2514.4543\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1748.3322 - val_loss: 703.3140\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1426.9941 - val_loss: 2349.6733\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1682.4226 - val_loss: 561.6818\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1350.1187 - val_loss: 2753.3625\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1740.5029 - val_loss: 960.5827\n"
      ]
     },
     {
@@ -4190,7 +4092,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>▂▅▅▅▁█▃▇▂▅▆▄▅▃▅▄▅▄▆▅▃▇▂▇▄</td></tr><tr><td>loss_valid</td><td>▆▅▄▃█▁▅▁▆▆▃▄▂▅▅▅▄▅▄▄▆▂▆▂▃</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>303364.3125</td></tr><tr><td>loss_valid</td><td>154305.65625</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▅▃▃▂▃▂▂▂▁▃▂▁▂▁▂▂▂▁▂▃▁▂▁▃</td></tr><tr><td>loss_valid</td><td>▇▃█▄▄▁▁▂▂▅▂▆▆▄▇▄▅▂▅▇▂▆▁█▃</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>1740.50293</td></tr><tr><td>loss_valid</td><td>960.5827</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4202,7 +4104,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">still-sweep-19</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/iwnhujgr' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/iwnhujgr</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">eager-sweep-19</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/vvfmajn3' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/vvfmajn3</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4214,7 +4116,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161454-iwnhujgr/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150426-vvfmajn3/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4227,20 +4129,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: qyfwgalu with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: gql3sf4b with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16, 16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4252,7 +4158,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161505-qyfwgalu</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150436-gql3sf4b</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4264,7 +4170,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/qyfwgalu' target=\"_blank\">revived-sweep-20</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/gql3sf4b' target=\"_blank\">floral-sweep-20</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4288,7 +4194,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4300,7 +4206,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/qyfwgalu' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/qyfwgalu</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/gql3sf4b' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/gql3sf4b</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4309,43 +4215,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 22ms/step - loss: 400.8685 - val_loss: 239.3029\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 273.6527 - val_loss: 157.4550\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 190.0688 - val_loss: 94.8376\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 89.0250 - val_loss: 55.9666\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 60.4976 - val_loss: 58.7380\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 55.1066 - val_loss: 40.4909\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 44.7462 - val_loss: 37.2563\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 40.6010 - val_loss: 35.9368\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 41.1247 - val_loss: 34.8694\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 34.3678 - val_loss: 35.0454\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 31.9020 - val_loss: 34.9006\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 34.1727 - val_loss: 34.9817\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 34.8505 - val_loss: 34.8526\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 33.7606 - val_loss: 34.7656\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 33.4066 - val_loss: 33.9803\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 32.3803 - val_loss: 33.5449\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 37.4509 - val_loss: 33.3724\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 36.5517 - val_loss: 32.8245\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 32.5922 - val_loss: 32.4329\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 29.3407 - val_loss: 32.2131\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 32.7494 - val_loss: 32.4370\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 32.4927 - val_loss: 32.8146\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 30.2642 - val_loss: 32.5236\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 32.0971 - val_loss: 32.2471\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 33.7234 - val_loss: 31.9616\n"
+      "9/9 [==============================] - 1s 16ms/step - loss: 547.6998 - val_loss: 437.5171\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 526.6570 - val_loss: 421.4272\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 507.1933 - val_loss: 405.4363\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 486.2029 - val_loss: 390.1145\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 467.6381 - val_loss: 374.6726\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 448.2101 - val_loss: 359.7934\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 429.1725 - val_loss: 345.2783\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 410.7883 - val_loss: 330.8986\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 392.7020 - val_loss: 316.6878\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 374.6365 - val_loss: 303.1376\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 356.8311 - val_loss: 290.3642\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 340.7737 - val_loss: 277.5180\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 323.6096 - val_loss: 265.1805\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 306.8699 - val_loss: 251.2504\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 286.8941 - val_loss: 236.7009\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 266.7264 - val_loss: 222.7445\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 248.0484 - val_loss: 208.7399\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 227.8091 - val_loss: 195.7927\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 209.2860 - val_loss: 183.6125\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 191.7536 - val_loss: 171.7677\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 175.3215 - val_loss: 160.2525\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 159.2595 - val_loss: 150.2272\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 145.1360 - val_loss: 142.6617\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 135.1303 - val_loss: 136.5774\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 126.4617 - val_loss: 131.6942\n"
      ]
     },
     {
@@ -4368,7 +4266,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▆▄▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▅▃▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>31.04342</td></tr><tr><td>loss_valid</td><td>31.96156</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▇▆▆▆▅▅▅▅▄▄▄▃▃▃▂▂▂▂▁▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▇▆▆▆▅▅▅▄▄▄▃▃▃▂▂▂▂▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>126.4617</td></tr><tr><td>loss_valid</td><td>131.69423</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4380,7 +4278,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">revived-sweep-20</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/qyfwgalu' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/qyfwgalu</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">floral-sweep-20</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/gql3sf4b' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/gql3sf4b</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4392,7 +4290,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161505-qyfwgalu/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150436-gql3sf4b/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4405,20 +4303,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: e1z2d54p with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: ua6dtv6t with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16, 16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4430,7 +4332,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161516-e1z2d54p</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150447-ua6dtv6t</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4442,7 +4344,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/e1z2d54p' target=\"_blank\">scarlet-sweep-21</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/ua6dtv6t' target=\"_blank\">devoted-sweep-21</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4466,7 +4368,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4478,7 +4380,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/e1z2d54p' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/e1z2d54p</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/ua6dtv6t' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/ua6dtv6t</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4487,43 +4389,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 23ms/step - loss: 1232.5117 - val_loss: 1033.0897\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1099.5930 - val_loss: 1017.4666\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1199.2771 - val_loss: 1001.5435\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1217.7865 - val_loss: 985.6517\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1225.6398 - val_loss: 969.9888\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 1039.1757 - val_loss: 954.7835\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1066.9211 - val_loss: 939.3024\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 1121.5378 - val_loss: 923.3838\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1107.6069 - val_loss: 907.7870\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1096.3735 - val_loss: 892.0805\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1069.5145 - val_loss: 876.4026\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 971.4418 - val_loss: 861.3870\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 995.5687 - val_loss: 845.8081\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 1062.7502 - val_loss: 830.0241\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1023.6437 - val_loss: 814.6701\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 934.0226 - val_loss: 799.4231\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 960.2711 - val_loss: 783.8150\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 914.7545 - val_loss: 768.5773\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 907.2589 - val_loss: 752.9658\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 880.1528 - val_loss: 737.6902\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 899.9557 - val_loss: 722.0730\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 874.6389 - val_loss: 706.7184\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 788.8896 - val_loss: 691.5974\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 773.1125 - val_loss: 676.1265\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 757.5392 - val_loss: 660.8420\n"
+      "9/9 [==============================] - 1s 13ms/step - loss: 1514.9027 - val_loss: 1051.0844\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1108.9028 - val_loss: 717.9202\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 698.6818 - val_loss: 383.8330\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 310.6759 - val_loss: 89.5923\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 112.9066 - val_loss: 149.6131\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 124.4004 - val_loss: 64.6149\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 89.7743 - val_loss: 75.8356\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 68.5106 - val_loss: 72.0952\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 63.4246 - val_loss: 63.3304\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 62.2171 - val_loss: 57.5246\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 55.3511 - val_loss: 56.3813\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 53.7672 - val_loss: 53.6028\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 49.7957 - val_loss: 52.6810\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 48.7375 - val_loss: 49.6193\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 45.8473 - val_loss: 47.5112\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 43.3879 - val_loss: 46.3321\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 43.2189 - val_loss: 44.0952\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 40.1838 - val_loss: 42.5549\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 38.9125 - val_loss: 40.9973\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 37.0097 - val_loss: 39.5051\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 35.4434 - val_loss: 38.7571\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 34.7501 - val_loss: 37.2008\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 34.2841 - val_loss: 36.3354\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 33.4984 - val_loss: 36.4832\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 32.0122 - val_loss: 34.5238\n"
      ]
     },
     {
@@ -4546,7 +4440,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▇▇▆▆▆▅▅▅▄▄▄▄▃▃▃▂▂▂▂▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▇▇▆▆▆▅▅▅▄▄▄▄▃▃▃▂▂▂▂▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>779.18506</td></tr><tr><td>loss_valid</td><td>660.84198</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▆▄▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▆▃▁▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>32.01224</td></tr><tr><td>loss_valid</td><td>34.52381</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4558,7 +4452,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">scarlet-sweep-21</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/e1z2d54p' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/e1z2d54p</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">devoted-sweep-21</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/ua6dtv6t' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/ua6dtv6t</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4570,7 +4464,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161516-e1z2d54p/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150447-ua6dtv6t/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4583,20 +4477,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: keesqcep with config:\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: wetu6dh3 with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4608,7 +4506,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161526-keesqcep</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150457-wetu6dh3</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4620,7 +4518,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/keesqcep' target=\"_blank\">revived-sweep-22</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/wetu6dh3' target=\"_blank\">rich-sweep-22</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4644,7 +4542,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4656,7 +4554,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/keesqcep' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/keesqcep</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/wetu6dh3' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/wetu6dh3</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4665,43 +4563,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 18ms/step - loss: 433.7912 - val_loss: 378.6963\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 428.7364 - val_loss: 371.5206\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 424.2532 - val_loss: 364.4499\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 392.9392 - val_loss: 357.6321\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 403.0571 - val_loss: 350.6096\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 390.2594 - val_loss: 343.4500\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 377.0409 - val_loss: 336.3739\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 356.4251 - val_loss: 329.3474\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 380.2450 - val_loss: 322.4118\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 371.0009 - val_loss: 316.0578\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 354.1033 - val_loss: 309.5834\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 344.0947 - val_loss: 303.3714\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 341.2033 - val_loss: 297.2771\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 310.4945 - val_loss: 291.3549\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 325.5523 - val_loss: 285.4034\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 299.9646 - val_loss: 279.6140\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 293.4885 - val_loss: 273.8668\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 299.0352 - val_loss: 269.1822\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 278.1805 - val_loss: 265.0975\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 285.5456 - val_loss: 261.3992\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 277.5122 - val_loss: 258.0837\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 268.1396 - val_loss: 254.9763\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 247.7330 - val_loss: 252.1956\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 250.9892 - val_loss: 249.3808\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 258.5593 - val_loss: 246.5298\n"
+      "9/9 [==============================] - 0s 17ms/step - loss: 1396.6420 - val_loss: 2385.2756\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1623.6116 - val_loss: 1073.1263\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1291.1538 - val_loss: 360.6027\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1299.9623 - val_loss: 1481.6904\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1269.9839 - val_loss: 2762.6843\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1410.0215 - val_loss: 1472.0118\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1247.7661 - val_loss: 1448.8239\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1221.0551 - val_loss: 1409.8193\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1218.3322 - val_loss: 661.7155\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1050.9008 - val_loss: 741.4514\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 932.5637 - val_loss: 897.2881\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1022.2747 - val_loss: 971.8735\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1050.3965 - val_loss: 559.1490\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 904.8151 - val_loss: 621.0137\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 936.5269 - val_loss: 701.1403\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 940.3846 - val_loss: 68.7337\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 724.2468 - val_loss: 1198.2750\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 858.4961 - val_loss: 445.4660\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 803.8655 - val_loss: 153.6629\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 691.4421 - val_loss: 1329.0311\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 866.2900 - val_loss: 211.4921\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 782.0925 - val_loss: 357.5953\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 786.9018 - val_loss: 299.9937\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 714.6655 - val_loss: 838.2617\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 780.3450 - val_loss: 198.5970\n"
      ]
     },
     {
@@ -4724,7 +4614,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▇▆▆▆▅▅▄▄▄▃▃▃▃▂▂▂▂▁▁▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▇▆▆▅▅▅▄▄▄▃▃▃▂▂▂▂▂▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>254.13031</td></tr><tr><td>loss_valid</td><td>246.5298</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>▆█▆▆▅▆▅▅▅▄▃▃▄▃▃▃▁▂▂▁▂▂▂▁▂</td></tr><tr><td>loss_valid</td><td>▇▄▂▅█▅▅▄▃▃▃▃▂▂▃▁▄▂▁▄▁▂▂▃▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>780.34497</td></tr><tr><td>loss_valid</td><td>198.59705</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4736,7 +4626,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">revived-sweep-22</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/keesqcep' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/keesqcep</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">rich-sweep-22</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/wetu6dh3' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/wetu6dh3</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4748,7 +4638,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161526-keesqcep/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150457-wetu6dh3/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4761,20 +4651,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: pjq46fj0 with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: r4p57of5 with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [32]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4786,7 +4680,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161537-pjq46fj0</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150508-r4p57of5</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4798,7 +4692,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/pjq46fj0' target=\"_blank\">azure-sweep-23</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/r4p57of5' target=\"_blank\">floral-sweep-23</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4822,7 +4716,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4834,7 +4728,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/pjq46fj0' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/pjq46fj0</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/r4p57of5' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/r4p57of5</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4843,43 +4737,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 20ms/step - loss: 135.0590 - val_loss: 86.7663\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 82.6881 - val_loss: 87.8192\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 86.7559 - val_loss: 85.9241\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 80.4371 - val_loss: 84.1557\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 79.6825 - val_loss: 84.1183\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 82.2015 - val_loss: 81.9223\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 76.4194 - val_loss: 81.1245\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 77.7286 - val_loss: 80.3060\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 76.2351 - val_loss: 79.4118\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 73.5924 - val_loss: 77.6896\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 71.2517 - val_loss: 77.4652\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 71.6474 - val_loss: 76.1239\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 71.1639 - val_loss: 74.4142\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 68.1805 - val_loss: 74.2487\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 71.1377 - val_loss: 72.6346\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 69.5775 - val_loss: 71.5489\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 67.9486 - val_loss: 69.9686\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 65.7441 - val_loss: 69.1180\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 65.6129 - val_loss: 67.9278\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 65.5165 - val_loss: 66.5821\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 61.6367 - val_loss: 65.1723\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 59.9326 - val_loss: 64.5087\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 60.6812 - val_loss: 63.1202\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 59.3239 - val_loss: 62.3628\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 58.6995 - val_loss: 60.8974\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 499.1097 - val_loss: 214.7566\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 129.2285 - val_loss: 119.8580\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 145.4370 - val_loss: 79.5334\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 59.4640 - val_loss: 55.9175\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 49.0695 - val_loss: 45.4472\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 40.8987 - val_loss: 32.3922\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 34.7018 - val_loss: 34.9079\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 32.9128 - val_loss: 31.0178\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 27.4802 - val_loss: 29.7440\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 26.7171 - val_loss: 28.6552\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 27.7907 - val_loss: 28.7305\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 25.4386 - val_loss: 29.0573\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 26.7782 - val_loss: 29.4664\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 25.8777 - val_loss: 27.1879\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 24.8178 - val_loss: 27.4858\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 25.5558 - val_loss: 26.7305\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 23.8289 - val_loss: 26.7204\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.8554 - val_loss: 26.7426\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.8188 - val_loss: 26.6538\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.6229 - val_loss: 26.1921\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 24.1301 - val_loss: 26.3674\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 23.1617 - val_loss: 26.6137\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.1025 - val_loss: 25.7700\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.2113 - val_loss: 25.7378\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 23.6467 - val_loss: 25.7209\n"
      ]
     },
     {
@@ -4902,7 +4788,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▅▄▄▃▃▃▃▃▃▃▃▂▂▂▂▂▂▂▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>███▇▇▆▆▆▆▅▅▅▅▄▄▄▃▃▃▂▂▂▂▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>58.13652</td></tr><tr><td>loss_valid</td><td>60.8974</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▃▃▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▄▃▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>23.64672</td></tr><tr><td>loss_valid</td><td>25.72086</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4914,7 +4800,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">azure-sweep-23</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/pjq46fj0' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/pjq46fj0</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">floral-sweep-23</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/r4p57of5' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/r4p57of5</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4926,7 +4812,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161537-pjq46fj0/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150508-r4p57of5/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4939,20 +4825,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: g5kk0we9 with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: mcluzid3 with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [32]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16, 16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4964,7 +4854,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161547-g5kk0we9</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150518-mcluzid3</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -4976,7 +4866,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/g5kk0we9' target=\"_blank\">fine-sweep-24</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/mcluzid3' target=\"_blank\">resilient-sweep-24</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5000,7 +4890,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5012,7 +4902,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/g5kk0we9' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/g5kk0we9</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/mcluzid3' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/mcluzid3</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5021,43 +4911,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 19ms/step - loss: 369.1923 - val_loss: 317.2588\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 346.6427 - val_loss: 303.6536\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 330.7915 - val_loss: 290.3673\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 315.6115 - val_loss: 277.0261\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 302.0160 - val_loss: 263.7625\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 275.5658 - val_loss: 250.6243\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 251.1155 - val_loss: 238.3750\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 242.8002 - val_loss: 226.3309\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 223.3871 - val_loss: 216.2358\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 210.0890 - val_loss: 209.3619\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 208.7549 - val_loss: 204.6810\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 202.3743 - val_loss: 199.9404\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 194.6253 - val_loss: 195.2500\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 178.5557 - val_loss: 190.4214\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 183.2821 - val_loss: 185.4072\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 182.8195 - val_loss: 180.6218\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 170.7283 - val_loss: 175.8323\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 159.7883 - val_loss: 171.1685\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 155.4698 - val_loss: 166.3720\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 160.9924 - val_loss: 161.5988\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 145.7462 - val_loss: 156.8839\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 153.3636 - val_loss: 152.0707\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 140.7270 - val_loss: 147.3500\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 141.5525 - val_loss: 142.7041\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 142.8334 - val_loss: 138.0623\n"
+      "9/9 [==============================] - 0s 17ms/step - loss: 313.8010 - val_loss: 529.0889\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 319.8384 - val_loss: 258.6804\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 291.1324 - val_loss: 353.8833\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 298.8256 - val_loss: 183.4529\n",
+      "9/9 [==============================] - 0s 10ms/step - loss: 282.3858 - val_loss: 389.4978\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 311.9205 - val_loss: 190.6295\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 302.4846 - val_loss: 399.2003\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 286.2772 - val_loss: 569.4782\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 321.7414 - val_loss: 75.1070\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 259.3968 - val_loss: 445.7378\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 265.5208 - val_loss: 258.8596\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 287.9886 - val_loss: 258.3434\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 299.0500 - val_loss: 183.4930\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 288.0428 - val_loss: 378.0447\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 331.8701 - val_loss: 147.9148\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 302.4475 - val_loss: 159.9049\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 266.5263 - val_loss: 149.3968\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 301.6125 - val_loss: 174.7923\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 306.7140 - val_loss: 210.8563\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 279.4569 - val_loss: 282.8980\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 305.7377 - val_loss: 334.7823\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 321.8493 - val_loss: 129.2203\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 278.5226 - val_loss: 423.0960\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 332.1918 - val_loss: 50.2876\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 276.9621 - val_loss: 264.8690\n"
      ]
     },
     {
@@ -5080,7 +4962,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▇▆▆▅▅▄▄▃▃▃▃▃▂▂▂▂▂▂▂▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▇▇▆▆▅▅▄▄▄▄▃▃▃▃▃▂▂▂▂▂▂▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>132.6037</td></tr><tr><td>loss_valid</td><td>138.0623</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>▆▇▄▅▃▆▅▄▇▁▂▄▅▄█▅▂▅▆▃▅▇▃█▃</td></tr><tr><td>loss_valid</td><td>▇▄▅▃▆▃▆█▁▆▄▄▃▅▂▂▂▃▃▄▅▂▆▁▄</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>276.96207</td></tr><tr><td>loss_valid</td><td>264.86899</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5092,7 +4974,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">fine-sweep-24</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/g5kk0we9' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/g5kk0we9</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">resilient-sweep-24</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/mcluzid3' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/mcluzid3</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5104,7 +4986,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161547-g5kk0we9/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150518-mcluzid3/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5117,20 +4999,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 70q1qs4k with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: hggt1kj0 with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [4, 4]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5142,7 +5028,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161558-70q1qs4k</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150529-hggt1kj0</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5154,7 +5040,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/70q1qs4k' target=\"_blank\">fiery-sweep-25</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/hggt1kj0' target=\"_blank\">deep-sweep-25</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5178,7 +5064,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5190,7 +5076,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/70q1qs4k' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/70q1qs4k</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/hggt1kj0' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/hggt1kj0</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5203,46 +5089,31 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m1/9\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 138ms/step - loss: 195.1066"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 716.6319 - val_loss: 541.3484\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 913.4852 - val_loss: 1003.3286\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 791.7849 - val_loss: 116.7279\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 572.5334 - val_loss: 353.8883\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 590.9959 - val_loss: 1268.0972\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1003.9509 - val_loss: 765.3657\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 852.8003 - val_loss: 399.9219\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 698.3024 - val_loss: 806.0473\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 730.6609 - val_loss: 671.4030\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 763.0090 - val_loss: 731.0415\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 670.6762 - val_loss: 1019.7757\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 730.1681 - val_loss: 661.9863\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 694.6899 - val_loss: 161.0568\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 453.4880 - val_loss: 539.3333\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 603.4644 - val_loss: 823.4114\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 703.9949 - val_loss: 389.9573\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 601.0822 - val_loss: 723.4084\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 543.7063 - val_loss: 786.6707\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 736.4147 - val_loss: 191.3257\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 532.7465 - val_loss: 313.6458\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 419.4425 - val_loss: 755.8044\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 600.3413 - val_loss: 758.5246\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 715.3646 - val_loss: 375.1808\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 435.1966 - val_loss: 217.6454\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 421.7916 - val_loss: 770.7307\n"
+      "9/9 [==============================] - 0s 16ms/step - loss: 4042.8918 - val_loss: 3714.1523\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3274.7805 - val_loss: 2420.9749\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3194.8513 - val_loss: 686.6002\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2412.3718 - val_loss: 4131.1211\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 2867.0049 - val_loss: 3116.2900\n",
+      "9/9 [==============================] - 0s 6ms/step - loss: 3192.1387 - val_loss: 3322.7949\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 2958.9424 - val_loss: 3956.0078\n",
+      "9/9 [==============================] - 0s 6ms/step - loss: 2986.1230 - val_loss: 3785.1936\n",
+      "9/9 [==============================] - 0s 6ms/step - loss: 2755.4802 - val_loss: 3452.4766\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2866.1003 - val_loss: 2681.5713\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3143.3994 - val_loss: 964.8264\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 2794.8469 - val_loss: 4880.5161\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3364.5085 - val_loss: 1423.7633\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3096.7524 - val_loss: 1169.6497\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 2871.6963 - val_loss: 3725.8477\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3021.4092 - val_loss: 172.9071\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2597.5093 - val_loss: 4751.3110\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3267.8083 - val_loss: 2163.9238\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3069.9814 - val_loss: 3100.2996\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3098.4189 - val_loss: 3316.9895\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 2817.4272 - val_loss: 3227.2725\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3224.5183 - val_loss: 357.8117\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2215.8645 - val_loss: 4179.1499\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3221.3777 - val_loss: 2955.1565\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3068.2307 - val_loss: 2060.6875\n"
      ]
     },
     {
@@ -5265,7 +5136,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▆▆▆▇▇▅▆▆▃▄▄▂▃▄▃▂▃▃▂▂▃▁▁</td></tr><tr><td>loss_valid</td><td>▄▆▁▂█▅▃▅▄▅▆▄▁▄▅▃▅▅▁▂▅▅▃▂▅</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>459.79285</td></tr><tr><td>loss_valid</td><td>770.73071</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▅▅▂▃▅▄▄▃▃▅▃▅▄▄▄▂▅▄▄▃▅▁▅▄</td></tr><tr><td>loss_valid</td><td>▆▄▂▇▅▆▇▆▆▅▂█▃▂▆▁█▄▅▆▆▁▇▅▄</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>3068.23071</td></tr><tr><td>loss_valid</td><td>2060.6875</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5277,7 +5148,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">fiery-sweep-25</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/70q1qs4k' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/70q1qs4k</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">deep-sweep-25</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/hggt1kj0' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/hggt1kj0</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5289,7 +5160,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161558-70q1qs4k/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150529-hggt1kj0/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5302,20 +5173,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: i4mihk3o with config:\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: g1mwyx5n with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5327,7 +5202,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161608-i4mihk3o</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150539-g1mwyx5n</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5339,7 +5214,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/i4mihk3o' target=\"_blank\">amber-sweep-26</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/g1mwyx5n' target=\"_blank\">zany-sweep-26</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5363,7 +5238,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5375,7 +5250,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/i4mihk3o' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/i4mihk3o</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/g1mwyx5n' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/g1mwyx5n</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5384,43 +5259,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 585.7816 - val_loss: 274.8994\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 304.9303 - val_loss: 280.2965\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 296.9077 - val_loss: 261.9572\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 324.3904 - val_loss: 171.2507\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 255.2729 - val_loss: 277.8224\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 292.0899 - val_loss: 102.2406\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 254.9427 - val_loss: 66.5948\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 208.2566 - val_loss: 119.3973\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 268.6265 - val_loss: 398.8486\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 305.7241 - val_loss: 423.0752\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 308.6520 - val_loss: 295.3683\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 247.4624 - val_loss: 155.0729\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 283.5184 - val_loss: 108.9832\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 273.3532 - val_loss: 347.5827\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 302.8515 - val_loss: 270.6931\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 294.2795 - val_loss: 464.5869\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 324.6469 - val_loss: 303.6444\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 259.5521 - val_loss: 285.3918\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 314.9050 - val_loss: 161.4872\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 286.2670 - val_loss: 156.8566\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 281.8893 - val_loss: 435.3989\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 319.6364 - val_loss: 365.7068\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 322.9889 - val_loss: 347.3818\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 349.3478 - val_loss: 120.4719\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 264.9764 - val_loss: 288.0826\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 967.2177 - val_loss: 1085.0150\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 857.9575 - val_loss: 101.9005\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 779.5940 - val_loss: 380.1910\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 761.9283 - val_loss: 504.2755\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 724.1053 - val_loss: 170.0907\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 711.6896 - val_loss: 404.1844\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 702.0679 - val_loss: 647.6172\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 665.0020 - val_loss: 608.4490\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 657.0671 - val_loss: 799.6707\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 668.3912 - val_loss: 704.3203\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 578.5634 - val_loss: 997.9150\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 617.2223 - val_loss: 892.0847\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 572.1138 - val_loss: 786.6357\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 572.7314 - val_loss: 446.8621\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 611.0338 - val_loss: 176.5419\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 570.5935 - val_loss: 310.1814\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 544.8936 - val_loss: 601.7809\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 521.4464 - val_loss: 773.0999\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 477.9088 - val_loss: 652.8232\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 570.6659 - val_loss: 84.4329\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 477.5414 - val_loss: 715.6848\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 567.4114 - val_loss: 265.3901\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 509.6311 - val_loss: 394.7251\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 464.7177 - val_loss: 366.0360\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 517.1508 - val_loss: 229.7352\n"
      ]
     },
     {
@@ -5443,7 +5310,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▄▄▄▄▂▁▃▁▄▁▅▂▂▂▃▃▅▃▁▄▄▅▃</td></tr><tr><td>loss_valid</td><td>▅▅▄▃▅▂▁▂▇▇▅▃▂▆▅█▅▅▃▃▇▆▆▂▅</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>282.50113</td></tr><tr><td>loss_valid</td><td>288.08261</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▆▅▅▅▄▄▄▄▄▃▃▂▃▃▂▂▂▁▂▁▂▂▁▂</td></tr><tr><td>loss_valid</td><td>█▁▃▄▂▃▅▅▆▅▇▇▆▄▂▃▅▆▅▁▅▂▃▃▂</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>517.15076</td></tr><tr><td>loss_valid</td><td>229.73523</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5455,7 +5322,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">amber-sweep-26</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/i4mihk3o' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/i4mihk3o</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">zany-sweep-26</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/g1mwyx5n' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/g1mwyx5n</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5467,7 +5334,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161608-i4mihk3o/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150539-g1mwyx5n/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5480,20 +5347,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: f2odnj7i with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: r9n7wxbd with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8, 8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [4, 4]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5505,7 +5376,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161619-f2odnj7i</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150550-r9n7wxbd</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5517,7 +5388,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/f2odnj7i' target=\"_blank\">comic-sweep-27</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/r9n7wxbd' target=\"_blank\">volcanic-sweep-27</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5541,7 +5412,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5553,7 +5424,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/f2odnj7i' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/f2odnj7i</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/r9n7wxbd' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/r9n7wxbd</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5562,43 +5433,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 8318.9473 - val_loss: 2100.3123\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3003.5359 - val_loss: 4637.1782\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3595.4878 - val_loss: 1431.9821\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2692.5239 - val_loss: 1162.6815\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2645.2969 - val_loss: 2842.4587\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3231.5425 - val_loss: 2605.6758\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2404.9854 - val_loss: 355.7976\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3082.0061 - val_loss: 659.6756\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3235.4700 - val_loss: 3057.9512\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3050.1538 - val_loss: 806.1579\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2898.1680 - val_loss: 1783.6217\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2640.2808 - val_loss: 591.0371\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2781.5789 - val_loss: 3249.5840\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3930.0767 - val_loss: 2385.6785\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2693.3145 - val_loss: 4033.1941\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3417.5083 - val_loss: 2223.5698\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2713.0430 - val_loss: 4824.8701\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3668.3103 - val_loss: 2536.7993\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2894.5576 - val_loss: 4603.6802\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3194.0793 - val_loss: 1225.2542\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2841.4565 - val_loss: 3607.4822\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2646.0881 - val_loss: 944.9686\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2822.4167 - val_loss: 515.5635\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2665.1094 - val_loss: 2220.0559\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2772.6963 - val_loss: 1370.8551\n"
+      "9/9 [==============================] - 1s 15ms/step - loss: 1119.5745 - val_loss: 889.4881\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1068.8798 - val_loss: 848.4966\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1019.2167 - val_loss: 807.3188\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 970.7853 - val_loss: 765.8406\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 921.3925 - val_loss: 724.6333\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 872.0748 - val_loss: 683.9295\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 821.9166 - val_loss: 644.1096\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 775.4157 - val_loss: 603.0369\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 725.8073 - val_loss: 562.9005\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 677.8279 - val_loss: 522.8899\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 630.3211 - val_loss: 482.8219\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 582.2126 - val_loss: 443.3866\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 535.3909 - val_loss: 404.1383\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 487.5038 - val_loss: 365.9716\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 442.3998 - val_loss: 327.0927\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 395.5153 - val_loss: 289.3497\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 350.3200 - val_loss: 252.1123\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 305.5286 - val_loss: 216.8567\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 262.9831 - val_loss: 185.5427\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 225.5449 - val_loss: 157.9622\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 190.7336 - val_loss: 136.3037\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 163.4524 - val_loss: 119.3409\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 142.1611 - val_loss: 108.1233\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 127.5132 - val_loss: 99.6844\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 116.7526 - val_loss: 93.9095\n"
      ]
     },
     {
@@ -5621,7 +5484,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▁▂▂▁▂▁▁▁▂▂▂▁▂▂▂▁▂▁▂▁▂▂▂▂</td></tr><tr><td>loss_valid</td><td>▄█▃▂▅▅▁▁▅▂▃▁▆▄▇▄█▄█▂▆▂▁▄▃</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>3115.01343</td></tr><tr><td>loss_valid</td><td>1370.8551</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>██▇▇▇▆▆▆▅▅▅▄▄▄▃▃▃▂▂▂▂▁▁▁▁</td></tr><tr><td>loss_valid</td><td>██▇▇▇▆▆▅▅▅▄▄▄▃▃▃▂▂▂▂▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>116.7526</td></tr><tr><td>loss_valid</td><td>93.90955</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5633,7 +5496,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">comic-sweep-27</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/f2odnj7i' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/f2odnj7i</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">volcanic-sweep-27</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/r9n7wxbd' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/r9n7wxbd</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5645,7 +5508,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161619-f2odnj7i/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150550-r9n7wxbd/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5658,20 +5521,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: d734y8x5 with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 6ktun08v with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5683,7 +5550,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161629-d734y8x5</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150600-6ktun08v</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5695,7 +5562,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/d734y8x5' target=\"_blank\">restful-sweep-28</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/6ktun08v' target=\"_blank\">frosty-sweep-28</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5719,7 +5586,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5731,7 +5598,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/d734y8x5' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/d734y8x5</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/6ktun08v' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/6ktun08v</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5740,43 +5607,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 5212.5532 - val_loss: 3967.9011\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 3393.6797 - val_loss: 80.4883\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2073.0776 - val_loss: 3745.3311\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 3099.7207 - val_loss: 1001.7495\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2747.7412 - val_loss: 2269.5325\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3034.7158 - val_loss: 3891.0437\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2996.8442 - val_loss: 605.5511\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2910.7493 - val_loss: 3134.8782\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 3559.1384 - val_loss: 4025.3057\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 3342.5266 - val_loss: 3477.2053\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2679.6165 - val_loss: 5265.6284\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3324.4429 - val_loss: 3774.5784\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3177.4756 - val_loss: 1904.0980\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2788.7607 - val_loss: 4811.3066\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 3517.8369 - val_loss: 1941.7983\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 3227.0693 - val_loss: 1962.0704\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 2863.5540 - val_loss: 3203.8289\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 3904.5681 - val_loss: 2299.4956\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 2885.7170 - val_loss: 4794.5366\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 3450.9536 - val_loss: 2259.6421\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2875.8984 - val_loss: 1263.0577\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2481.0383 - val_loss: 5042.3735\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3479.0823 - val_loss: 471.6104\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 2957.5371 - val_loss: 2645.2654\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2815.3914 - val_loss: 2043.7354\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 5364.2373 - val_loss: 3243.1423\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2984.8733 - val_loss: 720.6061\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2163.3467 - val_loss: 2591.0791\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2099.1045 - val_loss: 2710.4534\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1971.1180 - val_loss: 2073.2129\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1896.4807 - val_loss: 1980.2386\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1665.9551 - val_loss: 1705.0850\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1392.4124 - val_loss: 3421.9128\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1961.4088 - val_loss: 1140.0253\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1738.2841 - val_loss: 352.6407\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1681.2708 - val_loss: 1030.2872\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1680.7478 - val_loss: 1086.1704\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1644.8560 - val_loss: 1271.3328\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1500.5811 - val_loss: 1444.0914\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1633.9535 - val_loss: 1536.6351\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1681.1494 - val_loss: 640.0645\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1596.6736 - val_loss: 1276.5029\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1548.2556 - val_loss: 538.3155\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1622.7384 - val_loss: 151.1122\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1440.5967 - val_loss: 1723.9224\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1644.8647 - val_loss: 1267.7657\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1488.7402 - val_loss: 1330.0953\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1673.3082 - val_loss: 472.6750\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1586.1027 - val_loss: 812.4601\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1629.5829 - val_loss: 338.8354\n"
      ]
     },
     {
@@ -5799,7 +5658,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▁▄▃▃▄▂▃▃▂▃▃▂▄▃▂▃▂▃▃▂▄▂▃</td></tr><tr><td>loss_valid</td><td>▆▁▆▂▄▆▂▅▆▆█▆▃▇▄▄▅▄▇▄▃█▂▄▄</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>3104.40723</td></tr><tr><td>loss_valid</td><td>2043.73535</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▂▂▂▂▁▁▂▂▂▂▁▁▁▂▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▂▆▆▅▅▄█▃▁▃▃▃▄▄▂▃▂▁▄▃▄▂▂▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>1629.58289</td></tr><tr><td>loss_valid</td><td>338.83539</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5811,7 +5670,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">restful-sweep-28</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/d734y8x5' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/d734y8x5</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">frosty-sweep-28</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/6ktun08v' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/6ktun08v</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5823,7 +5682,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161629-d734y8x5/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150600-6ktun08v/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5836,20 +5695,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 687nvah6 with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 0adcpqyx with config:\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.0005\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5861,7 +5724,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161639-687nvah6</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150611-0adcpqyx</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5873,7 +5736,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/687nvah6' target=\"_blank\">volcanic-sweep-29</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0adcpqyx' target=\"_blank\">vibrant-sweep-29</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5897,7 +5760,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5909,7 +5772,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/687nvah6' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/687nvah6</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0adcpqyx' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0adcpqyx</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5918,43 +5781,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 20ms/step - loss: 2057.4780 - val_loss: 1642.8903\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1778.9401 - val_loss: 1510.5441\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1745.7764 - val_loss: 1377.4623\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1499.6112 - val_loss: 1247.4550\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1428.1172 - val_loss: 1115.1133\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 1302.2841 - val_loss: 982.7160\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1195.2408 - val_loss: 851.3364\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 1055.9851 - val_loss: 722.6569\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 819.0823 - val_loss: 595.1212\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 643.3785 - val_loss: 468.8297\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 477.4051 - val_loss: 343.1091\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 346.3425 - val_loss: 216.0155\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 196.4232 - val_loss: 122.1775\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 125.4360 - val_loss: 115.7195\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 134.2050 - val_loss: 106.9334\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 112.0018 - val_loss: 99.2267\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 92.5960 - val_loss: 97.9594\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 85.7069 - val_loss: 86.3893\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 85.6881 - val_loss: 79.1069\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 77.3293 - val_loss: 76.5086\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 79.5086 - val_loss: 69.5775\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 73.2312 - val_loss: 67.1195\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 68.7590 - val_loss: 62.9301\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 63.8377 - val_loss: 62.5621\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 61.9520 - val_loss: 59.4472\n"
+      "9/9 [==============================] - 0s 16ms/step - loss: 5243.3535 - val_loss: 904.3698\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2976.1763 - val_loss: 334.5070\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2414.8293 - val_loss: 1634.5923\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2157.5586 - val_loss: 521.8677\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1724.0922 - val_loss: 3024.1619\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2038.9800 - val_loss: 871.9214\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1737.5328 - val_loss: 2164.0144\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1807.8435 - val_loss: 1131.5868\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1626.2103 - val_loss: 2657.7246\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1745.4409 - val_loss: 879.2615\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1501.9691 - val_loss: 3027.0879\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1768.7504 - val_loss: 1966.6486\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1612.0194 - val_loss: 2309.8992\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1535.0822 - val_loss: 1757.2344\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1683.4514 - val_loss: 781.1623\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1448.8610 - val_loss: 909.9416\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1629.3881 - val_loss: 933.7205\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1544.8312 - val_loss: 1787.0171\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1554.8396 - val_loss: 2094.8757\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1685.0527 - val_loss: 1016.0782\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1597.1538 - val_loss: 607.2136\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 1427.4327 - val_loss: 2279.0837\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1740.4875 - val_loss: 697.6199\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 1385.7173 - val_loss: 2181.8804\n",
+      "9/9 [==============================] - 0s 7ms/step - loss: 1484.2804 - val_loss: 2207.4661\n"
      ]
     },
     {
@@ -5977,7 +5832,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▇▆▆▅▅▄▄▃▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▇▇▆▆▅▅▄▃▃▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>61.14803</td></tr><tr><td>loss_valid</td><td>59.44715</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▄▃▂▂▂▂▂▁▂▁▂▁▁▂▁▁▁▁▂▁▁▂▁▁</td></tr><tr><td>loss_valid</td><td>▂▁▄▁█▂▆▃▇▂█▅▆▅▂▂▃▅▆▃▂▆▂▆▆</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>1484.2804</td></tr><tr><td>loss_valid</td><td>2207.46606</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -5989,7 +5844,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">volcanic-sweep-29</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/687nvah6' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/687nvah6</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">vibrant-sweep-29</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0adcpqyx' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0adcpqyx</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6001,7 +5856,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161639-687nvah6/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150611-0adcpqyx/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6014,20 +5869,24 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 0day9f9o with config:\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: sigmoid\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 9rwyhlzg with config:\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tactivation: relu\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tbatch_size: 32\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tepochs: 25\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [8]\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \tfc_layer_size: [16, 16]\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tinput_dim: 11\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 0.001\n",
-      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: adam\n"
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \toptimizer: sgd\n",
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.18.7"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6039,7 +5898,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241204_161650-0day9f9o</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_150621-9rwyhlzg</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6051,7 +5910,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0day9f9o' target=\"_blank\">autumn-sweep-30</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/9rwyhlzg' target=\"_blank\">copper-sweep-30</a></strong> to <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>Sweep page: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6075,7 +5934,7 @@
     {
      "data": {
       "text/html": [
-       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/004ladd1</a>"
+       " View sweep at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/sweeps/ahk29776</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6087,7 +5946,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0day9f9o' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0day9f9o</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/9rwyhlzg' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/9rwyhlzg</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6096,43 +5955,35 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/johannes/opt/anaconda3/envs/py4ds24/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 19ms/step - loss: 1101.1085 - val_loss: 774.8168\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 807.8607 - val_loss: 652.3983\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 768.3516 - val_loss: 529.1523\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 702.2194 - val_loss: 424.2300\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 464.3943 - val_loss: 346.3944\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 347.3051 - val_loss: 295.5074\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 306.0117 - val_loss: 251.4182\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 305.7262 - val_loss: 206.8849\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 211.6295 - val_loss: 166.4550\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 168.7272 - val_loss: 138.4840\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 151.2613 - val_loss: 134.8421\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 128.7432 - val_loss: 125.7724\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 126.9040 - val_loss: 119.2986\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 117.7580 - val_loss: 112.8825\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 112.1060 - val_loss: 106.8671\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 110.8749 - val_loss: 100.6550\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 98.6114 - val_loss: 94.8495\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 96.9146 - val_loss: 88.7029\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 85.8564 - val_loss: 82.9656\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 82.6416 - val_loss: 76.9427\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 71.5635 - val_loss: 71.1004\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 69.3901 - val_loss: 65.2846\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 58.5716 - val_loss: 59.7770\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 57.7345 - val_loss: 54.3677\n",
-      "\u001b[1m9/9\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 48.4113 - val_loss: 50.2928\n"
+      "9/9 [==============================] - 0s 15ms/step - loss: 3147.4214 - val_loss: 1400.6484\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2861.6157 - val_loss: 4199.2031\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3062.1250 - val_loss: 4306.7310\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 3301.1218 - val_loss: 1292.0813\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3066.9463 - val_loss: 1307.4386\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3041.5464 - val_loss: 963.0196\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3038.1899 - val_loss: 154.1960\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2728.8474 - val_loss: 4085.3457\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3040.0713 - val_loss: 143.8178\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 2486.6836 - val_loss: 5893.2817\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3478.4673 - val_loss: 783.0181\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3082.0720 - val_loss: 1609.5492\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3067.0923 - val_loss: 616.5749\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2805.8650 - val_loss: 2078.2922\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 2944.6807 - val_loss: 3550.8523\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3182.8975 - val_loss: 3297.2385\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3328.1316 - val_loss: 784.3086\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2756.2271 - val_loss: 3353.5234\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3071.0085 - val_loss: 3856.9495\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 2968.2285 - val_loss: 3776.3821\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3232.6123 - val_loss: 2252.9871\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2913.7065 - val_loss: 4113.8730\n",
+      "9/9 [==============================] - 0s 9ms/step - loss: 3247.5635 - val_loss: 662.9700\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 2988.7654 - val_loss: 2378.6729\n",
+      "9/9 [==============================] - 0s 8ms/step - loss: 3109.7734 - val_loss: 101.4421\n"
      ]
     },
     {
@@ -6155,7 +6006,7 @@
        "            padding: 10px;\n",
        "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>█▇▆▅▄▃▃▃▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>loss_valid</td><td>█▇▆▅▄▃▃▃▂▂▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>48.79605</td></tr><tr><td>loss_valid</td><td>50.29279</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>▆▄▅▇▅▅▅▃▅▁█▅▅▃▄▆▇▃▅▄▆▄▆▅▅</td></tr><tr><td>loss_valid</td><td>▃▆▆▂▂▂▁▆▁█▂▃▂▃▅▅▂▅▆▅▄▆▂▄▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>loss_train</td><td>3109.77344</td></tr><tr><td>loss_valid</td><td>101.44208</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6167,7 +6018,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">autumn-sweep-30</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/0day9f9o' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/0day9f9o</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">copper-sweep-30</strong> at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo/runs/9rwyhlzg' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo/runs/9rwyhlzg</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/sweeps-demo' target=\"_blank\">https://wandb.ai/iaai-hdm/sweeps-demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6179,7 +6030,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20241204_161650-0day9f9o/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_150621-9rwyhlzg/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -6195,7 +6046,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 89,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -6365,7 +6216,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 88,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -6383,7 +6234,7 @@
  "metadata": {
   "celltoolbar": "Slideshow",
   "kernelspec": {
-   "display_name": "py4ds24",
+   "display_name": "python3",
    "language": "python",
    "name": "python3"
   },
@@ -6397,7 +6248,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.7"
+   "version": "3.9.20"
   },
   "toc": {
    "base_numbering": 1,
diff --git a/WandBexperiments/WandB-HousePricePrediction3.ipynb b/WandBexperiments/WandB-HousePricePrediction3.ipynb
index 178eedb33d67fdab0280dbd223be966db213b21a..9658254e266c2303fcf1e5ad7f91c28007d1c0df 100644
--- a/WandBexperiments/WandB-HousePricePrediction3.ipynb
+++ b/WandBexperiments/WandB-HousePricePrediction3.ipynb
@@ -49,7 +49,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -58,32 +58,38 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2023-12-14 15:40:59.101945: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
+      "2024-12-11 15:20:11.738818: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "2024-12-11 15:20:11.739148: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "2024-12-11 15:20:11.740269: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "2024-12-11 15:20:11.747246: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+      "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
+      "2024-12-11 15:20:12.921364: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
      ]
     }
    ],
    "source": [
     "import wandb\n",
-    "from wandb.keras import WandbMetricsLogger, WandbModelCheckpoint"
+    "from wandb.integration.keras import WandbMetricsLogger, WandbModelCheckpoint"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
+      "Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Using wandb-core as the SDK backend.  Please refer to https://wandb.me/wandb-core for more information.\n",
       "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mjohannes-maucher\u001b[0m (\u001b[33miaai-hdm\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
      ]
     },
@@ -93,7 +99,7 @@
        "True"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -111,7 +117,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -137,26 +143,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/html": [
-       "wandb version 0.16.1 is available!  To upgrade, please run:\n",
-       " $ pip install wandb --upgrade"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning: Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "  return self.__pydantic_serializer__.to_python(\n"
+     ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.16.0"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -168,7 +173,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20231214_162115-hq3dbraz</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_152029-lj6fvssk</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -180,7 +185,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/hq3dbraz' target=\"_blank\">comfy-shadow-29</a></strong> to <a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/lj6fvssk' target=\"_blank\">decent-valley-35</a></strong> to <a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -204,7 +209,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/hq3dbraz' target=\"_blank\">https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/hq3dbraz</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/lj6fvssk' target=\"_blank\">https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/lj6fvssk</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -216,13 +221,13 @@
     {
      "data": {
       "text/html": [
-       "<button onClick=\"this.nextSibling.style.display='block';this.style.display='none';\">Display W&B run</button><iframe src='https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/hq3dbraz?jupyter=true' style='border:none;width:100%;height:420px;display:none;'></iframe>"
+       "<button onClick=\"this.nextSibling.style.display='block';this.style.display='none';\">Display W&B run</button><iframe src='https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/lj6fvssk?jupyter=true' style='border:none;width:100%;height:420px;display:none;'></iframe>"
       ],
       "text/plain": [
-       "<wandb.sdk.wandb_run.Run at 0x15f390710>"
+       "<wandb.sdk.wandb_run.Run at 0x7f40a7bbefa0>"
       ]
      },
-     "execution_count": 70,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -272,7 +277,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 7,
    "metadata": {
     "slideshow": {
      "slide_type": "skip"
@@ -290,7 +295,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 9,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -379,15 +384,16 @@
        "4         3        4.0  4116    85266  971226"
       ]
      },
-     "execution_count": 34,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "#path=\"/Users/maucher/ownCloud/Workshops/Data/Houses-dataset/Houses Dataset/\"  #MacBook\n",
-    "path=\"/Users/johannes/DataSets/Houses-dataset/Houses Dataset/\"\n",
+    "#path=\"/Users/johannes/DataSets/Houses-dataset/Houses Dataset/\"\n",
     "#path=\"/Users/johannesmaucher/DataSets/Houses-dataset/Houses Dataset/\"\n",
+    "path=\"../Data/\"\n",
     "file=\"HousesInfo.txt\"\n",
     "cols = [\"bedrooms\", \"bathrooms\", \"area\", \"zipcode\", \"price\"]\n",
     "df = pd.read_csv(path+file, sep=\" \", header=None, names=cols, decimal=\".\")\n",
@@ -396,7 +402,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 10,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -512,7 +518,7 @@
        "max     10.000000    7.000000  9583.000000  98021.000000  5.858000e+06"
       ]
      },
-     "execution_count": 35,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -535,7 +541,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 11,
    "metadata": {
     "scrolled": true,
     "slideshow": {
@@ -549,7 +555,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 12,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -564,7 +570,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 13,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -680,7 +686,7 @@
        "max     10.000000    7.000000  9536.00000  94531.000000  5.858000e+06"
       ]
      },
-     "execution_count": 38,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -702,7 +708,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 14,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -724,7 +730,7 @@
        "Name: count, dtype: int64"
       ]
      },
-     "execution_count": 39,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -746,7 +752,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 15,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -771,7 +777,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 16,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -800,7 +806,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 17,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -826,7 +832,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 18,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -852,7 +858,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 19,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -878,7 +884,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -887,7 +893,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 21,
    "metadata": {
     "slideshow": {
      "slide_type": "skip"
@@ -921,7 +927,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 22,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -942,7 +948,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": 23,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -953,15 +959,15 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Model: \"sequential_3\"\n",
+      "Model: \"sequential\"\n",
       "_________________________________________________________________\n",
       " Layer (type)                Output Shape              Param #   \n",
       "=================================================================\n",
-      " dense_9 (Dense)             (None, 5)                 60        \n",
+      " dense (Dense)               (None, 5)                 60        \n",
       "                                                                 \n",
-      " dense_10 (Dense)            (None, 5)                 30        \n",
+      " dense_1 (Dense)             (None, 5)                 30        \n",
       "                                                                 \n",
-      " dense_11 (Dense)            (None, 1)                 6         \n",
+      " dense_2 (Dense)             (None, 1)                 6         \n",
       "                                                                 \n",
       "=================================================================\n",
       "Total params: 96 (384.00 Byte)\n",
@@ -969,6 +975,14 @@
       "Non-trainable params: 0 (0.00 Byte)\n",
       "_________________________________________________________________\n"
      ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-12-11 15:22:25.879061: W tensorflow/core/common_runtime/gpu/gpu_device.cc:2256] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n",
+      "Skipping registering GPU devices...\n"
+     ]
     }
    ],
    "source": [
@@ -989,7 +1003,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 24,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -1014,9 +1028,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 74,
+   "execution_count": 25,
    "metadata": {
-    "scrolled": false,
     "slideshow": {
      "slide_type": "fragment"
     }
@@ -1035,434 +1048,420 @@
      "text": [
       "[INFO] training model...\n",
       "Epoch 1/200\n",
-      " 1/36 [..............................] - ETA: 13s - loss: 453.4559"
+      " 1/36 [..............................] - ETA: 19s - loss: 348.3860"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/Users/johannes/opt/anaconda3/envs/ws2324/lib/python3.11/site-packages/keras/src/engine/training.py:3103: UserWarning:\n",
-      "\n",
-      "You are saving your model as an HDF5 file via `model.save()`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')`.\n",
-      "\n"
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/keras/src/engine/training.py:3103: UserWarning: You are saving your model as an HDF5 file via `model.save()`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')`.\n",
+      "  saving_api.save_model(\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "36/36 [==============================] - 1s 10ms/step - loss: 368.6832 - val_loss: 148.8992\n",
+      "36/36 [==============================] - 1s 14ms/step - loss: 297.4948 - val_loss: 152.8385\n",
       "Epoch 2/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 80.7166 - val_loss: 46.1786\n",
+      "36/36 [==============================] - 0s 9ms/step - loss: 116.5750 - val_loss: 104.1984\n",
       "Epoch 3/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 42.7075 - val_loss: 43.0805\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 79.6488 - val_loss: 74.3411\n",
       "Epoch 4/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 40.5723 - val_loss: 44.1839\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 61.9072 - val_loss: 66.4100\n",
       "Epoch 5/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 38.1065 - val_loss: 37.8170\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 56.1093 - val_loss: 60.0611\n",
       "Epoch 6/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 35.2672 - val_loss: 36.9955\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 50.6930 - val_loss: 56.4471\n",
       "Epoch 7/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 33.9480 - val_loss: 35.0087\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 46.7227 - val_loss: 53.3165\n",
       "Epoch 8/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 33.2558 - val_loss: 33.7160\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 43.2560 - val_loss: 49.1482\n",
       "Epoch 9/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 32.4519 - val_loss: 32.8940\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 39.8542 - val_loss: 44.6555\n",
       "Epoch 10/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 34.2230 - val_loss: 35.6282\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 39.2850 - val_loss: 43.1108\n",
       "Epoch 11/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 32.0126 - val_loss: 32.1396\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 35.9750 - val_loss: 41.4588\n",
       "Epoch 12/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 33.3927 - val_loss: 31.6923\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 34.4045 - val_loss: 41.0125\n",
       "Epoch 13/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 30.7464 - val_loss: 31.3319\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 35.1498 - val_loss: 39.7178\n",
       "Epoch 14/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 30.1453 - val_loss: 31.2441\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 33.2762 - val_loss: 37.6679\n",
       "Epoch 15/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 30.4885 - val_loss: 31.4420\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 36.5173 - val_loss: 44.3092\n",
       "Epoch 16/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 29.6253 - val_loss: 31.9232\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 32.3283 - val_loss: 36.0409\n",
       "Epoch 17/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 28.5344 - val_loss: 30.7912\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 31.7758 - val_loss: 35.0048\n",
       "Epoch 18/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 29.0765 - val_loss: 30.4293\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 31.1835 - val_loss: 34.6820\n",
       "Epoch 19/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 28.5036 - val_loss: 30.3541\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 31.8690 - val_loss: 38.0327\n",
       "Epoch 20/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 28.6232 - val_loss: 30.1611\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 30.2336 - val_loss: 34.7617\n",
       "Epoch 21/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 28.1789 - val_loss: 29.2029\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 30.8734 - val_loss: 34.5224\n",
       "Epoch 22/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 28.4372 - val_loss: 28.8596\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 30.5323 - val_loss: 34.5281\n",
       "Epoch 23/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 27.2304 - val_loss: 28.7550\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 29.2379 - val_loss: 33.1697\n",
       "Epoch 24/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 25.9992 - val_loss: 28.6851\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 28.0987 - val_loss: 37.2576\n",
       "Epoch 25/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 26.8993 - val_loss: 27.4723\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 30.1063 - val_loss: 33.4814\n",
       "Epoch 26/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 27.3611 - val_loss: 27.1213\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 30.0562 - val_loss: 31.8545\n",
       "Epoch 27/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 26.5069 - val_loss: 28.1960\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 28.2204 - val_loss: 32.9491\n",
       "Epoch 28/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 28.7183 - val_loss: 29.3400\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 29.2745 - val_loss: 31.3730\n",
       "Epoch 29/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 26.6514 - val_loss: 27.5701\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 28.1672 - val_loss: 32.6517\n",
       "Epoch 30/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 24.6572 - val_loss: 27.0300\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 27.5084 - val_loss: 31.2277\n",
       "Epoch 31/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 25.1781 - val_loss: 26.2799\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 27.1142 - val_loss: 30.5172\n",
       "Epoch 32/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 24.9494 - val_loss: 25.8184\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 26.4334 - val_loss: 32.0971\n",
       "Epoch 33/200\n",
-      "36/36 [==============================] - 0s 10ms/step - loss: 25.2612 - val_loss: 25.7746\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 27.4815 - val_loss: 29.8150\n",
       "Epoch 34/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 25.0562 - val_loss: 25.4987\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 26.5916 - val_loss: 30.8043\n",
       "Epoch 35/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 25.9761 - val_loss: 24.8577\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 26.9644 - val_loss: 29.3778\n",
       "Epoch 36/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 23.7805 - val_loss: 27.4591\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 26.2797 - val_loss: 29.2329\n",
       "Epoch 37/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 25.1403 - val_loss: 24.7374\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 26.5007 - val_loss: 28.4835\n",
       "Epoch 38/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 24.4368 - val_loss: 24.9313\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 26.4787 - val_loss: 28.0367\n",
       "Epoch 39/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 24.1269 - val_loss: 24.5913\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 26.2859 - val_loss: 35.1447\n",
       "Epoch 40/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 23.6331 - val_loss: 24.3536\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 26.7047 - val_loss: 29.8450\n",
       "Epoch 41/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 23.2781 - val_loss: 24.2358\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 25.2541 - val_loss: 27.9730\n",
       "Epoch 42/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 23.5278 - val_loss: 24.0423\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 26.8610 - val_loss: 28.1742\n",
       "Epoch 43/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 23.2747 - val_loss: 24.2737\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 26.3725 - val_loss: 30.2513\n",
       "Epoch 44/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 24.5821 - val_loss: 27.0743\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 25.4151 - val_loss: 27.8060\n",
       "Epoch 45/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 25.3157 - val_loss: 24.2971\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 24.2105 - val_loss: 27.9136\n",
       "Epoch 46/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 24.3025 - val_loss: 24.4064\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 25.1632 - val_loss: 27.9700\n",
       "Epoch 47/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 23.5870 - val_loss: 24.1735\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 25.8815 - val_loss: 29.2222\n",
       "Epoch 48/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.8370 - val_loss: 22.9201\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 26.0424 - val_loss: 27.4229\n",
       "Epoch 49/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 23.1851 - val_loss: 23.8346\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 23.6197 - val_loss: 26.6145\n",
       "Epoch 50/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.9863 - val_loss: 22.6802\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 23.2840 - val_loss: 27.2830\n",
       "Epoch 51/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 23.7785 - val_loss: 22.7434\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 23.4154 - val_loss: 28.2701\n",
       "Epoch 52/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.9845 - val_loss: 23.9078\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 24.4695 - val_loss: 25.8199\n",
       "Epoch 53/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.0630 - val_loss: 23.6710\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.8014 - val_loss: 26.4189\n",
       "Epoch 54/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.5279 - val_loss: 22.5783\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 24.6135 - val_loss: 25.8630\n",
       "Epoch 55/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 21.8647 - val_loss: 25.0541\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 26.1811 - val_loss: 25.9498\n",
       "Epoch 56/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 28.0221 - val_loss: 27.4632\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 25.0596 - val_loss: 26.8833\n",
       "Epoch 57/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 23.8739 - val_loss: 25.6206\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 23.5387 - val_loss: 25.9834\n",
       "Epoch 58/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 25.2780 - val_loss: 22.8436\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 23.1306 - val_loss: 25.9031\n",
       "Epoch 59/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.9568 - val_loss: 22.5444\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 23.9577 - val_loss: 25.4553\n",
       "Epoch 60/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.2654 - val_loss: 22.4785\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.9423 - val_loss: 24.8112\n",
       "Epoch 61/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 21.8960 - val_loss: 28.9865\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 23.9962 - val_loss: 25.0956\n",
       "Epoch 62/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 25.6033 - val_loss: 23.7954\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.4687 - val_loss: 25.6558\n",
       "Epoch 63/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 22.5994 - val_loss: 23.4162\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.0420 - val_loss: 26.5763\n",
       "Epoch 64/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 24.4556 - val_loss: 22.5658\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 24.0137 - val_loss: 27.8816\n",
       "Epoch 65/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.0665 - val_loss: 23.0658\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 24.3461 - val_loss: 25.9704\n",
       "Epoch 66/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 21.7000 - val_loss: 22.7972\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 25.9346 - val_loss: 27.3631\n",
       "Epoch 67/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.9885 - val_loss: 22.5635\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.9955 - val_loss: 24.5011\n",
       "Epoch 68/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.2071 - val_loss: 24.0364\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.9219 - val_loss: 25.4404\n",
       "Epoch 69/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 23.1946 - val_loss: 22.5356\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.6278 - val_loss: 24.9445\n",
       "Epoch 70/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.5921 - val_loss: 22.5250\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.6822 - val_loss: 25.4029\n",
       "Epoch 71/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 20.8956 - val_loss: 22.6348\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.5671 - val_loss: 27.3867\n",
       "Epoch 72/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 20.9827 - val_loss: 22.3788\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.8386 - val_loss: 24.3529\n",
       "Epoch 73/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.6389 - val_loss: 22.6659\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.7251 - val_loss: 25.1726\n",
       "Epoch 74/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.4987 - val_loss: 22.5173\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.8851 - val_loss: 25.2024\n",
       "Epoch 75/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.1780 - val_loss: 22.3873\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 26.3055 - val_loss: 26.0592\n",
       "Epoch 76/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.1640 - val_loss: 23.3701\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.2229 - val_loss: 24.4389\n",
       "Epoch 77/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 23.0602 - val_loss: 22.5302\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.7993 - val_loss: 25.0656\n",
       "Epoch 78/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.7679 - val_loss: 22.1282\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.8135 - val_loss: 24.3139\n",
       "Epoch 79/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.3859 - val_loss: 22.6977\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.0681 - val_loss: 23.9738\n",
       "Epoch 80/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.1542 - val_loss: 22.9496\n",
-      "Epoch 81/200\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.1644 - val_loss: 22.2099\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.7443 - val_loss: 24.5303\n",
+      "Epoch 81/200\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.7907 - val_loss: 25.8377\n",
       "Epoch 82/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 21.4351 - val_loss: 22.4233\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.5791 - val_loss: 27.8590\n",
       "Epoch 83/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 24.1943 - val_loss: 21.9921\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.3939 - val_loss: 23.7070\n",
       "Epoch 84/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.9398 - val_loss: 22.4203\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.2724 - val_loss: 24.7774\n",
       "Epoch 85/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.8448 - val_loss: 23.0466\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.3185 - val_loss: 24.7248\n",
       "Epoch 86/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 20.4952 - val_loss: 22.1617\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.8927 - val_loss: 28.1212\n",
       "Epoch 87/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 20.9473 - val_loss: 22.3945\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.4930 - val_loss: 24.1461\n",
       "Epoch 88/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.1045 - val_loss: 22.2045\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.1706 - val_loss: 24.5176\n",
       "Epoch 89/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 20.7915 - val_loss: 22.6854\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.7148 - val_loss: 23.7441\n",
       "Epoch 90/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.3013 - val_loss: 22.7373\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.9583 - val_loss: 24.5936\n",
       "Epoch 91/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.3213 - val_loss: 23.0437\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.4744 - val_loss: 23.7912\n",
       "Epoch 92/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.2227 - val_loss: 22.5953\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.9535 - val_loss: 24.3224\n",
       "Epoch 93/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.1950 - val_loss: 23.0190\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.9270 - val_loss: 23.5168\n",
       "Epoch 94/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.8093 - val_loss: 22.3050\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.3010 - val_loss: 23.9190\n",
       "Epoch 95/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.7370 - val_loss: 22.3179\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.7588 - val_loss: 25.6394\n",
       "Epoch 96/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.5914 - val_loss: 24.9662\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.9004 - val_loss: 23.5203\n",
       "Epoch 97/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.0793 - val_loss: 22.2542\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.2563 - val_loss: 25.0295\n",
       "Epoch 98/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.8559 - val_loss: 22.8644\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.5036 - val_loss: 23.5227\n",
       "Epoch 99/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.2244 - val_loss: 23.6200\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.6022 - val_loss: 23.9475\n",
       "Epoch 100/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.1521 - val_loss: 22.3524\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.7756 - val_loss: 27.1224\n",
       "Epoch 101/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 21.1975 - val_loss: 22.6206\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.6024 - val_loss: 25.9434\n",
       "Epoch 102/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.6409 - val_loss: 22.0760\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.4874 - val_loss: 24.5217\n",
       "Epoch 103/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.9423 - val_loss: 22.0852\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.8775 - val_loss: 24.3964\n",
       "Epoch 104/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.4715 - val_loss: 22.4526\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.3110 - val_loss: 28.6047\n",
       "Epoch 105/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.4149 - val_loss: 23.2361\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.7218 - val_loss: 24.2221\n",
       "Epoch 106/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.1629 - val_loss: 21.7931\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.4239 - val_loss: 24.8501\n",
       "Epoch 107/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.2612 - val_loss: 23.2504\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.4484 - val_loss: 23.7427\n",
       "Epoch 108/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.6203 - val_loss: 21.8926\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.9045 - val_loss: 23.7967\n",
       "Epoch 109/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.5966 - val_loss: 22.6508\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.6359 - val_loss: 26.0934\n",
       "Epoch 110/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.2858 - val_loss: 21.9572\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 23.0777 - val_loss: 24.4844\n",
       "Epoch 111/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 20.3859 - val_loss: 21.7042\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.2129 - val_loss: 25.2283\n",
       "Epoch 112/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.9898 - val_loss: 24.6485\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.7619 - val_loss: 27.5093\n",
       "Epoch 113/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.4812 - val_loss: 23.4120\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.4407 - val_loss: 23.7882\n",
       "Epoch 114/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 21.0362 - val_loss: 21.9167\n",
+      "36/36 [==============================] - 0s 13ms/step - loss: 21.9684 - val_loss: 23.9593\n",
       "Epoch 115/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.6347 - val_loss: 22.1545\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.9028 - val_loss: 23.8799\n",
       "Epoch 116/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.5080 - val_loss: 22.0843\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 23.5625 - val_loss: 28.6673\n",
       "Epoch 117/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.6799 - val_loss: 21.7090\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.1290 - val_loss: 23.3449\n",
       "Epoch 118/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.8640 - val_loss: 21.6910\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.7015 - val_loss: 24.7745\n",
       "Epoch 119/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.7317 - val_loss: 21.6701\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.5554 - val_loss: 23.1474\n",
       "Epoch 120/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.2778 - val_loss: 24.0167\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.6079 - val_loss: 25.2022\n",
       "Epoch 121/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.8706 - val_loss: 21.6477\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.6175 - val_loss: 23.2323\n",
       "Epoch 122/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 20.4178 - val_loss: 21.2848\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.4344 - val_loss: 24.2771\n",
       "Epoch 123/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.6042 - val_loss: 21.9293\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 23.0827 - val_loss: 23.7070\n",
       "Epoch 124/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.3648 - val_loss: 23.8413\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 23.3046 - val_loss: 22.8001\n",
       "Epoch 125/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.9572 - val_loss: 22.7195\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.3863 - val_loss: 24.6790\n",
       "Epoch 126/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.6655 - val_loss: 21.7151\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.2452 - val_loss: 24.5412\n",
       "Epoch 127/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.9576 - val_loss: 21.2512\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.2053 - val_loss: 24.1618\n",
       "Epoch 128/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.6696 - val_loss: 22.7996\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.5028 - val_loss: 24.3106\n",
       "Epoch 129/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.2914 - val_loss: 21.6856\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.0589 - val_loss: 27.0665\n",
       "Epoch 130/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 20.2118 - val_loss: 21.9723\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.6276 - val_loss: 23.2823\n",
       "Epoch 131/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.9598 - val_loss: 21.4784\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.6052 - val_loss: 23.8948\n",
       "Epoch 132/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.8378 - val_loss: 22.9300\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 19.8773 - val_loss: 24.3369\n",
       "Epoch 133/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.5727 - val_loss: 21.5604\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.8574 - val_loss: 23.4944\n",
       "Epoch 134/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.8544 - val_loss: 21.8171\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.3772 - val_loss: 23.4662\n",
       "Epoch 135/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 19.6925 - val_loss: 21.8199\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.8146 - val_loss: 23.9780\n",
       "Epoch 136/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.7413 - val_loss: 22.0907\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.1000 - val_loss: 26.5379\n",
       "Epoch 137/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.2669 - val_loss: 21.6934\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.4360 - val_loss: 23.0984\n",
       "Epoch 138/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.0524 - val_loss: 21.6050\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.7330 - val_loss: 23.4848\n",
       "Epoch 139/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.4848 - val_loss: 21.5896\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.5768 - val_loss: 23.0029\n",
       "Epoch 140/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.0315 - val_loss: 21.7463\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.8886 - val_loss: 23.5036\n",
       "Epoch 141/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 19.9536 - val_loss: 21.7161\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.0226 - val_loss: 25.8811\n",
       "Epoch 142/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.9441 - val_loss: 25.5864\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.7344 - val_loss: 23.7889\n",
       "Epoch 143/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 23.9329 - val_loss: 23.2412\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.6791 - val_loss: 23.7539\n",
       "Epoch 144/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 22.5884 - val_loss: 22.8016\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.2107 - val_loss: 23.6985\n",
       "Epoch 145/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.1625 - val_loss: 21.9709\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.2355 - val_loss: 23.3571\n",
       "Epoch 146/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.5099 - val_loss: 22.5808\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.8682 - val_loss: 24.8680\n",
       "Epoch 147/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.4417 - val_loss: 21.9817\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.0504 - val_loss: 24.0219\n",
       "Epoch 148/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.9020 - val_loss: 22.9248\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.5898 - val_loss: 23.3702\n",
       "Epoch 149/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 22.6936 - val_loss: 21.8218\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 19.9044 - val_loss: 23.3161\n",
       "Epoch 150/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.4584 - val_loss: 21.9148\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.5167 - val_loss: 22.7475\n",
       "Epoch 151/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.6080 - val_loss: 22.7796\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.1178 - val_loss: 23.7518\n",
       "Epoch 152/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.3425 - val_loss: 21.4871\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.6536 - val_loss: 23.4216\n",
       "Epoch 153/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.9670 - val_loss: 22.0932\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.4504 - val_loss: 23.0291\n",
       "Epoch 154/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.5355 - val_loss: 21.9120\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.4134 - val_loss: 24.0464\n",
       "Epoch 155/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.3326 - val_loss: 22.1213\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.3724 - val_loss: 24.5132\n",
       "Epoch 156/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.5591 - val_loss: 21.4177\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 21.0193 - val_loss: 23.0069\n",
       "Epoch 157/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.1174 - val_loss: 24.7002\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.9327 - val_loss: 24.5022\n",
       "Epoch 158/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.2395 - val_loss: 23.9401\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.5224 - val_loss: 26.3870\n",
       "Epoch 159/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 19.2409 - val_loss: 22.0839\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.3366 - val_loss: 23.9919\n",
       "Epoch 160/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.6042 - val_loss: 22.7359\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.8377 - val_loss: 24.6605\n",
       "Epoch 161/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 19.9842 - val_loss: 21.7851\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.1006 - val_loss: 23.3956\n",
       "Epoch 162/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.4122 - val_loss: 21.8690\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.0809 - val_loss: 28.2938\n",
       "Epoch 163/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.8345 - val_loss: 21.7872\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 23.2907 - val_loss: 24.4376\n",
       "Epoch 164/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 20.5294 - val_loss: 21.5674\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.1343 - val_loss: 24.9663\n",
       "Epoch 165/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.5079 - val_loss: 23.1199\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 24.0027 - val_loss: 24.7370\n",
       "Epoch 166/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 19.3260 - val_loss: 22.9873\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 22.6390 - val_loss: 24.6418\n",
       "Epoch 167/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 21.6509 - val_loss: 21.6373\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.7675 - val_loss: 23.4675\n",
       "Epoch 168/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.2129 - val_loss: 21.5401\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.8583 - val_loss: 23.1340\n",
       "Epoch 169/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.1059 - val_loss: 20.9587\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.8409 - val_loss: 27.3538\n",
       "Epoch 170/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.2090 - val_loss: 21.4236\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 23.0693 - val_loss: 22.7891\n",
       "Epoch 171/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 19.9237 - val_loss: 21.1320\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.9640 - val_loss: 26.5608\n",
       "Epoch 172/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.3166 - val_loss: 21.0516\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.6638 - val_loss: 23.2620\n",
       "Epoch 173/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.5764 - val_loss: 21.4573\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.7828 - val_loss: 25.0352\n",
       "Epoch 174/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.5839 - val_loss: 21.7679\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 19.9696 - val_loss: 23.7528\n",
       "Epoch 175/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.5698 - val_loss: 21.6499\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.6126 - val_loss: 22.9513\n",
       "Epoch 176/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.8062 - val_loss: 21.1697\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 19.4461 - val_loss: 23.6459\n",
       "Epoch 177/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.0208 - val_loss: 22.1455\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.3428 - val_loss: 23.8201\n",
       "Epoch 178/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 19.0114 - val_loss: 22.2846\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.5090 - val_loss: 22.6883\n",
       "Epoch 179/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.9753 - val_loss: 21.6587\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.3378 - val_loss: 26.1167\n",
       "Epoch 180/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.6799 - val_loss: 21.0560\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.3767 - val_loss: 23.3559\n",
       "Epoch 181/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 23.3574 - val_loss: 24.5357\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.9094 - val_loss: 22.9941\n",
       "Epoch 182/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 19.6176 - val_loss: 21.8934\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.6354 - val_loss: 23.2996\n",
       "Epoch 183/200\n",
-      "36/36 [==============================] - 0s 9ms/step - loss: 19.2490 - val_loss: 22.0600\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 19.1503 - val_loss: 23.6679\n",
       "Epoch 184/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.2910 - val_loss: 21.7559\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.0654 - val_loss: 25.0161\n",
       "Epoch 185/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 19.9332 - val_loss: 22.5011\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.4167 - val_loss: 23.6347\n",
       "Epoch 186/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.0733 - val_loss: 21.3785\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.9340 - val_loss: 23.0916\n",
       "Epoch 187/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.0310 - val_loss: 22.0279\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 22.4903 - val_loss: 23.2802\n",
       "Epoch 188/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 20.1000 - val_loss: 23.2720\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.3012 - val_loss: 23.6138\n",
       "Epoch 189/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.6536 - val_loss: 22.1121\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 19.6231 - val_loss: 23.3821\n",
       "Epoch 190/200\n",
-      "36/36 [==============================] - 0s 7ms/step - loss: 21.3965 - val_loss: 21.7402\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.0795 - val_loss: 23.8365\n",
       "Epoch 191/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.9201 - val_loss: 22.2865\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.8102 - val_loss: 25.0880\n",
       "Epoch 192/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.4532 - val_loss: 21.6405\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.4149 - val_loss: 23.3948\n",
       "Epoch 193/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.8956 - val_loss: 21.6803\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 19.9544 - val_loss: 23.9352\n",
       "Epoch 194/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.5035 - val_loss: 22.0653\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.7166 - val_loss: 23.1786\n",
       "Epoch 195/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.2722 - val_loss: 21.8870\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 20.0444 - val_loss: 25.1139\n",
       "Epoch 196/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.5531 - val_loss: 23.0037\n",
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.8615 - val_loss: 26.9069\n",
       "Epoch 197/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.4725 - val_loss: 22.0570\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 21.3380 - val_loss: 23.8444\n",
       "Epoch 198/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.1098 - val_loss: 22.2080\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.4698 - val_loss: 23.7768\n",
       "Epoch 199/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.0830 - val_loss: 21.6509\n",
+      "36/36 [==============================] - 0s 7ms/step - loss: 20.1683 - val_loss: 27.2511\n",
       "Epoch 200/200\n",
-      "36/36 [==============================] - 0s 8ms/step - loss: 19.4419 - val_loss: 22.4532\n"
+      "36/36 [==============================] - 0s 8ms/step - loss: 19.5183 - val_loss: 23.1843\n"
      ]
     }
    ],
@@ -1480,7 +1479,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 26,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -1500,24 +1499,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 96,
+   "execution_count": 27,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
     }
    },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAABIAAAANVCAYAAAAA/IVIAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdeXycZbn/8e9kMslk65puNE0XlrIvRWSxpS1I9RRlqfUoyC7noAKCgAhHPCyCCCq0nJ+ACuIBBRcICEesVGih7NhWNqEotKR0oaSlW5pJJpP5/XHPM/PMmnmSeWb9vF+vviZ5ZjJzJ3mazHxzXdftCYfDYQEAAAAAAKBsVRV6AQAAAAAAAHAXARAAAAAAAECZIwACAAAAAAAocwRAAAAAAAAAZY4ACAAAAAAAoMwRAAEAAAAAAJQ5AiAAAAAAAIAyRwAEAAAAAABQ5giAAAAAAAAAyhwBEAAARcTj8WT1b+nSpYN6nGuuuUYej2dAH7t06dKcrKHYnXXWWZo0aVJRPO6kSZN01lln9fuxg/nePP/887rmmmu0devWpOtmzZqlWbNmOb7PwVqzZo08Ho9+9atf5f2xAQAoN9WFXgAAAIh54YUX4t7//ve/ryVLluipp56KO77vvvsO6nHOPfdcffaznx3Qx06bNk0vvPDCoNeA7D388MMaMmSIq4/x/PPP69prr9VZZ52lYcOGxV13++23u/rYAADAfQRAAAAUkSOOOCLu/VGjRqmqqirpeKJdu3apvr4+68dpaWlRS0vLgNY4ZMiQfteD3DrkkEMK+viEfQAAlD5awAAAKDGzZs3S/vvvr2eeeUZHHXWU6uvrdc4550iSfve732nOnDkaN26c6urqtM8+++iKK65QZ2dn3H2kagGbNGmSPve5z2nRokWaNm2a6urqtPfee+uXv/xl3O1StRmdddZZamxs1L/+9S/NnTtXjY2NmjBhgi699FJ1d3fHffwHH3yg+fPnq6mpScOGDdNXvvIVvfLKK1m1+nz00Uf6xje+oX333VeNjY0aPXq0jjnmGC1btizudlbr0I9//GPdcsstmjx5shobG3XkkUfqxRdfTLrfX/3qV5o6dapqa2u1zz776N577824DstJJ52kiRMnqq+vL+m6ww8/XNOmTYu+/9Of/lRHH320Ro8erYaGBh1wwAG6+eabFQwG+32cVC1gb7/9tj772c+qvr5ezc3N+trXvqYdO3YkfezixYt14oknqqWlRX6/X3vssYfOO+88dXR0RG9zzTXX6Nvf/rYkafLkyUmthqlawLZs2aJvfOMbGj9+vGpqajRlyhR997vfTfp+ezweXXDBBbrvvvu0zz77qL6+XgcddJD+7//+r9/PO51nn31Wxx57rJqamlRfX6+jjjpKf/rTn+Jus2vXLl122WWaPHmy/H6/RowYoU984hN64IEHord577339OUvf1m77babamtrNWbMGB177LH6+9//PuC1AQBQrKgAAgCgBG3YsEGnnXaaLr/8cv3gBz9QVZX5m84///lPzZ07VxdffLEaGhr09ttv66abbtLLL7+c1EaWyquvvqpLL71UV1xxhcaMGaO77rpLX/3qV7XHHnvo6KOPzvixwWBQJ5xwgr761a/q0ksv1TPPPKPvf//7Gjp0qP77v/9bktTZ2anZs2dry5Ytuummm7THHnto0aJF+tKXvpTV571lyxZJ0tVXX62xY8dq586devjhhzVr1iw9+eSTSSHFT3/6U+29995asGCBJOl73/ue5s6dq9WrV2vo0KGSTPhz9tln68QTT9RPfvITbdu2Tddcc426u7ujX9d0zjnnHJ144ol66qmn9OlPfzp6/O2339bLL7+s2267LXrs3Xff1amnnqrJkyerpqZGr776qm644Qa9/fbbSSFbfz788EPNnDlTPp9Pt99+u8aMGaPf/OY3uuCCC5Ju++677+rII4/Uueeeq6FDh2rNmjW65ZZbNH36dL3++uvy+Xw699xztWXLFv3P//yP2traNG7cOEnpK38CgYBmz56td999V9dee60OPPBALVu2TDfeeKP+/ve/J4Uxf/rTn/TKK6/ouuuuU2Njo26++WadfPLJWrVqlaZMmeLoc3/66ad13HHH6cADD9Tdd9+t2tpa3X777fr85z+vBx54IHouXXLJJbrvvvt0/fXX65BDDlFnZ6feeOMNbd68OXpfc+fOVSgU0s0336zW1lZ1dHTo+eefTzkHCQCAkhcGAABF68wzzww3NDTEHZs5c2ZYUvjJJ5/M+LF9fX3hYDAYfvrpp8OSwq+++mr0uquvvjqc+DRg4sSJYb/fH37//fejx7q6usIjRowIn3feedFjS5YsCUsKL1myJG6dksK///3v4+5z7ty54alTp0bf/+lPfxqWFP7zn/8cd7vzzjsvLCl8zz33ZPycEvX29oaDwWD42GOPDZ988snR46tXrw5LCh9wwAHh3t7e6PGXX345LCn8wAMPhMPhcDgUCoV322238LRp08J9fX3R261Zsybs8/nCEydOzPj4wWAwPGbMmPCpp54ad/zyyy8P19TUhDs6OlJ+XCgUCgeDwfC9994b9nq94S1btkSvO/PMM5Med+LEieEzzzwz+v53vvOdsMfjCf/973+Pu91xxx2X9L2xs86J999/Pywp/Mc//jF63Y9+9KOwpPDq1auTPm7mzJnhmTNnRt+/8847U36/b7rpprCk8BNPPBE9Jik8ZsyY8Pbt26PHNm7cGK6qqgrfeOONKddpsb6P9vPiiCOOCI8ePTq8Y8eO6LHe3t7w/vvvH25paYl+H/fff//wSSedlPa+Ozo6wpLCCxYsyLgGAADKBS1gAACUoOHDh+uYY45JOv7ee+/p1FNP1dixY+X1euXz+TRz5kxJ0ltvvdXv/R588MFqbW2Nvu/3+7XXXnvp/fff7/djPR6PPv/5z8cdO/DAA+M+9umnn1ZTU1PSAOpTTjml3/u33HnnnZo2bZr8fr+qq6vl8/n05JNPpvz8jj/+eHm93rj1SIquadWqVVq/fr1OPfXUuJa4iRMn6qijjup3LdXV1TrttNPU1tambdu2SZJCoZDuu+8+nXjiiRo5cmT0titXrtQJJ5ygkSNHRr83Z5xxhkKhkN55552sP39JWrJkifbbbz8ddNBBccdPPfXUpNtu2rRJX/va1zRhwoTo12vixImSsjsnUnnqqafU0NCg+fPnxx232tSefPLJuOOzZ89WU1NT9P0xY8Zo9OjRWZ1Xdp2dnXrppZc0f/58NTY2Ro97vV6dfvrp+uCDD7Rq1SpJ0ic/+Un9+c9/1hVXXKGlS5eqq6sr7r5GjBih3XffXT/60Y90yy23aOXKlSlb+QAAKBcEQAAAlCCrRcdu586dmjFjhl566SVdf/31Wrp0qV555RW1tbVJUtIL4FTsgYWltrY2q4+tr6+X3+9P+thAIBB9f/PmzRozZkzSx6Y6lsott9yir3/96zr88MP10EMP6cUXX9Qrr7yiz372synXmPj51NbWSop9Lax2oLFjxyZ9bKpjqZxzzjkKBAL67W9/K0n6y1/+og0bNujss8+O3qa9vV0zZszQunXrtHDhQi1btkyvvPKKfvrTn8atJ1ubN2/Oas19fX2aM2eO2tradPnll+vJJ5/Uyy+/HJ2D5PRxEx8/cY7U6NGjVV1dHddmJQ3uvLL7+OOPFQ6HU57/u+22W3RtknTbbbfpO9/5jh555BHNnj1bI0aM0EknnaR//vOfkkxg+eSTT+ozn/mMbr75Zk2bNk2jRo3SN7/5zZSzlAAAKHXMAAIAoAQlvvCWTFXG+vXrtXTp0mjVj6SimmcycuRIvfzyy0nHN27cmNXH//rXv9asWbN0xx13xB0f6At2K5hI9fjZrmnffffVJz/5Sd1zzz0677zzdM8992i33XbTnDlzord55JFH1NnZqba2tmj1jaQBDxseOXJkVmt+44039Oqrr+pXv/qVzjzzzOjxf/3rXwN6XPvjv/TSSwqHw3Hn4qZNm9Tb26vm5uZB3X86w4cPV1VVlTZs2JB03fr16yUp+tgNDQ269tprde211+rDDz+MVgN9/vOf19tvvy3JVHrdfffdkqR33nlHv//973XNNdeop6dHd955pyufAwAAhUIFEAAAZcJ6IW5VuVh+9rOfFWI5Kc2cOVM7duzQn//857jjVvVMfzweT9Ln99prr+mFF14Y0HqmTp2qcePG6YEHHlA4HI4ef//99/X8889nfT9nn322XnrpJT377LN67LHHdOaZZ8a1nqX63oTDYf3iF78Y0Lpnz56tN998U6+++mrc8fvvvz/ufSfnRGJ1VCbHHnusdu7cqUceeSTuuLV72rHHHtvvfQxEQ0ODDj/8cLW1tcWts6+vT7/+9a/V0tKivfbaK+njxowZo7POOkunnHKKVq1apV27diXdZq+99tJVV12lAw44QCtWrHBl/QAAFBIVQAAAlImjjjpKw4cP19e+9jVdffXV8vl8+s1vfpMUEhTSmWeeqVtvvVWnnXaarr/+eu2xxx7685//rL/85S+S1O+uW5/73Of0/e9/X1dffbVmzpypVatW6brrrtPkyZPV29vreD1VVVX6/ve/r3PPPVcnn3yy/uM//kNbt27VNddck3ULmGRmGF1yySU65ZRT1N3dnbRl+3HHHaeamhqdcsopuvzyyxUIBHTHHXfo448/drxmSbr44ov1y1/+Uscff7yuv/766C5gVmWLZe+999buu++uK664QuFwWCNGjNBjjz2mxYsXJ93nAQccIElauHChzjzzTPl8Pk2dOjVudo/ljDPO0E9/+lOdeeaZWrNmjQ444AA9++yz+sEPfqC5c+fG7YiWazfeeKOOO+44zZ49W5dddplqamp0++2364033tADDzwQDb0OP/xwfe5zn9OBBx6o4cOH66233tJ9992nI488UvX19Xrttdd0wQUX6Itf/KL23HNP1dTU6KmnntJrr72mK664wrX1AwBQKFQAAQBQJkaOHKk//elPqq+v12mnnaZzzjlHjY2N+t3vflfopUU1NDToqaee0qxZs3T55ZfrC1/4gtrb23X77bdLkoYNG5bx47/73e/q0ksv1d13363jjz9ed911l+68805Nnz59wGv66le/qrvuukv/+Mc/NG/ePF133XX6r//6r5RDttMZOnSoTj75ZH3wwQf61Kc+lVSFsvfee+uhhx7Sxx9/rHnz5unCCy/UwQcfHLdNvBNjx47V008/rX333Vdf//rXddppp8nv9+v//b//F3c7n8+nxx57THvttZfOO+88nXLKKdq0aZP++te/Jt3nrFmzdOWVV+qxxx7T9OnTddhhh2n58uUpH9/v92vJkiX6yle+oh/96Ef6t3/7N/3qV7/SZZddFp055ZaZM2dGh1CfddZZ+vKXv6xt27bp0UcfjW4BL0nHHHOMHn30UZ199tmaM2eObr75Zp1xxhl67LHHJJmv4e67767bb79d8+fP14knnqjHHntMP/nJT3Tddde5+jkAAFAInrC93hkAAKAAfvCDH+iqq65Se3u7WlpaCr0cAACAskMLGAAAyCurSmXvvfdWMBjUU089pdtuu02nnXYa4Q8AAIBLCIAAAEBe1dfX69Zbb9WaNWvU3d2t1tZWfec739FVV11V6KUBAACULVrAAAAAAAAAyhxDoAEAAAAAAMocARAAAAAAAECZIwACAAAAAAAoc2U/BLqvr0/r169XU1OTPB5PoZcDAAAAAACQE+FwWDt27NBuu+2mqqrMNT5lHwCtX79eEyZMKPQyAAAAAAAAXLF27Vq1tLRkvE3ZB0BNTU2SzBdjyJAhBV7NwASDQT3xxBOaM2eOfD5foZeDEsF5g4HgvMFAcN7AKc4ZDATnDQaC8wZOldo5s337dk2YMCGafWRS9gGQ1fY1ZMiQkg6A6uvrNWTIkJI4AVEcOG8wEJw3GAjOGzjFOYOB4LzBQHDewKlSPWeyGXnDEGgAAAAAAIAyRwAEAAAAAABQ5giAAAAAAAAAyhwBEAAAAAAAQJkjAAIAAAAAAChzBEAAAAAAAABljgAIAAAAAACgzBEAAQAAAAAAlDkCIAAAAAAAgDJHAAQAAAAAAFDmCIAAAAAAAADKHAEQAAAAAABAmSMAAgAAAAAAKHMEQAAAAAAAAGWOAAgAAAAAAKDMEQABAAAAAACUOQIgAAAAAACAMkcABAAAAAAAUOYIgAAAAAAAAMocARAAAAAAAECZIwACAAAAAAAocwRAAAAAAAAAZY4ACAAAAAAAoMwRAAEAAAAAAJQ5AiAAAAAAAIAyRwAEAAAAAABQ5giAAAAAAAAAylx1oReA3Ghvlzo60l/f3Cy1tuZvPQAAAAAAoHgQAJWB9nZp6lQpEEh/G79fWrWKEAgAAAAAgEpEC1gZ6OjIHP5I5vpMFUIAAAAAAKB8EQABAAAAAACUOQIgAAAAAACAMkcABAAAAAAAUOYIgAAAAAAAAMocARAAAAAAAECZIwACAAAAAAAocwRAZaC5WfL7M9/G7ze3AwAAAAAAlae60AvA4LW2SqtWSR0d0hlnSG++aY6/8opUFYn4mpvN7QAAAAAAQOUhACoTra3mXyAQO7bPPlJDQ+HWBAAAAAAAigMtYGVm8+bY2zt3Fm4dAAAAAACgeBAAlZHeXmnr1tj7BEAAAAAAAEAiACor9vBHIgACAAAAAAAGAVAZsbd/SdKOHYVZBwAAAAAAKC4EQGUkMQCiAggAAAAAAEgEQGVly5b49wmAAAAAAACARABUVqgAAgAAAAAAqRAAlRECIAAAAAAAkAoBUBkhAAIAAAAAAKkQAJURZgABAAAAAIBUCIDKiFUB1NhoLgmAAAAAAACARABUVqwAaOJEc0kABAAAAAAAJKm60AtA7lgtYBMnSm++Ke3YUdj1AG5ob5c6OtJf39wstbbmbz0AAAAAUAoIgMqIVQFkvfilAgjlpr1dmjpVCgTS38bvl1atIgQCAAAAADtawMoILWAodx0dmcMfyVyfqUIIAAAAACoRAVCZCASkXbvM2wRAAAAAAADAjgCoTFjzf7xeafx48zYBEAAAAAAAkAiAyobV/jV8uNTUZN4mAAIAAAAAABIBUNmwAqCRIwmAAAAAAABAPAKgMmG1gI0cKTU2mrd37pTC4cKtCQAAAAAAFAcCoDJhVQCNGBELgPr6+t8xCQAAAAAAlD8CoDJhbwGrr48dpw0M5aS5WfL7M9/G7ze3AwAAAADEVBd6AcgNewBUVSU1NEidndKOHdKoUYVdG5Arra3SqlVSR4f0f/8nXX21NHq09Oc/x27T3GxuBwAAAACIIQAqE/YZQJJpA+vspAII5ae11fx79VXzflWVNG1aYdcEAAAAAMWOFrAyYZ8BJMUPggbKUW9v/CUAAAAAID0CoDJhbwGTCIBQ/kIhc0kABAAAAAD9IwAqE6lawCQCIJQvAiAAAAAAyB4BUJmgBQyVhgAIAAAAALJHAFQGwuHkFrCmJnNJAIRyxQwgAAAAAMgeAVAZ2LEj9iKYFjBUCnsFUDhc2LUAAAAAQLEjACoD1vwfv1+qrw1JS5eqcf07kqSd2/sKuDLAPVYAlPg2AAAAACAZAVAZiM7/qe+SJk2SZs9W4xMPSZJ2Lrxbamsr3OIAl9hbv2gDAwAAAIDMCIDKQHT+z5Z/Sh98IElqlOn92rHTI82fTwiEsmOv+iEAAgAAAIDMCIDKwJYO0+Y1Upujx6wAaKcazIGLL6ZPBmWFAAgAAAAAskcAVAY2v/QvSdIIbYkeiwVAjWZC7tq10rJlBVkf4AZawAAAAAAgewRAZWDz+oCkdBVAjbEbbtiQ13UBbqICCAAAAACyRwBUBjb3jZCURQA0blxe1wW4iQAIAAAAALJXXegFYPC21O0mSRqZrgXM45FaWqQZMwqyPsAN9gAoGCzcOgAAAACgFFABVAY2bzHfxrQzgCRpwQLJ68330gDXMAMIAAAAALJHAFQGotvAf+dcqdEEPk3aIUna6RkiPfigNG9eoZYHuIIWMAAAAADIHgFQGdgSKfwZ+bkjpdNPlyQ11piemJ3eIQqfTPiD8kMABAAAAADZIwAqA1YF0IgRkrq7JUmNPSYV6u31qKenQAsDXEQLGAAAAABkjwCoxIVC0tat5u2RIyXt2iVJaojMAJKkHTvyvy7AbVQAAQAAAED2CIBK3McfS+GweXvECEUDIK/6VFdnrti5M80HAyWMAAgAAAAAskcAVOKs+T9Dhkg+n6Suruh1jfV9kgiAUJ4IgAAAAAAgewRAJS5u/o8UrQCSpMY68wqZAAjlyB76BIOFWwcAAAAAlAICoBIX3QJ+ZOSAPQDyEwChfFEBBAAAAADZIwAqcdEt4K0AyN4C5o9sBU8AhDJEAAQAAAAA2SMAKnEZW8BqzP7vBEAoR2wDDwAAAADZIwAqcZlawJpquiURAKE8UQEEAAAAANkjACpxSQGQvQWsmgAI5YsACAAAAACyRwBU4uJmAIXD8S1gXhMGEQChHBEAAQAAAED2CIBKXNwMoO5uEwJFWAHQjh0FWBjgMmYAAQAAAED2CIBKXFwLmK36R5IaPZ2SqABCebJXAAWDhVsHAAAAAJQCAqASF9cCZpv/I0mNHpP8EAChHNECBgAAAADZIwAqcXEtYIkVQGECIJQvWsAAAAAAIHsEQCWsu1vqNF1eqVvAwmb4DwEQyhEVQAAAAACQPQKgEmZV/1RVSUOHKrkFLLRNEgEQyhMBEAAAAABkjwCohFnzf0aMMCFQUgUQARDKGAEQAAAAAGSPAKiExc3/kZICoKagSYgIgFCOmAEEAAAAANkjACphcVvAS8ktYMGPJREAoTxRAQQAAAAA2SMAKmFxW8BLsQogj0eS1NhjbrBjR54XBuSBPQAKBgu3DgAAAAAoBQRAJSxtC1jkQGOgQ5J5cdzTk+fFAS6jBQwAAAAAskcAVMLStoA1N0uSGgKbo7elDQzlhhYwAAAAAMgeAVAJSwqArAqgUaMkSb6u7aqtNYcIgFBuCIAAAAAAIHvVhV4AnGlvlzpMZ5fee89cdnZKK1ZIem+YmjVBrVYi1Nmpxkapu5sACOWHAAgAAAAAskcAVELa26X995cCgfjjN95o/kkXyK+vapX/arVKUiCgxjFhbd7sIQBC2WEGEAAAAABkjxawErJ5c3L4kyigOnXUTYi+31jfJ4kKIJQfKoAAAAAAIHsEQOVoyJDom411BEAoTwRAAAAAAJA9AqByVFdn/klqqjOvjAmAUG7soU8wWLh1AAAAAEApIAAqR36/1NAgSWqsNa+MCYBQbqgAAgAAAIDsEQCVI79fqq+XJDXW9kiSduwo5IKA3AqHCYAAAAAAwAkCoHJkD4B8JgCiAgjlpK8v/n0CIAAAAADIjACoHNlbwKrNtmEEQCgn9uofiQAIAAAAAPpDAFRCRo402U4mfnWpeXRVrAKouksSARDKCwEQAAAAADhDAFRCWlulVauk5culSy4xx+bMMe8vXy4tb/6MVmmqWqdUxyqAqgiAUH4IgAAAAADAmepCLwDOtLaafw89ZN7fay9p2rTIlcGXJG0z1T9WBZCnUxIBEMpLYuBDAAQAAAAAmREAlajNm81lc7Pt4K5d5rKuzhYAmeSHAAiuCoWkZcukDRukceOkGTMkr9fVh7MLBl17KAAAAAAoCwRAJaqjw1xGA6De3tir4Pr6WAtY2Oz/TgAE17S1SRddJH3wQexYS4u0cKE0b54rD0kLGAAAAAA4wwygEpUUAHV1xa60tYA1EQDBTW1t0vz58eGPJK1bZ463tbnysLSAAQAAAIAzBQ2AbrzxRh122GFqamrS6NGjddJJJ2nVqlVxt9m5c6cuuOACtbS0qK6uTvvss4/uuOOOAq24eCQFQFb7l2S2CrNawELbJBEAwQWhkKn8CYeTr7OOXXxxcrlOjh7ajgAIAAAAADIraAD09NNP6/zzz9eLL76oxYsXq7e3V3PmzFFnZ2f0Nt/61re0aNEi/frXv9Zbb72lb33rW7rwwgv1xz/+sYArL7y0AVBdneTxxFrAerdKknbsyO/6UAGWLUuu/LELh6W1a83tcowACAAAAACcKegMoEWLFsW9f88992j06NFavny5jj76aEnSCy+8oDPPPFOzZs2SJP3nf/6nfvazn+lvf/ubTjzxxHwvuSiEwxlawCKVP9EKoEgARAUQcm7DhtzezgECIAAAAABwpqiGQG/bZtqVRowYET02ffp0PfroozrnnHO02267aenSpXrnnXe0cOHClPfR3d2t7u7u6Pvbt2+XJAWDQQVLdKsga93W5datUijkkyQNGRJUMCh5tm9XtaRwfb16g0F5amtVLam+22wX1t0t7doVlM9XgE8ABZF43uSaZ9SorH6A9I4apXCO12DyztjJ3NsbVjBICpQLbp83KE+cN3CKcwYDwXmDgeC8gVOlds44WWfRBEDhcFiXXHKJpk+frv333z96/LbbbtN//Md/qKWlRdXV1aqqqtJdd92l6dOnp7yfG2+8Uddee23S8SeeeEL1VnVMiVq8eLEkacOGBkmflt/fq6eeelySNPLNNzVdUmcopCcff1zj33lHn5DUvf6d6Mc//PATamzkRXKlsc6bnAuFNGfkSPk3b5YnxdVhSV3NzVq8fbv0+OM5fei1a5skHRN9f8eOLj3+uEufZ4Vy7bxBWeO8gVOcMxgIzhsMBOcNnCqVc2aXfR5wP4omALrgggv02muv6dlnn407ftttt+nFF1/Uo48+qokTJ+qZZ57RN77xDY0bN06f/vSnk+7nyiuv1CWXXBJ9f/v27ZowYYLmzJmjIUOGuP55uCEYDGrx4sU67rjj5PP59NJL5uX22LFezZ07V5LkqTbfyoZRozR37lx5gkHp1ls1rrFGPl9YwaBHRx01Ry0tBfs0kGeJ540bPLffLn35ywpL8tiGQYc95hyt+elPNffzn8/5477+evz71dV10f8LGJx8nDcoP5w3cIpzBgPBeYOB4LyBU6V2zlhdT9koigDowgsv1KOPPqpnnnlGLbaEoqurS//1X/+lhx9+WMcff7wk6cADD9Tf//53/fjHP04ZANXW1qq2tjbpuM/nK4lvXibW57B1q3m/udkT+5x6eiRJnoYGc2zoUElSVVeXGhs9+vhjqbvbRwtYBXL13P/3f5eqq81uYLaB0J6WFmnBAlXPm+fKw3oSSo56ez0l//+72JTDz0zkH+cNnOKcwUBw3mAgOG/gVKmcM07WWNBdwMLhsC644AK1tbXpqaee0uTJk+Out+b2VFXFL9Pr9aqvry+fSy0q1gDokSNtB+27gEmxYdCdnWpsNG8yCBqumDdPWrNG+uQnzftf+IK0erU57hKGQAMAAACAMwWtADr//PN1//33649//KOampq0ceNGSdLQoUNVV1enIUOGaObMmfr2t7+turo6TZw4UU8//bTuvfde3XLLLYVcekEl7QAmpd0FTLt2qdEUAxEAwT1erzRsmHl77FjzvosIgAAAAADAmYIGQHfccYckRbd4t9xzzz0666yzJEm//e1vdeWVV+orX/mKtmzZookTJ+qGG27Q1772tTyvtnikDICsCiAr+GloMJednWocb94kAIKrrBQm0o7oJisA8vmkYJAACAAAAAD6U9AAKGwbGpvO2LFjdc899+RhNaUjYwCU2AK2a5eamsybBEBwlZXK5GG7RCvwqa0lAAIAAACAbBR0BhAGZvNmc5lVC1gwqMZ6My9px478rA8Vykph8hAAWVmT3x976CzyZAAAAACoWARAJchRC5ikxjrzwpwKILgqjxVAiQGQJFXwXHgAAAAA6BcBUAnKqgWspkaK7J7WWGtekBMAwVV5rACyt4BZ8vCwAAAAAFCyCIBKUFa7gHk80bcbawiAkAcFrgBiDhAAAAAApEcAVGJCIWnLFvN2xhYwKdoG1ujrlkQABJcVYBcwewUQARAAAAAApEcAVGK2bo3NOhk50nZFYguYFKsAqg5IIgCCywpQAUQABAAAAADZIQAqMVb719Chks9nuyKxBUyKVQARACEfCjADqLo6OuqKAAgAAAAAMiAAKjEp5/9IqVvArAqgKnMdARBcVYAKoOpq808iAAIAAACATAiASsyAAiBPpyQCILgsjxVAVgDk9RIAAQAAAEA2CIBKjBUAxc3/kWItYPYZQJEWsCaPSX4IgOCqPFYAWWEPARAAAAAAZIcAqMQMqAIovEOStGOHy4tDZbMCoDzuAlZdHZuFlYfcCQAAAABKFgFQiRlMAEQFEFxFCxgAAAAAFC0CoBKTNgDK0ALWGNomiQAILqMFDAAAAACKFgFQiUkZAIXDmSuAerdKMhmR9RodyDkqgAAAAACgaBEAlZjNm81lXAAUCMTezhAASVJnp3trQ4VjG3gAAAAAKFoEQCUmZQWQ1f4lpWwBqw1sk9drDtEGBtdQAQQAAAAARYsAqMSkDICs9i+fL/ZqWIpWAHm6dqmx0RwiAIJr8rgLGDOAAAAAAMCZ6v5vgmLR2yt9/LF5O2UAZG//ktTeNUodOkRaP1Y1NebYK6/EQqDmZqm11d01o4IUoAKIFjAAAAAAyA4BUAnZssVcejzS8OG2K6wAyNb+1d4uTf3ufAX0Jem52E1POy32tt8vrVpFCIQc6OuLvR0KmcHkHo9rD2dvAfP5zNt5yJ0AAAAAoGTRAlZCrPav4cPjO72iM4BsFUAdHVIg6M14f4FA7D6BQUksv3E5jaEFDAAAAACcIQAqIZs3m4qKuPYvKW0LGJA3VkmOxeUAiCHQAAAAAOAMAVAJSTkAWkrZAgbkVZ4rgJgBBAAAAADOEACVkM2bzWVSAJSiBQzIq8QKIJd3AqMCCAAAAACcIQAqIR0dpgVs5MiEK2gBQ6ExAwgAAAAAihq7gJWQtBVAJdoC1t6eeQg129QXv+j3cLNH0iGxK1Z6pA/d+x7SAgYAAAAAzhAAlRCrAqgcWsDa26WpU81OZOmwTX1xi/8ejpS0Inbl582FW99DWsAAAAAAwBlawEpIvxVAtgCouVny+8MZ78/vT3FfedLRkTn8kdimvtgV8ntobwHz+czbLnedAQAAAEBJIwAqIU4CoNZWadUqj5ZXf1LLNU3LH/9Qe+9trvvJT6Tly6muQemiBQwAAAAAnKEFrIRs3txPC1jCDKDWVqm14R1p2zZpylZNmzZGb79tXihPm5aHBQMuoQUMAAAAAJyhAqiEWK002VQARTU0RG8zdap58+23XVkekDcEQAAAAADgDAFQiQgGPdq+PU0FUKYAyDq2a1e0BYwACKWObeABAAAAwBkCoGIXCsnz9NNqXGx2WKqqCmvYsITbpGkBkxSrAOrsjKsACmeeDw0UNWYAAQAAAIAzBEDFrK1NmjRJ1ccdp/E/f0iSNFKbVfVIW/ztsqwA2nNPyeORPv6Y3bVQ2mgBAwAAAABnCICKVVubNH++9MEHkqQOmb6v5r5N5nibLQTKMgCqr5cmTjTvFroNzGxTn/k2hdymHv0r5PeQFjAAAAAAcIYAqBiFQtJFF8X1aUUDIEVKdy6+OFYGkWULmKRoG9iqVbletDNmm3qzHf0DD8SO/+IX5hjb1Bc/+/dw+S9f1WS9K0marme0/OYnXf0e2lvAfD7zdjCY+8cBAAAAgHLBNvDFaNmyaOWPJS4ACoeltWvN7WbNyroCSJL23lv6y18KXwEkRbapb41/4T5pElvUlxLre6jO7ZKaJEle9WlayybJxe8jLWAAAAAA4AwVQMVow4akQ1YANFKbk2/nMACSiiMAsgQCqd9GCentVZdMBVqnGlwvxyEAAgAAAABnCICK0bhxSYeSWsDstyvBFjA7AqAyEApFA6CdanQ9AGIGEAAAAAA4QwBUjGbMkFpazJZdEXEBkMcjTZhgbicNqALovfek7m5XVu+YlV9JBEAlq7dXAZmJ0PkIgNgGHgAAAACcIQAqRl6vtHCheTsSAsUCoEgL2IIF5nZSdgFQpAJo7FhpyBCpr0/617/cWLxzVACVvr5gSN2RAIgWMAAAAAAoPgRAxWrePOnBB6Xx4yXZAqBmmePz5pnbBYOxV76ZWsAiIZHHU3xtYARApS/QFduxjhYwAAAAACg+BEDFbN48ac0a9f7yl9qskZKk5j/eHQt/pPj+qSxawKTiGwRNAFT67KdhUDXq2eVuGkMLGAAAAAA4QwBU7LxehU84IVYB1JiQkFjBjscj1dYmf3zCEGgpVgFEAIRc6doVjnu/c5cnzS1zw94C5vOZt10uOgIAAACAkkYAVAK6qpvUqUZJUnPvxoQrI6UX9fVxQ6OjMlQAFUsLmL16pFgGU8MZ+/dQknZ25i8AogIIAAAAAPpHAFQCNm8xL6arFdSQHevir7SCnVTzf6R+W8DC4RQfk2dUAJW+xACos8vdHy3MAAIAAAAAZwiASkBHh7lsVoc8GzfEX5lpBzApZQvYHntIVVXS9u3Shx/meLEDQABU+roC8RU/O3e5+6OFGUAAAAAA4AwBUAnYvNm8uG5Wh7TBYQCUogKotlaaPNm8XQxzgAiASl9SANTldfXxaAEDAAAAAGcIgIpUe7u0YoX597e/mWO1CmjFSo9WrDDXS4r13jhoAZOKaycwe/sQAVBpCnTHB0C0gAEAAABAcaku9AKQrL3d7NQVC0PMt2m5DtOh9x4m3Sv5/WaIc+sAWsAkc/9/+lNxDIKmAqj0dSV833YG3P3RQgsYAAAAADhDBVAR6ujoPwgJBCKzgbJtAevqkvr6ooeLqQKIAKj0dQXif5R0BmgBAwAAAIBiQgVQqcu2Bcy6baQiiABoYNrbY0O5U2lullpb87eeYtHVHR8A7ez2ufp4qVrAgkFXHxIAAAAAShoBUKnLtgLIum0kAJo61Rx6/32TC6XLj/LBPgOou7tw6+hPcmtesmhrXoWFQPkOgOwtYL7IQ1EBBAAAAADp0QJW6voLgKqqTCphv62kUaOk4cOlcFj65z9dXmM/SqUCyFFrXoVJDIA6e/ITANECBgAAAADZoQKo1PXXAiaZqp9AIDoI2mpjammRPv5Yevzx+BfP+W5jKpUACOl19cTP/NnZU+Pq4xEAAQAAAIAzBEClrr8KIOu6zZulXbtStjFdeaX5Z8l3GxMBUOlLDIA6g+4GQGwDDwAAAADO0AJW6rINgCK3LcY2JgKg0hfoMT9K6mXOx53BWlcfj23gAQAAAMAZAqAi1NwcG9uTjt9vbpd1C5gUbQErNvYh0ARApakraCqARnm3SJJ29uYnAKICCAAAAACyQwtYEWptNS1YVhVOb29Qzz77nGY895y8bQ9J53xVzVefb1q0HFYAFSMqgEqf1QLWXL1V74da1OlyAEQLGAAAAAA4QwBUpFpbYzN4gkFpw4ZtmrajV962lZJWSNZ8njILgIp5G3ik1xU0P0pG1WyTuqWdvRkq0gYpHJb6+szb9hawYNC1hwQAAACAkkcLWAkJjxtn3tiwIXawDFrA7AFQT0/sxX2xcdSaV2G6ekwK01y7Q5K0M9TPF2oQ7OeH1yv5IjvOUwEEAAAAAOkRAJWSsWPNpT0AKvEKoGAwNs/FUqxVQFZr3vLl5t8ee5jjX/xi7Fg+d08rJl29kQCobqckqbPPvQog+/lCCxgAAAAAZIcWsBISHmwAVIQVQKlm/gQCmQuaCsnemueN7Hze1CRNm1a4NRWDrqApwxlVZ86xnX0ZzsdBsgc9BEAAAAAAkB0qgEqJ1QK2aVPs1a7VApYpALJawHbtKro2JnsAVFWVfKyYWesslfW6KVoB1GDOx3xVACVuAx8Ou/awAAAAAFDSCIBKyahRJiUJh00IJMUqgDKVzNhawBLbmC6+2Fw1Z05h2pis8KSmJvYplEqgYq2zWFvW8qmrN1IB1GS+KD2qVU+PO4+VrgVMKt75UQAAAABQaARApcTrlcaMMW9bbWDZtIAlDIFubTUtS9OmSUceGbsb61g+Z9hYBUx+v1Qb2Tm8VAIgK/gplfW6KWAFQENiaZhbHYfpWsASrwMAAAAAxBAAlZrEncCyaQHLMAS6pcVcrl2bo/U5ZIUnfn+sNa1UAhVawGK6QiYAGtIUlk+m9MetAMheAVRVRQAEAAAAANkgACo19gCory+7beAzBEATJpjLdesK0z5jhSd1dbEAqBRaqsJhWsDsukI1kqS6hio1yuwEtnOnO49lBUBer+TxxAdAwaA7jwkAAAAApY4AqNTYAyB76YmDFrDEu6uqMpUTH36Yw3VmqVQrgOxBQyms123WDKC6Rq8aFNkJLA8BkEQFEAAAAABkgwCo1NgDIKv6RxpwBVB1dewuC9EGZp8BVEoBkH2NpbBeN4VCUjAcC4CsCqDO7aFMHzZgVshjBUBVVbEd5AiAAAAAACA1AqBSYw+ArECnpib2ajgVKwBKM5TFagP74IMcrdGBUq0Asq+x0lvA7Dmkv7E6VgG0zZ0AyKoAslf+2LeCBwAAAAAkIwAqNakCoEztX1KsBSxFBZBU2EHQqWYAlUIAZA99SmG9boorRGuqdr0CKLEFTCIAAgAAAID+VPd/ExQVKwBavz67HcDs16cJgIqlAsjjiT9WzGgBi7FOwxp1q6qhLjYE2qUKoMQWMIkACAAAAAD6QwBUaqwAaOPG2JTdTPN/pH5bwIqhAogAqHRFN6JTl1RbG2sB2+7OtnK0gAEAAACAcwRApWbsWHPZ2xsr2RlkC1ghK4DsQ6BLKQCyt4BV+gygaBufuiSvV41VO6U+qXOHuwEQFUAAAAAAkD1mAJWamhqpudm8/e675jLbFrCenpSvkIuhAsg+A6gUAhV7SNXTI/W5k3WUhLgKoOpqNVaZAzt3hF15vEwBUDDoykMCAAAAQMkjACpFVhuYFQBl2wImpawCsiqA1q+PvbjOl3LYBUwqjdDKLXEBkNerBq/54nR2uhMAWRmmvQXM54u/DgAAAAAQjwCoFCUGQP1VANn7q1IEQOPGmWqK3l7pww9zuM4slGoAlBj4EADZKoC8kQqgne48Hi1gAAAAAOAcAVApsgKg994zl/0FQB5Pxp3AvN7YXeZ7DpB9BlApBUCJayyFNbsl+j1UwFQA+XokEQABAAAAQDEhACpFVlqzbp257K8FTIoNgk6zE5jVBpbvOUD2CqDa2vhjxSyx4qcU1uyWpAqgaqsFzOPK47ENPAAAAAA4RwBUiqwAKByZsdJfBVAoFGsBW7Ys5aCfQg2CTjUEuhTCFCqAYhJnADX6TDq2c5c7ARDbwAMAAACAcwRApcgKgCyZAqC2NmnSpNhwn/PPN++3tcXdrFBbwZfqDCCGQMckVgBFW8B2ufPjhRYwAAAAAHCOAKgUZRsAtbVJ8+cnpzrr1pnjthCoUBVApToDiBawmKQKoBoTAHV2EQABAAAAQLEgACpFiQFQqhlAoZB00UWxNjE769jFF0dfTRdTBVApVNPQAhYTbeOzKoBqgpKknV3eDB81cKm2gbfeDgZdeUgAAAAAKHkEQKUomwqgZcsypznhsCn3WbZMEjOAnKIFLCapAqjWpDCdLgVAqSqAfD5zSQUQAAAAAKRGAFSK6uulIUPi30+0YUN29xW5nVUBtH59yhnRrinVGUC0gMUk7QIWCYB2BvIXANECBgAAAACZEQCVKnsVUKoWsMQqoX7uZ+xY84I6FJI2bszB+rJUqjOAaAGLSawAavCbhKan1+tKSxbbwAMAAACAcwRApcoe8KSqAJoxw/R1edJsxe3xmLKfGTMkmRfTu+1mrsrnHCB7BVBtbfyxYkYAFBMN8RQwFUD+WArT2Zn7x2MbeAAAAABwjgCoVPUXAHm90sKF5u3EEMh6f8GCuDIKqw0sn3OASnUGUGILGDOAYhVANbUe+RTZCn5n7h+PFjAAAAAAcI4AqFT11wImSfPmSQ8+KI0fH3+8pcUcnzcv6bBUmACIFrDSlTgDSD6fGmRKf9yoAKIFDAAAAACcIwAqVWPHxt5+6630k5vnzZPWrJH+8z/N+3PmSKtXJ4U/UmG2gmcb+NKXWAGkmho1ypT+uFkBRAsYAAAAAGSPAKgUtbVJP/xh7P3zz5cmTTLHU/F6pQMPNG83NcWXTtgUogKoVIdAWyFVTU38+5UoKQCyVQDluwXMjaHTAAAAAFAOCIBKTVubNH++tGVL/PF168zxdCFQQ4O5zNCTk+8KoN7e2Iv5xAAoHM7PGgbKCqmGDYt/vxIFAuabZW8BsyqA3BwCbQ+AfD5zSQUQAAAAAKRGAFRKQiHpootSpyPWsYsvTt0OZgVAu3alvft8VwDZQxP7EOi+vuJ/IW+tfejQ+PcrUaoKIDdbwJgBBAAAAADOEQCVEM+zz2YuzwmHTXqzbFnyddZOYVlUAG3YkJ8X0vbQpLY2tg184nXFyGr5sgKgim4Bi2SKqYZAMwMIAAAAAIoDAVAp2bBh4LfLogVszBjzQjoUkjZuHMD6HLIqR3w+U81RSgEQLWAxmSqA8tUCRgAEAAAAAJkRAJUS+9bvTm+XRQuY1yvttpt5Ox9zgOw7gElSVVVsqHKxByqJFUDFvl43dVnfRwXyUgFECxgAAAAAOEcAVELC06ebQT0eT+obeDymj2vGjOTrsqgAkmJtYPmYA2SFJnV1sWOlshMYM4BiMm0D72YFEC1gAAAAAJA9AqBS4vVKCxeatxNDIOv9BQtSb/OexQwgKTYIuhAVQPa3i32mTmIAVOzrdUswKIVC5tzL1xBoWsAAAAAAwDkCoFIzb5704IPS+PHxx1tazPF581J/nFUBFAik3iUsIp8VQFblSKoAqNgraqzAp9JnAFnfQ0mqU8D08eVpCHSqACgYzP3jAQAAAEA5qO7/Jig68+ZJJ55odvvasMHM/JkxI3Xlj8UKgCTzqr2xMeXN8rkVfKYKoGIPVGgBM+wBkL86Un7j8hDoVDOAfL746wAAAAAA8QiASpXXK82alf3t7YN2OjvTBkBWBVA+W8DsS7N2AivmQCUUigUNld4CFg3x1CVPdSSRyVMLGDOAAAAAACB7tIBVCo8nqzlAVAD1zx720AJmLuvUFUthCtgCRgAEAAAAAKkRAFWSLHYCsyqANmxw/8V0qQZA9rXRAmYuowOgJdd3AWMbeAAAAABwjgCoklgB0K5daW8yZox5Md3XZ0IgN5XqEGhrbV5v/GztSlTICiBawAAAAAAge8wAqiT9tIC1t0sdHVJzs7Rxo/Tkk9KBB8aub26WWltzt5xUM4BKIQCyWsD8/tLZtt4t0RBPgVhJjstDoGkBAwAAAADnCIAqSYYWsPZ2aerU+ODl7LPjb+P3S6tW5S4EytQCVsyBin3dpRBYuSldBVA+hkATAAEAAABA9mgBqyQZAqCOjv5DjEDA3C5XSn0GUG1taexa5qaUM4BcbgGzQp5ULWDBYO4fDwAAAADKAQFQJcliBlA+leoMoHQtYOFw4dZUKP1VAPX05D6UoQIIAAAAAJwjAKokWWwDn0+pKoBKoaLGXgFkX3tPT2HWU0j97QIm5f50SxUA+XzmkgAIAAAAAFIjAKokWWwDn0+lOgQ61Qwg+/FKEv0eJlQA1SioapnSn1yfbmwDDwAAAADOEQBVkiJrASvVGUD2FrCamuTjlSTdDCBJaqwy51mu5wCxDTwAAAAAOEcAVEmKrAKoVGcA2VvAPJ7SaFtzS7oZQJLU4HE3AKICCAAAAACyRwBUSUpgBlApbANvrwCyX1Z8AJRYARTZCSwfM4AIgAAAAAAgMwKgSpKhAqi5OT6IScXvN7fLlXKYASRRASRJfgWSAyCPKf3JdQVQpm3gCYAAAAAAILXq/m+CspFhBlBrq7RqldTRYd5va5NuuEE64gjppz81x5qbze1ypVRnANlbwKTSqFpyS8YWsLA7AVCmCqBcbzkPAAAAAOWCAKiS9DMDqLU1FvAEgyYAWr1amjbNneWkmgFUCtU0tIDFpNsGXpIaIwEQLWAAAAAAUHi0gFUSBzOA9t/fDDj+8EPzzw2lXgFEANRfBdAOSe61gNkDoMhDEgABAAAAQBoEQJXEwS5gDQ3SHnuYt197zZ3llPoMIKtaybqsxBaw6Pcw1RDoSADkVgUQM4AAAAAAIHsEQJUkwwygVA46yFy6HQCVWgUQLWAxmSqAGpX/GUAEQAAAAACQGgFQJXG4DfyBB5pLAqB4tIDFZNoGviGyDTwBEAAAAAAUHgFQJXHQAibFAqBXX3VnOamGQJfCjlrpWsAqPgBKUwGU6xYwtoEHAAAAAOcIgCqJwwDIagH7xz/c2V67VCuA0rWAFXNo5ZZMFUCFaAFjG3gAAAAASI0AqJJYAVBPT1alEhMnSk1N5kX122/ndim9vbEl2IdAl0I1TWIFUCmEVm6JVnEpEEthqqokr5cWMAAAAAAoIgRAlcSaASRlNQja43FvDpC9WqbUKoCYARSTsgJIknw+11vACIAAAAAAIHsFDYBuvPFGHXbYYWpqatLo0aN10kknadWqVUm3e+utt3TCCSdo6NChampq0hFHHKH29vYCrLjE+f0m1ZEct4HlOgCyggMpVkkjxcKUnh6pry+3j5kriS1glbwNfMoZQJLk87leAZTwcJJMABQO5/bxAAAAAKAcFDQAevrpp3X++efrxRdf1OLFi9Xb26s5c+ao0xZOvPvuu5o+fbr23ntvLV26VK+++qq+973vyW8vG0F2PB7HW8HndBB0KCQtXSo98IACS16QZF7E21/I27+txRqo0AJmhMOFqQDK1AImFW9wCAAAAACFVN3/TdyzaNGiuPfvuecejR49WsuXL9fRRx8tSfrud7+ruXPn6uabb47ebsqUKXldZ1lpaDAlGfmuAGprky66SPrgA0lSQLtL+pfqfEFJvujN7AFQIBA/H6hYpBsCXWkBUDAYq7ZJVQHk1hDoTC1g1vX26wAAAAAABQ6AEm3btk2SNGLECElSX1+f/vSnP+nyyy/XZz7zGa1cuVKTJ0/WlVdeqZNOOinlfXR3d6vbVjqyfft2SVIwGFSwRLcIstadi/VX19fLI6l32zaFs7i/qVMlyacNG6T164MaNcr5Y3oefljeL39ZCocVaUBTQCY18Xd9rN7fL1X45JMlmUChqqpafX0e7dgRVGOj88dzW1dXtSSPqqt7FQyGVV1dJcmrrq6QgsHiKT/J5XmTivmvZcK7OnUp5PGoL/JY1TU1thawsILB3A3nCYXM118KRnf9MkGUWUtXV1BVTDcbMLfPG5Qnzhs4xTmDgeC8wUBw3sCpUjtnnKyzaAKgcDisSy65RNOnT9f+++8vSdq0aZN27typH/7wh7r++ut10003adGiRZo3b56WLFmimTNnJt3PjTfeqGuvvTbp+BNPPKF6+xDkErR48eJB38fsUEhDJL28ZIk+2rIlq48ZO/ZYbdzYqLvuelkHHdTh7AFDIc35xjfktYU/ktQlU9rjV0A955+vxdXV0bINn+94dXdXa9GiJRozpivFnRbW5s3HSmrUihUvqLt7i9as2UPSfnr33XV6/PGVhV5eklycN6l8/HGtpM/Koz7VqEdr1q3Ta48/Lkn6dE9PtAJox44+PR45ngudnZ+R5Nfzzz+rjRutgNcj6QRJ0uOPP6GGBqZBD5Zb5w3KG+cNnOKcwUBw3mAgOG/gVKmcM7uyHO8iFVEAdMEFF+i1117Ts88+Gz3WFxnmceKJJ+pb3/qWJOnggw/W888/rzvvvDNlAHTllVfqkksuib6/fft2TZgwQXPmzNGQIUNc/izcEQwGtXjxYh133HHy+Xz9f0AG3h/8QGpv1yf331/huXOz+pgjjvDqkUek+vojNHeuswoXz9NPq3rz5qTj0QogBVTf0aHjhwxROPL9rK/3qrtbOvLI2dp7b0cPlxc+n/lvM3v2kfrEJ8JavbpK//u/0siRLZo7d1yBVxeTy/MmldWrzWWdr1eeoNQ6ZYpaIudU9dCh6v7wo8g6vJozZ25cm9ZgWF//mTOn64ADzDH73J/Zs+eouTk3j1WJ3D5vUJ44b+AU5wwGgvMGA8F5A6dK7Zyxup6yURQB0IUXXqhHH31UzzzzjFpaWqLHm5ubVV1drX333Tfu9vvss09cUGRXW1urWvu2UhE+n68kvnmZ5ORziPRUVXd3x7ZO6sfBB0uPPCK98YZXPp/D4SoffZTysBUA1clU+FR/9FF0PdZMnVDIl+0S88qa9dPYWC2fLzZXu6enSj5f8fUeuXXuW7N46qqDUlDy1tTIaz2OrQVMknp6fDmb5xR93Lr488PjMa1gHk9xnjelphx+ZiL/OG/gFOcMBoLzBgPBeQOnSuWccbLGgr5aDYfDuuCCC9TW1qannnpKkydPjru+pqZGhx12WNLW8O+8844mTpyYz6WWD6sNzsHWTNZOYAMaBD0udUWMvQIo8XbFPlQ5cRewSt0G3toBzO+N9Jwm7AJWox5Ve01pTi4HQafaBUyKDYLupfsLAAAAAJIUtALo/PPP1/33368//vGPampq0saNGyVJQ4cOVV2kXODb3/62vvSlL+noo4/W7NmztWjRIj322GNaunRpAVdewqxyFQcBkLUT2Jtvmp2fHIWgM2ZILS3SunWxLaOUEABNmGBuF1HsARC7gBnRLeCrIwFQwi5gHkkN/pC2dVblJQDy+cz5SQAEAAAAAMkKWgF0xx13aNu2bZo1a5bGjRsX/fe73/0uepuTTz5Zd955p26++WYdcMABuuuuu/TQQw9p+vTpBVx5CbMCIAeDoiZNMp1jPT3SO+84fDyvV1q40LztiY2Btg+B1oIFca/mizlQCYdj6yIAMpd13h7zhj2RqamRJDXWmnDIQd7Yr1TbwEtUAAEAAABAJgWtAArbKkIyOeecc3TOOee4vJoKMYAKoKoq0wb2/POmDWy//Rw+5rx50oMPShdcIG3YIMk2A+iwA6R5u8XdvJgDlZ6e2Nu0gJnLaACUUAEkSY1+k8a4UQGUOFSaAAgAAAAA0iuKIdDII4czgNrbpY6O2Iiev/xFmjo1dn1zs9TamsUdzZtn7uSooyRJgakHS6sk/5Tdkm5azAGQPeSp9Aog6/NNWQEUCYAaakwFEDOAAAAAAKCwCIAqjYMKoPZ2E/bYg43//V/zz+L3S6tWZRkCdXRE3wzUDIl+fCLrWDFW1Ni/FpEup4oNgKIVQFXpA6DGGnNdrlrAwuHYlu8EQAAAAACQveLbsxrucjADqKOj/1AjEIjLdTKLDPmWpK6AmQeUKgCyWqqKMVCx7wBmjTSq+ADIG0nqUrSANfhyWwFkVf8kPpz9/WAwN48FAAAAAOWECqBKM4Bt4Pvz1lvJx1K2hn34YfTNQHf6AKiYA5XEHcAkZgDVVUU+8VQVQD5zXa5ON3sARAUQAAAAAGSPAKjSDGAIdH9OOy35WMrWMHsA1GMCoLq61B8rFWcAZK8AshTzet1kBUB+T4Yh0JEAyI0KIAIgAAAAAMgeLWCVZgDbwA9EytawuADIvHovtQqgxC3g7W8HAmZGTaXIWAEUGZDUUJ3bAMge7iQGQJHMiQAIAAAAAFIYUAC0detW3XXXXbryyiu1ZcsWSdKKFSu0bt26nC4OLnChAihr9hlAQVOuUWoBUKYWsHC4ssKHaADkiXyjUlUAVZvr3GgBYxt4AAAAAMie4xaw1157TZ/+9Kc1dOhQrVmzRv/xH/+hESNG6OGHH9b777+ve++91411IldcmAGUNXsFULC0K4BStYBZ11uVKOUuqxlAkQCIFjAAAAAAKCzHFUCXXHKJzjrrLP3zn/+U3/bK99/+7d/0zDPP5HRxcEEhK4DsAVCvebWeaQZQMQ5VzlQBJBVnaOWWaACkyBupdgGrMte5EQBVJfz0IgACAAAAgPQcB0CvvPKKzjvvvKTj48eP10Zbiw+KlIMZQM3NqSt0BiQQkLZti70bMgFBqW4Db193VVV05E1Rrtkt1ucabQFLVQFUZc6zXOWNVriT2P5lP0YABAAAAADJHLeA+f1+bd++Pen4qlWrNGrUqJwsCi5yUAHU2mp28koc5vzWW6l3/srIVv0jSV1hk/KUQwuY9X5PT3FWLbmlkBVAie1f9ocPBnPzWAAAAABQThwHQCeeeKKuu+46/f73v5ckeTwetbe364orrtAXvvCFnC8QOWbNAAoGzb9+Bta0tiZs5T5QVgA0cqS0ebMCMilPqQVAqVrArPd37CjONbslaQh0il3Acl0BlE0ARAUQAAAAACRz3AL24x//WB999JFGjx6trq4uzZw5U3vssYeampp0ww03uLFG5JJVASQN+FV5Nq1hfr+5XZQVAE2aJEnRACjTDKBiDFPSVQAV85rdEqsAirQTptoFzGPOsVxvA08ABAAAAADOOK4AGjJkiJ599lk99dRTWrFihfr6+jRt2jR9+tOfdmN9yLWaGvPqORQyc4CGDXN8F6law+64Q7rrLumYY6Qf/ciEP3GVQ9Z8qHHjJL9fgUBpVgClmgEkxQKhSmwB84fTzwBqUG4DIKsCKNUMIKuYjQAIAAAAAJI5DoAsxxxzjI455phcrgX54PGYKqDt2wfVl5PYGnbeeSYAevllab/9kitkohVAY8ZI9fUlGwBlagGTinPNbolWAIWTK4Dad45Qhw5R+/Zhksz87xUrYh+bFBBmiRYwAAAAABgYxwHQbbfdlvK4x+OR3+/XHnvsoaOPPlreVK/QUBzq6wcdACWaNk3abTdp/Xpp6VLpM59JuIE9AKqrU5dM71epBUC0gMUkDYGO/J9vb5em3niWAjpXetZctW2bdOihsY/1+00VmdMQKKsA6B/vSA8sN9VmM2akvjEAAAAAVBjHAdCtt96qjz76SLt27dLw4cMVDoe1detW1dfXq7GxUZs2bdKUKVO0ZMkSTZgwwY01Y7Ac7ASWraoq6XOfk37+c+nRRzMEQGPHmgqgDDOAirmdKl0LmPV+Ma7ZLdEAqC9yHkUSmI4OKdCb+UdLIGBu5zQAyrgN/Ia1kiaod+H/k/Q/5mBLi7RwoTRvnrMHAgCghLW3J+/iajfQSlwAQGlzPAT6Bz/4gQ477DD985//1ObNm7Vlyxa98847Ovzww7Vw4UK1t7dr7Nix+ta3vuXGepELVgC0a1dO7/aEE8zlY49J4XDCldYMIKsFrMx2AbNCq2Jcs1vSVQC5KW0FUFubqp9bKknqtefa69ZJ8+dLbW2urw0AgGLQ3i5NnWoqb9P9mzrV3A4AUFkcB0BXXXWVbr31Vu2+++7RY3vssYd+/OMf68orr1RLS4tuvvlmPffcczldKHLI2go+hxVAkhkAXV8vrV0rvfpqwpW2FrBQXaOCMtuEl1oARAtYjPW5JlYAuSllABQKSRddpGqZ8qCgfLHrrCTy4otjHwwAQBnr6Oj/+YhViQsAqCyOA6ANGzaoN8WU1d7eXm2MVHnstttu2rFjx+BXB3e40AImmXau444zbz/6aMKVtgAoUDs0erhUA6BKHwIdDqdoActDBVDKFrBly6QPPogGQL2Jna3hsEklly1zfX0AAAAAUKwcB0CzZ8/Weeedp5UrV0aPrVy5Ul//+teju4K9/vrrmjx5cu5WidxyqQVMim8DiwoEzBRgSRo7tqQDoP5awCplBpD98yx4BdCGDebh0wVACbcDAAAAgErkOAC6++67NWLECB166KGqra1VbW2tPvGJT2jEiBG6++67JUmNjY36yU9+kvPFIkdcqgCSpOOPNzvN/+1vZkcwSbHqn5oaaehQBWqGSJKqq0IpMwN7AJQ0S6jAaAEzrOofKb8VQCkDoHHjJEk+BSVlCIAitwMAAACASuT4T/Zjx47V4sWL9fbbb+udd95ROBzW3nvvralTp0ZvM3v27JwuEjnm0gwgyVSG7L+/9Prr0u23RzZfemOHpEOk4WPVvNajYCQA8lf3SkoODawwpa/PtPz4fEk3KRhawAwrAKqqkqp7I590HiqArBawuABoxgyppUXVH5h0KCkA8njMbmAzZri+PgAAAAAoVgN+xbb33ntr7733zuVakC8uVQBZu05YIcgNN5h/0v6SVkgfSv6p0qPHjpdkBUC1SfdjD1cCgeIKgNK1gFXaNvDR+T91kqcvviynuVny14QU6ElfEeT3m9s5ZVUAxWVNXq+0cKGqv/CupIQAyOMxlwsW5KVCCQAAAACK1YACoA8++ECPPvqo2tvb1dPTE3fdLbfckpOFwUUuzQDKdteJD/vMK3+/N5jyNvb2qu5uqakpVyscvHQtYJW2Dbw9AEqczNzaKq36zXJ1fPFrUutEndbwsN56S1q4UJo+3dy0udnczqm028DPm6fqeauktoQAqKXFhD/z5jl/MAAAAAAoI44DoCeffFInnHCCJk+erFWrVmn//ffXmjVrFA6HNW3aNDfWiFxzcQZQNrq9pgWtrqon5fVVVabqJxgsvkClvwqgYluvW+ICoO3JqUxrS59atVLybtWIEeZYS4s02B8RaQMgSdX7TTUB0Mix0mZJn/2s9H//R+UPAKCiNDeb5yWZnpMMtBIXAFDaHA+BvvLKK3XppZfqjTfekN/v10MPPaS1a9dq5syZ+uIXv+jGGpFrLs4AykaPt06S5K9K3y9VrIEKQ6CNlBVA9qDF6tsLBnO6Q1rKbeAVfyxYbc4vjRhB+AMAqDitrdKqVdLy5dIvfhE7/tBD5tjy5eb6gVTiAgBKm+MKoLfeeksPPPCA+eDqanV1damxsVHXXXedTjzxRH3961/P+SKRY4WuAPJEAiBP5gBox47iC1TSDYGutG3gra9DXZ1SD+axAqCenpyGYxkrgCIP3xu5TcV8MwAASNDaav59/HHs2OTJ0iGHFG5NAIDCc1wB1NDQoO7IC6vddttN7777bvS6jo6O3K0M7nFpBlC2uqtMIuBX6VUA0QJmxFUApUplbBVA+Q+AIoOfCYAAABXOPqrT+t0NAKhcjiuAjjjiCD333HPad999dfzxx+vSSy/V66+/rra2Nh1xxBFurBG5VuAKoB6PSQTqlP6ZSLEGKrSAGZmGQEtyLQBKuQ18wkMSAAEAYARt+20QAAEAHAdAt9xyi3bu3ClJuuaaa7Rz50797ne/0x577KFbb7015wuECwo8A6jbY9ITf7h0AyC2gTeXdf6wFA6bd+ypTE2NuczxDKCU28Ar/lhvqCp3DwgAQAmjAggAYOc4AJoyZUr07fr6et1+++05XRDywKUKoGx3nfDVmhfo/nD6FrRinamTrgWsUreB99eGYwfzUAGUVQtYHwEQAAASFUAAgHiOZwBNmTJFmzdvTjq+devWuHAIRcylGUD2XSeWLze7cEvSN7VAy6sP1/K/hbVqlVTXaF6p+/vSP34xVgD19sZakGgBM5d1flsAlGoGUF+f/DV9kvIZANECBgCARAUQACCe4wqgNWvWKGS9CrPp7u7WunXrcrIouMzFGUDWrhOSdOih0qJFUlA1mjZug3SoeWEeCEdawEKlFQDZ8wRawMxlXW1f7GCqCiBJtb4+SVV52wY+WgFUTCcPAAAFQAUQAMAu6wDo0Ucfjb79l7/8RUOHDo2+HwqF9OSTT2rSpEk5XRxcYp8BFA5LHo8rDzN5srl8T1OkMWOix60AqC60I+3HFnsAlFgBFGsBC0tLn5Y2bJDGjZNmzEhdrlLiUgZAqSqAJPl9IUnVeasACvZFrqyUNA4AgDTsFUAF2vwVAFBEsg6ATjrpJEmSx+PRmWeeGXedz+fTpEmT9JOf/CSni4NLrAqgUMj8acga2JtjVkfgak2Wxo6NHg+ETDjg792Z9mOLMQCy1uL1JlegRNe75kNp9uzYFS0t0sKF0rx5+VlknjipADIBUD5bwAiAAACQqAACAMTLegZQX1+f+vr61Nraqk2bNkXf7+vrU3d3t1atWqXPfe5zbq4VuWIFQJKrO4FZFUBrNEl9o2MBUFevLQAKh1N9aFEHQIntX5LkX7bY3KbPF3/FunXS/PlSW5vLq8sv62sRFwBV2X6c2MIgv6837mMGI9M28NEAKMwQaAAAJGYAAQDiOR4CvXr1ajU3N7uxFuSLzxd7texiANTSIlVXhdSjWq2v3yN6PFoBpEDaVKAYA6B0O4ApFJL/xqvNbZTQG2YFXBdfHCtfKQPRCqAaW0mOvZXQ44lWAdV6zW3i8phQSFq6VHrgAXOZ5dcmq23grcJGAiAAQIWjAggAYOd4CLQkPfnkk3ryySejlUB2v/zlL3OyMLisoUHatm3wAVAoJC1blnLmTXW11Fr3kd7rHKvVVburJfIhgV5zfZ26TEN6XV3S3RbjturWWhLn/2jZMtVuXGNuoxTlQeGwtHat+TrNmuXmEvMmZQCUyOcz28BXJ1QAtbVJF10kffBB7LZZtsplagGzus4IgAAAMKgAAgDYOa4AuvbaazVnzhw9+eST6ujo0Mcffxz3DyUiF1vBt7VJkyaZmTennmouJ02Ka3ea7DMv8t/rnRA9Fug2p51fgbSPX4y7aqVtAduwwXwukkKqVq/SDH3esMG9xeVZUgCUqiQnksj4vebPj4GAzLkxf358+CNl3SqX1QwgKwAKBqWEgBoAgEpCAAQAsHNcAXTnnXfqV7/6lU4//XQ31oN8GexW8NYL+cQZPtYL+QcflObN05Twu3pSn9DqztguYNYTkGwCoGKqALLCqKQKoHHjogGQZNrAqpXi8xo3zr3F5Vn0e+jrvySnNhIAdQfCpvIn1dwnaze6iy+WTjwx7c5pWW0Db/+x1t2dssIMAIBKQAsYAMDOcQVQT0+PjjrqKDfWgnyybwXvVCiU+YW8FJ15MznwtiRp9dbh0ZtEK2kUSPtspBgDoLQVQDNmqHb8qNjtEtvAPB5pwgTTHlcmohVAvgyJTLQCKNIC1rEzufLHzt4ql4ajCiCpuErIAADIMyqAAAB2jgOgc889V/fff78ba0E+DaYCaNmy7F7IP/mkpnT/Q5L03of10aujO0hZM4BSKMYAKO0QaK9X3ttuVbUirU72AMgajLxgQdqqllKUFACl+txqaiRJ/irz7DOwK8t2rAytctkEQEHZdmIjAAIAVDB7BdBguv4BAOXBcQtYIBDQz3/+c/31r3/VgQceKJ8vftvrW265JWeLg4sGMwMo21k2b7+tyVotSVq9NnaqxVUAlVAAlHYItCTNmye/P6idgYQAqKXFhD/9DDcuNU4qgGqrIsFYuCa7O8/QKjegFjAAACoUFUAAADvHAdBrr72mgw8+WJL0xhtvxF3nsW8DjeKWqQIow85ekrKfZePzRQOg9es9CgRMsFPqAVBSBVCEv9GnnQHbVvCnnSb96ldlVfljyaoCyGoBi1QAdXv8JhBbty51+6DHY67P0CpHCxgAANljBhAAwM5xALRkyRI31oF8SzcDKJstumfMyO6F/LhxalaHGqs6tbOvQe+/L02dmjAEOs2zkWLcBj5tC1hEdM1WBVBDQ1mGP5Ktja868swy0wwgT3fkYzzSzxeaIeGJsmyVIwACACB7VAABAOwczwCy/Otf/9Jf/vIXdUV+m4RTBQEoXqkqgLLdotvrNYFQJgsWSB99JI+kyQ2bJEmrTTGQsxlAH26VHnhAWro09uq/QDK2gMm2ZisA2rTJ/UUVSLQCyAqAMlYAWQGQTIj44INSY2P8bVtaojvHZZIpALK6UQmAAAAwqAACANg5DoA2b96sY489VnvttZfmzp2rDZF5MOeee64uvfTSnC8QLkmcAeRgZy9J5oX6DTck37aqSvrtb831H34oSZoyfKsk6b33zE2yagFb8bwkqfu1VdKpp0qzZ0uTJsVCqALotwUscjzaAvbRR+4vqkCSAqBMM4AUaQGzsph586STTzZvNzRIS5aYdDCLOUnMAAIAIHtUAAEA7BwHQN/61rfk8/nU3t6u+vrYzk5f+tKXtGjRopwuDi5KrADKdmcv+xbd1qvxo4+W7r1XGj5c6rPt9BQJgCaPMSFPYgVQ2gCorU3+H15jbmsfqJxYiZRn/baA+cznHl1zmQZAfX2xr0VWFUCRFrDe3tgpo+3bY7ebNSvrVjnHLWDF1EMIAECeUQEEALBzHAA98cQTuummm9TS0hJ3fM8999T777+fs4XBZYkzgLLd2ct+u8WLzeWpp0qnny6df755/847zaUVAE0wr/pXrzYv4K2/RqWcARSpRPLLHI8LgFJVIuVRvy1gVqtTmQdA9kzF780QAFnbwCv2AdGCnG3bzKX9T5NZYAYQAADZs/+aZRt4AIDjAKizszOu8sfS0dGh2nSvjFF8ElvAst3Zy7rdjh3SCy+Yt487zlz+x3+YFrAlS6S335Y2bpQkTdnDnGbvvRf/ejxlBVCkEskKDeICICl1JVKe9NsCFjahVXfDSHNgyxZbyUv5sGd2dd7IM8uMLWCxb3o0PLICoGAwvmqsH9m0gAXlix0kAAIAVDB7BVAwWPBxigCAAnMcAB199NG69957o+97PB719fXpRz/6kWbPnp3TxcFFiS1g1s5e1m5MiTweacKE2BbdzzxjXo1PmWL+SVJrq3T88ebtn/0sVgG0j0lMVq+Orx5JOQQ6UmGUNgBKuF0+WVlCupyzttd8LoHWvWJfx82b87Cy/LICoOpqqVr9bwNfHeqOXp1UASTFPzvtR3YVQD5FJ1kRAAEAKlhioS1tYABQ2RxvA/+jH/1Is2bN0t/+9jf19PTo8ssv15tvvqktW7boueeec2ONcENiC5i1s1e2W3Rb7V+f/nT8bb/2Nemxx6R77om++J4cfEfSYdq6NZbbeKv6VN0XSg6AIhVG/QZA2VYs5VC/FUC9O83tho+VRo6UOjpMG9iYMXlaobva282n1N5u3q+pkVasapB0iNS9n5rbTQYYZW3LFQzK7zenWjQA3Lo1druenvSpWoJsAiBJ6lOVvOojAAIAVLTEv7F0dSVvxAkAqByOK4D23Xdfvfbaa/rkJz+p4447Tp2dnZo3b55Wrlyp3Xff3Y01wg2ptoGfN0+6/fbk2zY2Jm/RbQVAVvuX5TOfkUaNMhUekVf79f95msZUmS3R33rL3MxfHakcSfxTVKQSydo5KikASqxEyqN+A6AeU9USaBptvgZS2cwBam+Xpk6VDj00toHXrl3SoZfM1KFaoUPf+F9NnRoLhyQlBUBS5GsYDsdXADkIabINgKJzgAiAAAAVjAogAICd4wogSRo7dqyuvfbaXK8F+ZQ4A8hilXBMmiSdcIJ0223S0KHSSSfFbrN+vfSPf5gw5phj4j/+j39MGXpM7ntXH2q0/vHgPyTtK78vJPWkePxIJZL/C1+XJPWoVn3yqErh1JVIedRfC5g/YEKN7saRJgB66y1p06Y8rc5dHR39b6gVCJjbRauAbAGQ9TXr7pb5ntuHEDgYBJ1pBpDPNvqnV9UmRCQAAgBUMAIgAICd4wqge+65R3/4wx+Sjv/hD3/Q//7v/+ZkUciDVBVAUqxE5xOfkG66yYQ/H3wgPf107DZ//au5PPRQacSI2PHIDl6pTNF7kqR/PPovSVJdbWTwb6otKebNk/++X0Tf7ZHZTUotLcmVSHnUXwVQ7a4t5nb1w8uuAmhAIruAJVUA2at/JCqAAABwSaoWMABA5XIcAP3whz9Uc3Nz0vHRo0frBz/4QU4WhTxInAFksQKgffYxSce//7t53zb4OxoAJbZ/RXbwSmWyVpu775ooSfLXZAiAJPn//YTo2wH5pSuvNFOkCxT+SFm0gO00A58DfgIgSelbwOzzfyRHFUCOA6D+ypYAAChjVAABAOwcB0Dvv/++Jk+enHR84sSJao8bAIKi1l8F0D77mMszzjCXDz5owppwOH0AlGFnLqsCaJWmSpL8VhtVmmciPp/kkQmJAvKbwKoAbV92GVvAtm2TP7jd3K52CAGQlLIFbLAVQJlawKqqJI/H7P9FBRAAAMkVQGn+7gYAqBCOZwCNHj1ar732miZNmhR3/NVXX9XIkSNztS64zT4DKByZrxMOJwdAn/qUNHmyqb555BHpwANN0FNXJx11VPx9ZtiZy6oA6o4Mdfb7w7HHT8HjkfxVPerq85sAqAjCxYwVQGvXqlYmbAiEfARAUiwA6umJfs26u5UcAOWoAkiSqqv6FAx5FZTP9oBA+bN26UunuTlhlz4AFcH6FdvUJO3YQQUQAFQ6xwHQl7/8ZX3zm99UU1OTjj76aEnS008/rYsuukhf/vKXc75AuMQKgPoiW2X7/WZg8ccfm/RlqqnUkccjnX66dN11Zvjy3nub4zNmJJfCRHbw0rp1JkyysQIgS11d5I0Mf4ryK6AuFU8AZGUJ6QKg6Nb1AREASelbwLrdmQEkSdWekILyUgGEimLt0pep49Hvl1atIgQCKo1VATR0KAEQAGAALWDXX3+9Dj/8cB177LGqq6tTXV2d5syZo2OOOYYZQKXEmgEkxdrArOqfyZNtCY2k0aPN5SuvSPfdZ95+6SWprS3+PiM7eEmK7dgV0aJ1qlasDtlfF7k+QwAUraiRX3r//f4/J5dZL65StoAlBkDW14wAKKczgKwWsEwVQBItYKgsTnbpA1BZrF+xQ4aYSwIgAKhsjiqAwuGwNmzYoHvuuUfXX3+9/v73v6uurk4HHHCAJk6c6NYa4YbqarNLU0+PCYBGjkxu/5JMyHPhhckfv327NH9+8q5c8+aZYxddFDcQunrCOLX2dOu9D00o4K+LZI8Znon4+8x1AfnVvqZLHcvDScGSJR/tDRlbwNrbowFQd7diFUBlsg18c7P5vPurMIibD2/bBSxuG/gctIClmgEkmQogSeqlBQwAUOHC4fgKIIkACAAqneMAaM8999Sbb76pPffcU3vuuadb60I+NDSYF99WFU5iAGRt657QziUpNjfo4oulE0+ML8mYN88cW7bMzAsaN06aMUNTPuvVex+am/gbIgGQfQaRXSAgv8yzlHZN0OzAEgU+kTr8kfLT3tBfC1htpKAurgVs82bzdSzwAOvBam01X9+ODumuu6Q77pBOPlm6avJvpFt+In3239T8sxviv/7pKoBc2gZeknxVkQCoYajU6ey+AQAoJ1bVrEQABAAwHAVAVVVV2nPPPbV582bCn3LQ0GBm/iS2gFkBUIZt3SWZ4GbtWnO7WbPir/N6k47ZN4/z10dewff1mRAqsa9q27ZoRc2mxt0V2FmnTKz2BjcDoP5bwMbEbmcNRA+HpS1bYoFQCWttNf+GDzfvt7RI08ZtkLRSGrW/lPi1zzYAyuUQaKsCqH6ICYDYBh4AUKHsO4ARAAEApAHMALr55pv17W9/W2+88YYb60E+WXOA0gVAGbZ1j5Pl7ewBUF2j7RV8qjlAW7dGA6CeYWOyW4fL+tsFLK4FzOeLJSVlNgfI+jrU1Snzvuy2XcDitoFPnAGUo23gpYQAyOF9AwBQTux/X7FmALENPABUNse7gJ122mnatWuXDjroINXU1KiuLr4yY8uWLTlbHFxm3wp+2zaze5cUC4AybOsep5/bWdsT27u8tu+s0oqqT0h9ITX/q0ethyV8UFwANFrKUIiUD+FwLEtIqgCKVELVylTFRYtORo0yFVZlFgBZfz2sq1PmkpwUFUCubwMvAiAAAKT4CiCGQAMApAEEQAsWLHBhGSgIKwDq7JTeftu8PXasNGyYeTvDtu6STKLT0mJul0a67Yl/+zuPfqtXJEn+GX1a9U5C+9a2bfJHXsx3N40cwCeXW/aMIqkC6KOPpO7u+F3AJBMAvfNO2QZAfr+k7iwqgPI4A6jaY9YTrCMAAgBUNuu5S3V1rOibAAgAKpvjAOjMM890Yx0oBHsAlGoHMGtb9/nzTdhjD4Gscp4FCzIOOM5qe+LuquT5PVu3qlZmF6mexhHZfT4usn8OSQHQ2rXm+IgGaUtCACSVXQAU1wK2K0MiY9sFLGUANGKEmY80gG3g07aAWRVA/kZzgAAIFWBAu/QBKHtWBVBNTeR3tgiAAKDSOZ4BJEnvvvuurrrqKp1yyinaFNnmetGiRXrzzTdzuji4zD4DKFUAJMW2dR8/Pv54S0vyFvC5ZGsB664b7s5jOGDPEaxcI8oKgMYOi7/t6NHmsky2grfEtYBlMwMocRt4awaQ9fXJZQWQzHoIgFBJrF36li+Xnn46dvy668yx5cvd3yURQPGx/r7i81EBBAAwHAdATz/9tA444AC99NJLamtr086dOyVJr732mq6++uqcLxAuss8AShcASSbkWbNGWrJEuv9+c7l6tXvhjxQ/A6h+qHuPkyX7DmCJO9ZbAVDtbiPjbluuFUBxLWAOZwDFVQBZX5+czgAiAEJlam2Vpk2T9t47dmzsWHNs2jTCH6ASWb9eqQACAFgcB0BXXHGFrr/+ei1evFg1tlKI2bNn64UXXsjp4uCyVC1g++6b+rbWtu6nnGIuM7R95YRtG/jq4U3yK/MzFrfbG/rbAUyS/OMrIwAayC5g0QCoKyxt327esSqAchgA+WTq3XtrI+c2ARAqjL0NrL/2WwDlzWoB8/kIgAAAhuMA6PXXX9fJJ5+cdHzUqFHavHlzThaFPLHqgbdskd57z7ydqgKoEGwVQP6hft1cc5UkaeSwXr34onT33eZmw4ZJf/ub++0NaXcAk8yka0n+1tFxty3XAGggu4BFt4Hv7I3NkhpAC1j/M4AiFUBWAMQrYFQYAiAAFiqAAACJHAdAw4YN04YNG5KOr1y5UuMT58SguFkVQH//u9TXJw0danoGioEtAAp0e3S/93RJ0jdPeF+HHy6ddpp5MrN1q7l0u70hmwqg2onmaxcMRnKRMg+ABtIC1t0ZuX1NTWxP2ly2gIWpAEJlIwACYElVAbRrV+HWAwAoPMcB0KmnnqrvfOc72rhxozwej/r6+vTcc8/psssu0xlnnOHGGuEWKwBavtxc7rNPigE3BWILgJ55Rnqx62DVqFvnHfySJJMfHHmkual96KlbrBwhYwvY5HHxty/TAMhxC5h9BpC1a9jQoYqfDJ2d/mcARQKgmnrH9w2UA/tf9wmAgMpGBRAAIJHjAOiGG25Qa2urxo8fr507d2rffffV0UcfraOOOkpXXXWVG2uEW6wAKDLI2432L2t74kz81b1x83va26UV68Zos8z271Y+dZye0Lq3tlsdV5o501zmIwCyD4GOEwpJ69dLkvy7xyrg4gKgjg5TYVUmsm4Bs20DH20B2xX5OgwdGrs+l9vARyqAgj4CIFQme+jD6Q9UNmYAAQASpXkZlZ7P59NvfvMbXXfddVq5cqX6+vp0yCGHaM8993RjfXCTNQPI4kIAZG1P3NGR4srrr5ceblPzRWeptfWbkkz4M3WqFAj8Munmf9Ln9adfSP77zH0efbQ5/vTTZqyMm8VLaVvANmwwIUh1tapbxsrrNe8GAooFQKGQ6VUbMcK9BeZRXAuYwwqg7kBk/s+wYe5UAIUTKoB6e034VuU46wZKEi1gACxUAAEAEjkOgCy77767pkyZIknyFEvbEJyxKoAsLg2Abm1NM6NnwkeSVko1n40e6ujo/0VLIGBud/jh5knNxo3SP/8p7bVXTpcdJ+0QaKscabfdJK9XtbWmvz4QkFnc0KFm2/NNm8omAIprActmBpB9FzDrezvACqB+A6C+SABUbUvqurtjz3yBMkcABMBirwCy/uZHADRw7e1p/qAZ0dzs/kxKABisAf1Z/O6779b+++8vv98vv9+v/fffX3fddVeu1wa35SkASmuQz0bq6kwIJJk5QW5KWwEUmf+jCRPiri/XreDD4cFVAAW6Iz9y7AFQTiuATJjU60sIgIAKQQAEwEIFUO5YFeqHHpr+39Spsb8LAkCxchwAfe9739NFF12kz3/+8/rDH/6gP/zhD/r85z+vb33rW8wAKjX2AKi2Vpo0Kb+PbwVAg9iSIl9zgPoNgCJ/8om2OpXpVvDBYGwX9wFtA99jC4CsgzmcAeTriwRA3tpYTyCvglFBCIAAWFLNAOrpif3qRvacVKgDQDFz3AJ2xx136Be/+IVOOeWU6LETTjhBBx54oC688EJdf/31OV0gXGTvZxo/Pv3t3JKjAOj6692fA5S2BSyhAigadJRpBZD9L4cD2QWsuzcSAA0b5rgFLByOhU/pW8AiAZCqzTcjEKACCBWFAAiAJVUFkGR+lzc2FmZNAIDCchwAhUIhfeITn0g6fuihh6rXejGI4tfWJn3jG7H333vPVAAtXCjNm5efNVjPRgYRAB15pMke1q6V1qyRJk/OzdIS0QJmWAGQxxPJb7LcBSz6demN/MgZwDbw9r9Y9hsAhQmAUJkIgNzHHBCUilQVQBIBEABUMscB0GmnnaY77rhDt9xyS9zxn//85/rKV76Ss4XBRW1t0vz5sXIKy7p15viDD+YnBMrBRMKGBumww6QXXjBVQMUSAJVrC5j96+DxKOsKoNqasCSPgn3V6pNHVQMYAm3Pl1O2gIVCqlZkCLRVASQRAKGiEAC5K7ZTZfrb+P1mp0pCIBSavQKoqspc9vQwBwgAKtmAdgG7++679cQTT+iII46QJL344otau3atzjjjDF1yySXR2yWGRCgCoZB00UXJ4Y8U66G6+GLpxBPTl1nkSg5awCTTBmYFQGedNfhlpdLvLmAVVgEU/UtiNjOAJPmreyWZ97tVqzo3KoB6elQtkxIF+7wEQKhIBEDucjIHhAAIhWZVAFl/b6mrIwACgErnOAB64403NG3aNEnSu+++K0kaNWqURo0apTfeeCN6O7aGL1LLlkkffJD++nDYVLUsWybNmuXuWlIEQM3Nkt8XUiCYPnzye4Nqbo6FCzNnSj/8obuDoFNWAHV3m+3dpegz/aQZQKNHm0vrdiUubgcwKbsKIJnvmRUABeRX3QBmADkJgHrDBECoTARAACzWr1fr13F9vbRtGwEQAFQyxwHQkiVL3FgH8mXDhtzebjBSzABqbZVW3fCgOi6/SZo+w8wksvzhD9IPb1Tz7EPU2nq3JFOA09BgSptXr5Yef1waOzb2IbmaxZAUAIVCplVOMs+shg2Lu75cK4Csz8tpBVB1OKiqKqmvzwRArswACgYJgFDx7KEPpz5Q2VJVAEkEQABQyQbUAoYSNm5cbm83GGlmALV616lVK6XWfaRptis2Nkg/XCl1mPa1VLMYjj8+/iFyNYshrgWsrc200VmVVMGgGT60cKH8/nlxty+3ACipBSzLCiBPr9kKvqvLFgBZbYgDmAHUbwVQyEMAhIpk/3FKBRBQ2RIrgAiABq652Tyn7G/+V3Nz/tYEAANRVegFIM9mzJBaWtLvl+7xmHk2M2a4v5Z0M4C2bTOXkaqaKCvFef99Sc5mMQxWtALoX6+bQdmJbXSRAdq1H62Nu300AOroSD13qcQktYBlqgDyek1plhS/FbxqTQBk/UnSYQWQxxO72zg9PfJZQ6B7laIfDyh/tIABsNiHQEsEQIPR2mr+oLh8uXT33bHj8+ebY8uXM/wdQGmgAqjSeL2mrWr+fPNK2h5KWKHQggXuD4CW0gdAW7eay3QB0McfSzt2SGpycXHxogHQo3/IOEDbv/JFSROSA6Bg0ARbiZ9TiUlqActUASSZPzt2d0cCILMTWEB+83WwEh2HM4DSnpr2CqBepdiSDSh/BEAALPZt4KWUnfdwoLXV/LP+TimZpxjTpqX/GFSO9vbMf3TO1VgKYLAIgCrRvHlmfo29jUkylUELFuRnC3gp/TORdAHQkCHm2Natkd239nN1eXbRFrBtH6a/UTgs/67NcbeX3y81Nko7d5o2sBIPgBztAibFAqCeHtX6+iR5Yy1gO3aY2zhsAUuXNSUFQLSAoQIRAAGwUAHkDvvTikz7qqBypBpLkShXYymAwXLUAhYMBnX22Wfrvffec2s9yJd586Q1a6QlS6T77zeXq1fnL/yRYhVAvb2xP1NJsQBo6NDkj5k40Vxa26/nSbQCSJlfUVnXx/0CKKM5QI52AZNif3YMBuX3mbCou2aIOT7AIdBpK4DsQ6AJgFCh7D97envjZ2dh8Kw5IJkwBwTFIl0FEAHQ4Nj/bkUABCm/YymAwXIUAPl8Pj388MNurQX55vWard5POcVc5qPty84KgKT4ZyPpZgBJsdg8zwFQtAJImcME6/qUAVAZbAXvaBcwKT4AqjavRAMNI80x60+SoVD8Fl9pOGkBCwZFAISKlPgElNM/t+xzQK6/Pnb81luZA4Lik1gBlGbvDThk/7n60UdUWwIoLY6HQJ988sl65JFHXFgKKk5tbWzukL0NLF0LmJQ0CDpfohVAIxszDtD2DzGhQ9yLrtGjzWUZVQA5mgEkmQDIGwmA6keYY1ZAI2XVBmYFQLSAAeklvhDhhUnutbaamR/2zTJHjjTHpk0j/EHxoALIHYlPWdatK8w6AGAgHM8A2mOPPfT9739fzz//vA499FA1NDTEXf/Nb34zZ4tDmfN4zLORXbuyD4AK3QL29bOlG36ZdoC2//Ofln5TQS1gDiqAaqvMM6ZA3XBzzPqTpGSeTUVTpdSsrCnrIdBNBECoPARA+WP/0bJlS+HWAaTDDCB3JD6t+OADaffdC7MWAHDKcQB01113adiwYVq+fLmWL18ed53H4yEAgjP19Sb8sT8byTQDyFYBZM1i6G/gWi5mMURbwI75lHRI+gHatWv2L+sAKG0LWLqyHOtZZzAov8d8Ebv9Q+Ovk7IKaVyZARQKScuWSRs2mD/nz5iR/1ZIIIdoAcsf+9f2448Ltw4gHSqA3JFYAcQcIAClxHEAtHr1ajfWgUqVuBV8X5+0fbt5O1UFUEuLuXzrLbW+t1Sr/jFDHR/HXrAHAtKcOVJnp3TXXdJxx+WmHD9aAeSXGZT9uc/FAoa2NumEEySvV/7b428vqawCoLQtYP1VAPX0yG/NR6odYo55POb6YNBRC1imCiCfgrFlWd+fdAlhW1vqIG/hwvwOQwdyiAqg/LF/bQmAUIzSVQCxDfzgpKoAAoBS4XgGkF04HFbY3gYDOJUYAO3YEWutSqwAamuTvvhF8/bmzdLs2Wo9epKmrWmLzl446qjYTZYvz90shrgASDLbuluOPz6aSljXxz05KMMAKKkFLIsZQLVh88GBGtv31cGcHsfbwKf8ZkS0tUnz5yc/a1u3zhxva+t3PUAxIgDKHyqAUOyoAHIHFUAAStmAAqB7771XBxxwgOrq6lRXV6cDDzxQ9913X67XhkqQ+Ocoq/2rtjZ+r13rBfuGDfEfn+IF+6mnmsvf/z5+d/nBiLaAWXOLrXXW18e1MllLtl50tbdLK7btrhU6RCveH6kVKxT3L8+jjAYtqQUs2wqgYFD+PvOMs9vXGLve+trlqAIoqxawUMhU/qQKr61jF1+c1c5kQLEhAMofZgCh2DEDyB3W/31rTxACIFhjKTLJ1VgKYLAct4Ddcsst+t73vqcLLrhAn/rUpxQOh/Xcc8/pa1/7mjo6OvStb33LjXWiXCXuSZpqAHR/L9g9HvOC/cQTJa9Xs2dLY8ZIH34oPfGEKdAZrKQKoDSDqu1dR+3t0tSpUiAwXdIKaZWkQ+Pv1+8vrS2DBzME2t/XKUkKVBc4AFq2LPOztXBYWrvW3G7WrH7XBRQT6//okCGmm5YAyD1UAKHYWX8EIwDKLespy4QJ5rne2rWFXQ8Kr7XVPJ/v6JDefVf69383x++9V9pvP/N2c3PpPN9HeXMcAP3P//yP7rjjDp1xxhnRYyeeeKL2228/XXPNNQRAcCaxBSxVsOLwBXt1tfSlL0m33Sbdf79LAZD1bD8hALJ3HXV09P/iKxAwtyuVXwhpK4Cy2Qa+1wqAbDsH5rIFzDYEOhjMcN+JVWTpZHs7oEj09cVemAwbRgDkNmYAodhZPw+sX8WJf3PDwFhPK3bf3QRAVABBMs/lW1tjlWGSNGmSGVEBFBPHLWAbNmzQUUcdlXT8qKOO0gZeMMGpxABo2zZzaQ9WBvCC3WoDe+QRMxB6MHp7Y9UnSS1gw4fH3TaxBazcJA2B7q8sx7YLWG2vmZsUqGpIvj6fFUDjxvX7WI5uBxQJ+6lu/Qgt159FxYAWMBQ7KoDcYT1lmTLFXH74YVZPY1Ah7OcCv4NRjBwHQHvssYd+//vfJx3/3e9+pz333DMni0IFSVcBZB8APYAX7GPHSuPHm7tduFCDmr1jf5LfXwVQfxtPlbqkFrBsK4B6euQP7pAkdVfVxa53UAGUswBoxgyz25f9TzR2Ho+p654xo981AcXE/nPHyqbL9WdRMUhsAWNPDBSbxAogAqDcsP7vjx8fe6qxfn3h1oPiQgCEYue4Bezaa6/Vl770JT3zzDP61Kc+JY/Ho2effVZPPvlkymAIyCjx2UiqFjDrBfu6damfYXs85vrIC/b2dmnvvWM/dL/7XfPPzsnsHfsP70qvAEpqAXMyA6jbhHwB2abk5aMCKPGb4fWaVHD+/OT7sEKhBQsyPBBQnKxTvapKamyMP4bcswdAPT3m15j1Nw2gGDAE2h3W17W21jz9fPdd0wY2aVJBl4UiQQCEYue4AugLX/iCXn75ZTU3N+uRRx5RW1ubmpub9fLLL+vkk092Y40oZ9nMALJesEvpqzZsL9idzN7JhvUk3+u1FbqkGQKdaefxcpDUAuZgBlBtt2nvC6g2dr1LM4AyVgBJ0rx50oMPmkm5di0t5vi8ef2uByg29lll1v9Rnny6J/FrSxsYik26beCtp1wYGPvOsC0t5m3mAMFCAIRi56gCKBgM6j//8z/1ve99T7/+9a/dWhMqSTYzgKTYC/aLLor/LVtXJ/36166+YE8aAC0ltYC1t5tAydoJorNTeust15ZUMHEtYOGwswqggPnedodtAVCOK4B8Ms92e3vVfxo3b5707LPSrbea9598Upo5k8oflCz7zyoH2SoGKPFr+/HHsReDQDGgAsgd9q+r9X+encBgsf9uIABCMXJUAeTz+fTwww+7tRZUomxmAFnmzZPWrJGWLJGuvjr28Sed5OoSrR/etbbcwt4CZm33fuihsaV0dkqnnebqsgoirgWsry92RX8VQLt2yR/cbu6jzxe7vhAzgOzsz4KPOILwByXNHgCVeztqMUgVAAHFJF0FEAHQ4FABhEzsf9Pk/xqKkeMWsJNPPlmPPPKIC0tBRcpmBpCd1yvNmmWG+jQ1SZs3S3//uytLa283A6Otu6+qsg2Sfn+k2jVBGjYsq5azdPy+kJqbc7Zk18W1gFmJjNT/LmAffSS/zBcp0OtLvj6LCqB+W8AGEgDt3Bl7m9/SKHEEQPlFCxiKXWIFENvA50aqCiACIFhoAUOxczwEeo899tD3v/99Pf/88zr00EPV0NAQd/03v/nNnC0OFSCbGUCp+HwmCHrsMWnxYmnatJwuy6rqsf/g7ugwVT7GbfLrJq0KLs36Pn+tU7VCh+oWXaoD9Kp+pXPU3OxT6/jnJJVG5UlcC5iVyEj9VwB1dKhWJogJdNvmOLk0BDoYVHYBUGdn7G2eEaPEEQDll30+XChEBRCKT7oKoJ4ec85S9Dow9gog6+kqARAsBEAodo4DoLvuukvDhg3T8uXLtXz58rjrPB4PARCcyXYGUCpz5pgA6IknpO98J6fLymqQtOrUoezLd/bR2zpGS7RAF+t1HaSh2qrWDe9Jy5aZMKvI9fXFfqllXQFkC4D8kR83cXlMLlvAnAyBtlABhDJCAJRf1o+WMWPMFtAEQCg26WYASeZnQ8LfcJEl6/9+TY00YYJ5mwAIFgIgFDtHAVA4HNaSJUs0evRo1bPXKXLByQygRMcdZy6ffdZ8vMNzMnFIc3NzdtvCx2lqcnTzcdqoT+uvekKf0W/0Ff23vi9t2ODwQQvD/kusrk5S0EEF0Ecfya/hSfeTl23gqQBChSAAyi/rR8vYsSYAogUMxSQUMns1SMkVQJL5lUcANDCJ28BL5qlcMBj7WqNyEQCh2DmaARQOh7XXXntp3bp1bq0HlcbpDCC7vfYyf3rp6TFVNBHNzQk7dqVx2mmmpcv6N3Wqaf1yJHEb8Sx8Rb+RJP1apyksSePGOb6PQrDnI36/HFcARVvA7L8Mc7kNfLoAKNNvXyqAUEbsLZoEQO6zvrbWj3AqgFBM7C9Crb+1VFXF3mYr+IGzVwCNGmWe6oTDJfP3PLiMAAjFzlEAVFVVpT333FObN292az2oNPYKoHDYWQDk8cSqgBYvjh5ubZVWrZKWL4/9+/Wv+7+7QMC0fjnisAJIkk7Ww6rTLv1Te+mV0Z+TZsxwfB+FYP0Sq66OhDBWIuPxmGeVqcS1gJk7iMt6qABCtkIhaelS6YEHzKU9gIQkKoDyzfrRQgCEYmTN/5Hiq1LYCWzw7BVAVVXS+PHmfdrAILENPIqf413Abr75Zn3729/WG2+84cZ6UGnsAdCuXbEXddkEQFLKAEgyIdC0abF/++yTm+UmGUD9dJN26iQ9Ikn6zSduLZkpjHE7gElZJDKK+1NjdBewAVYAZTMDyCfzjLe3V7FXwKFQ+rDAXgHEb+ni1dYmTZokzZ4tnXqquZw0yRxHlHUK19URAOWDvQVMIgBCcbH/XYUAKLfsFUASO4EhHhVAKHaOh0Cfdtpp2rVrlw466CDV1NSozt5QLGkLTfBwwh4AWdU/Xm/283yOPdZcvvaa9OGHZhpnPlVVRVvOMv2Q9yugZpnyonZN0BHD3tYDW6V7n99DX3k5vq1pQLOI8iBuBzApi54sxT3rTNkClo9t4CXzbC3VOUUFUPFra5Pmz48Ns7CsW2eOP/igNG9eYdZWZOwVQA6yVQxQYgUQT39QTKwKIK83/g8nbAU/ePYKIIkACPEIgFDsHAdACxYscGEZqFj2P0XZ2788nnQfEW/UKOmQQ6SVK6W//lX6ylfcWGVGVstZpvax5uE+tZ46Xu0vSlO97yqw1QQjW7dKhx8ef1u/39xfsYVA9uoCSdlVANkCINcrgJwGQOEwAVCxC4Wkiy5KDn8kc8zjkS6+WDrxxJKppHMTLWD509cXe4FNCxiKkfUiNHEoMRVAg2ffBl5iJzDEIwBCsXMcAJ155plurAOVKlUFULbtX5bjjjMB0BNP5CwAam42v9gz5RJ+T7eam81v/9bW/gIbr3TIIep4sVuBUOYtIqxZRMUWAA22AsgKgHp6Yq/d3ZoBFA5LIU+1vB6PeSfVN7KrKz5Y4Nlw8Vm2LPMz6nBYWrvW3G7WrLwtq1gRAOWP/UcKLWAoRlZAaf2atRAADZ71lCWxBWzt2sKsB8XF/pSW/2coRo5nAEnSu+++q6uuukqnnHKKNm3aJElatGiR3nzzzZwuDhXACoC6u2P18wMJgCTp//5Puv/+nAyIbW2VbrrJvN3SIv3tb7ah0jcs0nJN06ojznQW0hRbouNQriqAJNuLJ5cCIEnqDXkyVxjZ5/9I/JYuRtluqcLWK5IIgPIpXQCUqlgNKAQqgNyTWAFECxjsqABCsXMcAD399NM64IAD9NJLL6mtrU07Iy+iXnvtNV199dU5XyDKnL0tx3oRN3Sos/uweq+2bDEVQDkaELtokbn86lfNNvHRodLDV2uaVqp1bP+hRZwSD4DSDoF2OANIsv1CzOU28MFgfADU305gBEDFz+qtydXtyhwBUP7Yv67W6LlQSNqxozDrARIlVqlYrN/hbAM/MOFw+gogAiBIBEAofo4DoCuuuELXX3+9Fi9erBrbb5XZs2frhRdeyOniUAGi/USKBUBOKoDa2syuQImsAbGREMga1NzfUpqbzdsbN5qOMilFV5lV5z98ePbrlMomAEpqAcuyAqhGsd+IeakAsgdAqX4D2+f/SARAxWjGDPPMOt1MMI/HDF+YMSO/6ypSBED5Y68AqK+P/aihDQzFwmoBowIot3p7Y5V+iRVAGzbEnhqhcrENPIqd4wDo9ddf18knn5x0fNSoUdq8eXNOFoUKUlUVe6Wyfr25zDYA6m9ArGQGxIZC0UHN0TauyL+77zY3q6mRXnghltH89rdmyOcRR0h77plw3wOdVVTiAVDaFrBMFUC2kNgjyV8Tirsvt4ZAS1QAlQWvV1q40LydGAJZ7y9YwADoCAKg/ElsARkxwlyyExiKRX8VQPzKGxj736usr+2YMeapUChkNqRFZaMCCMXOcQA0bNgwbUgxb2HlypUaP358ThaFCmO1gTltAXMyIFYmf4m2cUX+nX22uezpkf7859iH3nefuTzttBT3O9AAaLfdJM+Axm4VhaQWMIcVQFKKgpwcbwPvVZ88nnDs9tar4FQBEBVApWHePLPVe+Lvl5YWtoBPQACUP4kBkFUQSgUQigUVQO6wP52w/v97veYpnkQbGAiAUPwcvxo99dRT9Z3vfEcbN26Ux+NRX1+fnnvuOV122WU644wz3Fgjyp0VADmtAMrBgFiPxxQRSdJPf2qeMP3jH9KKFSZo+NKXUnzQQFvAqqul0aOdfUwRSWoBczgE2v6xrlQARZ7tVnttARAVQOVh3jxpzRqT1krSkUdKq1cT/iQgAMof+9daIgBC8UlXAWQ95eJX3sBYX1ePJ/75CDuBwUIAhGLneBv4G264QWeddZbGjx+vcDisfffdV6FQSKeeeqquuuoqN9aIcmf9OcrpDKAcDYg98kjz5H3dOuknP5HeeSd2vL3dDEqM694aaAWQpOYJdfJ/2KWA6tLexj6LqJgktYA53AZekvx1pm3HrRlA1nKCvVkEQC5UALW3x2aSp9LcXPKdgIXj9cZeuTQ00PaVgj2ktZ/64XD6MUoYGFrAUOyoAHKH/f++/ecqg6BhIQBCsXMcAPl8Pv3mN7/R97//fa1YsUJ9fX065JBDtGfSoBQgS9aLuo0bzWW2wYo1IHbdutRzgDwec32GAbHt7dKBB8Z+QF95Zey6ZcvM7l9+v5kfFH3hPtAKIEmte9Zq1d+mquPiG6TTT9fzz0sXXijttZf0wAPmNsUaEqTdBSzbCiCPJxoAJVUAOQiAMrWASbEKoGBQea0Aam+Xpk7N/Ms+6VyCM9YXl+1rUkpVASSZ/xrWfwXkRqm1gBFOVx5mALkj3deVAAiWxACIP8Kg2DgOgCxTpkzRlClTcrkWVCorAOrrM5fZzgCyBsTOn29+stpDoCwHxHZ09J/OBwLmdtEnx4OoAFJrq1q1Vq19f5OmnR79C113d6y7pVil3QUs2wqgoUNVW5sQAFnPoBxsA59NBVD09nmsABrQuQRnrO8jr1xSslfp2QOgQIAAKNesU7EUWsAIpysTFUDuSAx/LQRAsCQ+5eSPMCg2pTuRFuXDCoAsToKVQgyIHUwANGGCuWxvlxR70VAKbQNpdwHLVAFk/xPZ0KHJM5kHUAE0oAAo1SsfqwKoqclc8my4+FEBlJG9Asjni+XglKDnnvU1LYUWMCfhNMpHfxVA/BgdmHRfV+vpHQEQEp/S8vQSxaagAdCNN96oww47TE1NTRo9erROOukkrVq1Ku3tzzvvPHk8Hi1YsCB/i4T76hLm4TgNVqwBsQ89FDv2j3+4E/6Ew7EAaAAtYNE/ryYEQDt2xCpcilXaXcAcVAAlDaZ1UAGUMQDq64vewHEFkDVwid/Qxc86cfhepWQPgDweBkG7qdRawFB5qAByBxVA6E9iAMTvYBSbggZATz/9tM4//3y9+OKLWrx4sXp7ezVnzhx1JrZmSHrkkUf00ksvaTdrn0WUj8FUAFm8Xunkk2N/hv3nPwe9rJR27owlEQNsAZMUDYDsd2HlSsVq0LuADR3q3jbw1jNdSdU+T+z22cwAGjXKXPJsuPhRAZRR4s5UBEDuIQBCsWMGkDv6mwG0bl3s6REqEwEQil1BA6BFixbprLPO0n777aeDDjpI99xzj9rb27V8+fK4261bt04XXHCBfvOb38iX+KcMlL7EACjbGUCJPB5p//3N22++Obg1pWOlND5fcuVSNqwAqKND2rVLPp/U2GgOFfsLh0HvAjZsmHvbwNt+21oP2dsrJfec2VhBMwFQ6WAGUEYEQPmT+LUu5hYwVCbr7yJsA59b6SqAxo6VqqrMc49Nm/K/LhQPAiAUuwENgV62bJl+9rOf6d1339WDDz6o8ePH67777tPkyZM1ffr0AS9m27ZtkqQR1jMpSX19fTr99NP17W9/W/vtt1+/99Hd3a1u24u97du3S5KCwaCCtiqBUmKtu1TX358qv1/Wa/qwx6Peurq4ig5H97XPPvI+84xCr76qvi99qd/bmwyj/1CxtzdolrRpk3ySwsOHq3cgPVsNDapubJRn504FV6+W9tpLw4dXa+dOjz76qFeTJqXYzWyAcn3e7NrllVQln69XwWBYnu5uVUvqq6pSKMNjWF/dvqYm1XT3SarSrl0hBYN9ksdjvp49PertZ53BoHl8KfKxdp2d0cfxRn6qBQK96vP5zEfs2qW+hPv3bt+uKkl9I0aoSlK4q6vfNWTi+FwqUsX886Y6EJBHUnjXLvX29LCtRoJAoFqSR16vOcf8fvP+zp3m/6ybivm8ccOuXVWSvPL5+hQMhtTU5JFUrY8/DisYLK5+3mL92VRp50y+dXWZc9TrNeeoxecz5+quzj71/vUpacMGadw4hadPz1zRWyQKfd7s2mW+ftb/fckUdW/eLI0cWa2PPvLoL3/p1b77xn7mjhzJgPVCy+d509Njfvdaduwo7ud9SK3QP2uccrJOxwHQQw89pNNPP11f+cpXtHLlymjYsmPHDv3gBz/Q448/7vQuJUnhcFiXXHKJpk+frv2tKg5JN910k6qrq/XNb34zq/u58cYbde211yYdf+KJJ1SfWGlSYhYvXlzoJbhivw0btEfk7d66Oj2+aNGA72tyOKwDJX20dKleyuJcfPfdoZJm9Xu7Z599Ths2bNPIN9/UdEmd1dV6coDn+uzhwzVk50698tBD+uigg+T1zpI0VE888bI++uijAd1nJrk6bz744FOSmvX22yv1+OPrNf5vf9MnJG3eulXPp/la1H34oeZE3l6zdas271onaYL+/ve39Pjj76r244/1WUnq7tbjf/pTxhf0a9dOkzRB77zzDz3++Htx11n3E/Z4FAjslDREzz77olo3bNAUSf968029nbDGI9as0RhJ7+7YoT0l9WzbpkUD/J5Kzs+lYld0P2/6+nRi5M9qnnBYix59VH1UhMbp6vq8JI+ef/4prVoVUDB4jKQmLV36ojo6NudlDUV33rjk1Vf3kLSfOjo+0OOPr9QHHzRKOlabNgX1+ON/LvTy4hT7z6ZKOWfy7Y03zDm6adNaPf7436PHX3utWdKn1PXqKlUfd1z0eNfIkXr93HO14cgj877WgSjUefPCC+MkfVKdnR/r8cef1Ucf1ekb3zg28kcq4+yz419e+Xwh3X77kxo1irKrQsvHedPZ+W+SYqV3S5a8oPXri7zMH2mVyu+oXQ7GIzgOgK6//nrdeeedOuOMM/Tb3/42evyoo47Sdddd5/Tuoi644AK99tprevbZZ6PHli9froULF2rFihXyZPmX3iuvvFKXXHJJ9P3t27drwoQJmjNnjoYMGTLg9RVSMBjU4sWLddxxx5VlC1zVyy9Lf/yjJKl61CjNnTt3wPflaWyUfv5zjenoyOp+2tul7343rEAg/fnl94d14omfUmur5IlU/dS3tAx4nd477pDWrtUnx41TeO5c3XKLV2vWSHvs8UnNnZvbCiDrvNmwwafNGV7/ZfPXqR/8wDy5OfLIQzR37sHyRHodRo4Zk/5rsX599M2JBxygKR+N19Kl0qRJ+2ju3KnRfglPOKy5n/lMxnayX//aPP4BB+yruXP3jr8yMlNJNTUaNqxJa9dKhx56hCZumSo9/rj2mDBBUxLW6P3RjyRJUw47THrkEdWEQoM695yeS8WqaH/eJPQrfPboowc2iL1M9fZKoZDp6p479xiNHGn+Gv3BB9LBBx+hOXPcrwAqyvPGJStXmq/17ruP19y547Rpk3TBBdKuXT595jNzi6qQYuXK7G43ffqndMgh7q7FrtLOmXyzztHJk1s0d25sfuaI15+RJAVC8b1h/i1bdNjNNyv0298qfPLJ+VuoQ4U+b7ZvN7/jx44drrlz52rlSsWFP6kEg14deODsvP7/Qrx8njd9fea5bH19WLt2eTRt2lGaOdPd38HIvUL/rHHK6nrKhuMAaNWqVTr66KOTjg8ZMkRbBzjF9sILL9Sjjz6qZ555Ri3WFDWZVrNNmzap1fZqKRQK6dJLL9WCBQu0Zs2apPuqra1VbWJjriSfz1cS37xMyuFzSMnahluSZ+jQwX2OBx1k7mfNGvm6u2MDdtLYfXdp1arM2982N3vU2hpZU2RwcNXw4aoa6DonTpQkVa9bJ/l80dkRO3ZUJ+3WkQsbNvi0//6+jD3Ifr/5OmQKJqyPb2yMX2eVz5f+a2GruvOOHKn6TvOEtLfXK5/PG/f98YXDyduV2IQjvztraiIfm+JKT01NpLxdkqrljQws8vb2ypt435EZQN6xY83HdnUN6txLPJeOPdaMjDrgAOlXvzLH4s6lIld0P28SNgfw9fZmPF8qjX3mQFOTL25MWSjkzs+WVIruvHGJVWldV2d+Ho0ebd4Phz3atSv2c70YjB1rfsb39ztg7FhfQf5LVco5k299kU5pv9/2OzMUUtP/3CzpWO1SfFW8JxyWPB5VX3aZ9IUvFH07WKHOG2seod9fJZ+vKuMYRLvq6sL8/0K8fJw31u/jIUM82rVL6u3N3+9g5F6p/I5yskbHAdC4ceP0r3/9S5MmTYo7/uyzz2rKlCmO7iscDuvCCy/Uww8/rKVLl2ry5Mlx159++un69Kc/HXfsM5/5jE4//XSdffbZTpeOYmVvzRvIzlp2zc3SmDHShx9Kb70lHXZYvx/S2uqgN9sKOQezzjRbwbs1BHrz5v4H0AUCJrjI9HVI2gY+m13Aqmxz5jdulL/GzABK2gVMMpMVM7RpZjUEuqYm9Tbwqb4AidvAh0LmVd0gfsjbzyWrErOvT5o2bcB3CUvi95CdwOLYvzzWac8QaPckDoL1+aSGBvNj5eOPVVQBUGtrLJzu7ZUOP9wcv+wy6ZRTzNvNzcwoKTfWr8W4X2nLlqlu0xpJUpdSbGQRDktr10rLlkmzZrm9xJJk/d9PHK4NSOappPV8dcgQaeNGfgej+DgOgM477zxddNFF+uUvfymPx6P169frhRde0GWXXab//u//dnRf559/vu6//3798Y9/VFNTkzZu3ChJGjp0qOrq6jRy5EiNHDky7mN8Pp/Gjh2rqVOnOl06ipV9N63BBkCStN9+JgB6442sAiBHrJRmMK0nCQGQ9UKh7HYBa2uT7LO7brlFtU0TJX0z9suwutrM/QmH+90KPuPD2Z7ppgyAstkGXjIpVw5S/u7u2JIcVGQik8RnUGxhE8f6clRXx/6PEAC5J9VOQMOHxwKgYmOF0zt2xI41NxNOl7OU25Vv2KA6mR8WKQMg2+2QmvV1TdFsAMQNe7Y2NebpCoqN4wDo8ssv17Zt2zR79mwFAgEdffTRqq2t1WWXXaYLLrjA0X3dcccdkqRZCX9luOeee3TWWWc5XRpKVS4rgCQTAD31lDtbwZdgBVCuWL/ArBeVGUty2tqk+fNjfVsR/h1myHXg7dWSJpvwp6bGvJrqZyv4jBVAtv1usw6ArAoge8jc1WX+ZDNI22xzVAmAcoQKoIySAloRALnJ+pES/XkoE+Z/8EFxbwVvfyGSqxcl7e39tVFTXVQI1q/FuL9pjBunepmfnT2qVUhV8qov+YPHjXN/gSUq3TbwgBT/t0zr6SS/g1FsBrQN/A033KDvfve7+sc//qG+vj7tu+++auxn1koq4bDzgVip5v6gxNkDICsuHwxrFzk3A6BcVQCFwxo+3MysSfeioVieXGddARQKSRddlBT+SJI/8pfH7udXSKFWk+ZYAVA/FUDZtoBZT3Z7exV7dZYYAIXDsQqgxsbYgIwcvSKyhz7bt5s2MHs3HAYg8XvIn9TiWP8/7YEEAZB7rK9pYgWQVNxhfq4DoPZ2aerU/ucL9TdjDrmXsgJoxgzV7TZCiuzPEJBfDbKF6R6P1NIizZiRt3WWmpRfVyAifh6fueR3MIqN45ck55xzjnbs2KH6+np94hOf0Cc/+Uk1Njaqs7NT55xzjhtrRLlzowJIMi1guWY9sx/MOsePN0+yuruljz7K+KLBenJ96KHp/02dGtsEy01ZzwBatsz8GTwFv8xvwcCukLmdlLlKxyarFrBsK4C6u2MTMhsbY59Ujn5L2yuAwuGk+cUYCCqAMiIAyq90LWBSZQVAHR3Zz5hDfqWsAPJ6Vbfwh9F349rArN12Fywo+gHQhUQFEDKxzo/q6tjLG34Ho9g4DoD+93//V10pnjV0dXXp3nvvzcmiUGHcmAEkmRDC/ko8F3LRAlZTEyuvbm/P+KKhWJ5cB4P2nS8iB60DiYlMhtkBtTK/GQPyx25n/RltEBVA7R9UaYUO0YreA6Nhy7vvSivWj9UKHaL2bQmVZVb1j2Qmt1rnYI6qShJPO9rAcoAZQBkRAOVXqheB1jy3Ym4Bs+em/Bcqb+kqVarmz1NNtfmFGhcAtbRIDz4ozZuXpxWWpsSva3Nz/M/dVPz+2H4TKG/284PfwShWWbeAbd++XeFwWOFwWDt27JDf9tMuFArp8ccf12hrH1TAiVxXAA0bZqps1q2T/vEP6cgjB3+flly0gEmmFn79ehMAjf+EpOL+q7H9l1dSC1hiIpNhdoBVAdStWmlcpDk6ywqgdAFQe7s09avTFdAK6R2Zf5KuvVa6Vv8m6d/kf75bq9ptLQhWSuT3mzvMcQCUGPhs22ZOSQwCFUAZEQDlV6oZQJVYAYTilbICKKKuwauebZEAyOeTnnjCtH1R+dOvxPDXvsvee+9JX/yimf2yZEnsY5iDVTkIgFAKsg6Ahg0bJo/HI4/Ho7322ivpeo/Ho2uvvTani0OFsP8Jde1a80p/sE9C9tvPBEBvvJHbACgXLWCSNGGC9OKLJgDaP/6ucyIUkufppzX+mWc04tAR8vunKxDwpL15f3+dsr9Q6LcCaMYM85fEdeuSh0BbLWC1Q6UZkR3aBlkB1NEhBYKZz5dAuDZ+m3v7/B+JCqBSQAVQRqkCIOtHK08+c48ZQCh2mWbV1NWZ31O7VG+SoiOPJPzJUqqvq7XLnvU8qrubHfYqlf38yPF0ASBnsg6AlixZonA4rGOOOUYPPfSQRli1zpJqamo0ceJE7bbbbq4sEmWsrU06//zY+9dcI911l7Rw4eDKkPff3/xFK9eDoHPRAibFDYK2XjTs2GGKatLtqp61tjbpootU/cEHMrVFt2jV2E+q49IbdUHbMXrhBemQQ6SVK6Xdd5d+//v+/zplvVCorY2NCUhbAeT1mu/f/PmxLd4jamV+MwZa94p9nPUKajDbwDtlVQA1NJhLlyuACIByILFCjAqgOFQA5VeptoARAFWOjBVA1q88qwVs2zaJKv6sZJoBZD2l6O7O0fM5lBzrqWxtLb+DUbyy/tE0c+ZMSdLq1avV2toqjyd9NQGQlTRbhWvdOnN8ML3obgyC7u01KY2UmxYwSWpvj8uStm4dZJ94mq9p64evqPXyT6t39w5JI/Stb0nnnmvm5Ph8/Zcmp9piOm0FkGS+bw8+aHYDsw2E9o9qlD6SAnWxADn6Z7TBbAPvFBVApYcKoIwyBUD9/NfCANAChmLXXwWQZAuAtm4lAMpSpq+rfUPkzs7cbGyL0kILGEqB42z6/fff1/vvv5/2+qOPPnpQC0KFyLBVuMJhUzly8cXSiScO7BW/FQDlsgLI/qp+sL/VrcRl7Vr5fOZJw86d5oXDgAOgLL6mW9ZslzRCu+8uHX+89PDD0v33SzfemPmuk3YAk9JXAFnmzTPfv2XLzMDncePkD8+Qjkl4QZplBZArAVCeKoByPYu8IjEDKCMqgPKLFjAUO6sCKFVQYY1ejAuAkJVMFUA1NeZvYr295mkGAVDlIQBCKXAcAM2aNSvpmL0aKGS9SgMyybBVuCQTWKxda26X4pzr1777msuNG6XNm6WRIwe0zDjWE6TGxtQ11U7YKoAk88LBCoAGLIuv6eZe82xkxAjp1FNjAdANN0hVGfYEtF4oxO10kU0i4/XGff9qXzKXcb8Ms6wAcqUFjAqg0kEFUEYEQPlFC5hh7YCU6RxjB6TCsF6IZtUCRgCUtUwVQB6P+bvStm2xpxmoLNbvBnsAxNMVFBvH28B//PHHcf82bdqkRYsW6bDDDtMTTzzhxhpRjjJsFT6g2yVqapImTjRv56oKKFcDoKVYALRxo9TdHX3hkBgAOdpetJ+vVUhV2irzJ+oRI0wF0JAhJoN6/vnMj5GyBWwAiUzKF6Q52AbesTxXABEA5QAzgDJKFdISALknVQBUiRVA1g5Iy5dL3/te7PhPfmKOLV9urmcHpPzLVAFEADRwmSqApNjflaynGagsVAChFDgOgIYOHRr3r7m5Wccdd5xuvvlmXX755W6sEeUow1bhA7pdKvtHttfKVQCUqwHQkqlIsp6BffBB2hcO9ifXkybFjv/2tymeXPfztfpYsblFI0aYh7dGLP3mN5mXm7IFbACJTMqZJIPcBn5A8lQBZI1UIADKASqAMkoV0vLk0z2ZZgDt3Bl78V1s7Llprv4LtbaaHY/sVT7Dhplj06YR/hQKFUDuyFQBJMX+rkQFUGUiAEIpcBwApTNq1CitWrUqV3eHcmdtFZ5umLjHY7ZKnzFj4I+R6zlA1hOkwQ6Alsznl2InsFR/ObaeXNvbikaPTvHkup+v6RaZNrghQ8KqrjaVP5/8pLnu/vull16SVqyI/Yt0p0lK0wJWoAqgxIdrbpb81b2ZH1dd8S0IeaoAamkxl8wAygHrpLF6FakAikMLWH6lmgGUONC/GLk5A8j+gnfz5tzeN5zLpgJolyLDgIr1hC1CVAAhE3YBQylwHAC99tprcf9effVVLVq0SF//+td10EEHubFGlCNrq3ApObCw3l+wYHDlHrneCSyXLWBSygAo3eyI7u74cCjl7exf00Qej7bI9JmNGOFRe7s0dar0jW+Yq7dvl444Qjr00Ni/qVNjIVDGXcAcfI+sJ0yBgG1WdZYVQOlmTre2Sqsu+B8t1zQtn3+jli+XTjvNXPeFz3druaZplaaqdTdbSJRYAZTjRm0r8JkwwVxSAZQD1klo/f+jAigOAVB+pXoR6PXGhr4W6xwgAqDKQQWQO7KtACIAqkxUAKEUOA6ADj74YB1yyCE6+OCDo2/PnTtXPT09uvvuu91YI8qVtVX4+PHxx1taBrcFvMVqAVu50pS4LF0aCy0GIpcVQFLWFUCStGlT/Ptpn1xbX9MhQ+KPt7Ro83/9RJLpPuvo6P8XUiBgbiflvgJIshX85GAGUGvdR5qmlZo2/kNNmyaddJI5/q811ZqmlWrV2viAKU8VQARAOWR9/6z/LFQAxUkVANkDV+ROOBz/V167Yp8DlBgApdo0cqDsL3gJgArP8TbwyEq2FUC0gFUmAiCUAsf76axevTru/aqqKo0aNUr+/ibVAqmk2CpcM2bkZtCL1ZK4fbv0la+Yt1taTJXMQMIlNyuAJsU/RKIPP4x/P+Nfl+fNk/70J+mXv5QkhS67TN4f/lBb7jdfU2vgtBO5ngEkmSdRtbXKzTbwCc90jzjCvPv6m1XaqQY1qtM8YGJzvsszgAiAcsh6BjVihPTuu1QAJchFBVB7eyz0TaW5mXkuUvyPqsSnPiNGSGvWlEYAZAVZ6V7IOmV/wZvpPEJ+WC1gqSqA2AZ+4KgAQib2XcCsp5YEQCg2jgOgidbOSkCuJGwVnhNtbbHQx27dOmn+/IFVGOVyCLQUHwAdYt5M96Jh48b49/v966p9R7Dx4yWvNxoajRzpeKU52wXM/oQpEIgUKuViG/iEZ2Tjx5vwZe1aj17RJzVbS1JXALkQAPX1JVcAMQMoB6yTkAqglDIFQP3815KkaFtof9t5s6NT/NcoXQVQKbSAWe+7EQBRAVR4VAC5gwogZEIFEEpBVq/cbrvttqzv8Jvf/OaAFwPkRCgkXXRR6tr2cNjMGLr4YlN55KTSqIAtYIkVQP0+uV63LvZ2JOywPmYwFUBxf+0eQAVQVZX5pdjTY/uFmMsKINufOo84Qlq7Vnqxerpm9yYEQNYzMxdawDo7Y6ceFUA5lBgAUQEUZ7AVQE7aQis9ALL/KEl8cV1KLWDW+7n6mwYBUHHJVAFEADRwVAAhEwIglIKsAqBbb701qzvzeP4/e38eHkd1Zo/jpxet1mrJi2S5vYIBY8AGs9rEJAESh4RgCGQIn2yTTDYChJlJMpNkJtsMv2x8YUhC1pmQEBgSRoFAzJaExRA2L4DBxruRF3mRZEnW0pJ6+f3x9tv3VnVVdVV1VXdJuud5+ulWdam7uurWvfc997znDSkCSKH0WLcO2L/f/P10mpiBdeucKY+8TgFj76Pdu9HY8SqA0/MqgMJhUpjkXV02IID4fzxLAXOhAAJoQBwdlYIomwogSwLIoNzJeecBv/898DzOy/18HxVArPaJRoEZM+i1IoA8gPIAsoQygS4eZIl/WOekOB4JIK+gCKBgwVIBVJkGEBIEkJKp2oZSAClYwYgAUutVCkGDrchN7/ujoBBoyOlPXuzH8DIFrL0dYLJ0dBSNX/4HAC/i2IEhgMuySmAF0IIFwI4deSbX8bh2h8wshDd5lgLmQgEE0IDY3+9eAWQnBQwQPkAvJJcjDSBUJAUQkz11daIi0PHjRNzpg0UFB5A9gAA1o9JBEUDFg1EJeAY3z/GUAuYV9CbQLLhVKA0sFUDlSQBRpQByAaUAUrCCKgOvMB5QUDiSTqeR9rKEhIKCF2hp8XY/hlcpYO3t5EMkqXQaQcvFx7oS9L4OTACdcgo9WwYXBw9q/gx5qAAqtAoYYFCZyKEHkB0TaABYtoz+PJpuxh7MK7oCqL5eFGNLp9VksGAoDyBLWBFAyaS4fxQKh5UCIOgKIP1t45cCKJEg4luhNEilxKKJoQIoSuzQEC84KQLINpQCSMEKRgqgREKNwQrBgisC6Ne//jWWLFmCqqoqVFVV4bTTTsNvfvMbr49NQcEdVq6kal9mS4+hEJmzrFzp7HO9SAEz8SdiAug46pC48R9zytVzChgTQJYKIDn9CzBMAWtuzq1eo0dlJe0HeK8Akj/TizLwRgRQRQWwNGOu/TzO0y7B+FgGXlYAVVSI1VeVBlYgjDyA1AJEFlYEkPy+QuEYzwRQsVLAAJUGVkqw+gcwUQBlCKCsAmhoKO8YrECQFR5GYAJILfpMThgRQIC9YgwKCsWCYwLo1ltvxWc+8xmsXr0av/vd73DffffhXe96Fz796U/b9gpSUPAVkQiVegdySSD++7bbcpmEZBJ46ing3nvpWUfCeKIAMvEnYgIIAHr3H6f9JBgpgExjXz0BZJACFotRNZ8NG+jxq1/RezNnim1ytR+vPYAAaTDkWZQXHkC6me55GfufF3CusQm0zwqgUEikgSkCqEDoCaB0Ws2oJBip9OQARRFA3oGbnRGJPplTwBQBFBzIXI6RAqi6jHbIEkCA8gGygWTSWlkFiHUlpQCanJA94tQYrBBUOC4Df8cdd+DOO+/Ehz/84ey2yy+/HIsXL8bXv/51fOELX/D0ABUUXGHNGir1fuONWsKlrY3IH30J+PZ2431vv532jcdFr16IAsjEdyiKJGrRj+OowzE0olm3n14BNDZGq0u1tQYfliGA0uXlCI2OZmch+hSwWEwQPJyqNDBAqVN6eFUFDLBIAbNYfUylBOFl1wMIED5Az+M8YEQqpVYkBRA/d3WpuXXB4PtPzmEcHs4vZZskMFLphcPEiY6Nqcmnl7DyABovCqApU2ho8IMAqq2l9C9FAJUOeRVA4QwBFJ4C1NTRwNXbC0ybVpwDHKeQpylKAaRgBHk6Go3SI5FQY7BCsOBYAdTZ2Ynzzz8/Z/v555+PTqemugoKfmLNGmDvXuDnP6e/KyvJQdmI/LnqqlxlzoEDtL29Xczmw2ExuruBhe8Qq4B6MFWzXzwuyIN588Skw3SFmRVACxbQ88AAEgnxGUYm0LxtYMBYVGGYAlagAsiJCbQsxrKbAgYIAuhVnI6h/oTYl4/dZwUQIIggpQAqENxgampEI1A+QFkYpYDJf+ebfDpNC53MmAgpYMyjenULpVKCAOKFBUUAlQ48JIZCxmNmVZga8TCqxKKW8gHKC3l+pBRACkbQT0eVEbRCEOGYAFq4cCF+97vf5Wy/7777cMIJJ3hyUAoKniESAT72MYrC43Fgyxbt+yaePADEtptuEjPZhobCSjlZ+BNljaCbT9T4Ex05Qs/l5fT1PHE3nVxniKz0iScCIBNoORgxEjDV14tJotHnGqaAFegB5KQMvFsCKBYDWsq7kEAZNrxpUJqjSAogebuCS8gMR3XGuFRVAsuiUAJITgu98Uax/brrjNNCJzMmQgqY18X05M+ZM4eeFQFUOrACqLzc2A5RQwDxaoUigPJCnqYYKasApQCa7NB7RPH0UhFACkGC4xSwb3zjG7jmmmvwzDPP4IILLkAoFMKzzz6Lv/zlL4bEkIJCyRGJAOefDzz6KPDss8IZGDD15MkinQb27SNPIKDwEvDsT3TVVTQrk4inLAF03ec1LAenf82YQf/S1ESZZKaTa04ByxBAGBzMBiP19caCnXCYPvfIEUpXam3Vvm+ZAlZkBZDh15l4AIVCwLmN2/CHw8144c16rATEslx5udhfHqELrF2sVwApDyCPIDMcVVWUY6IUQFnkI4Ds2CVxWuivfy22VVQYp4VOZthRAMXj9AhShmIyKbpKrwkgWe3Q1kbPigAqHXg4NSMpqkLUYSgFkDPIa01m0wRVBn5yQymAFMYDHEsZrrzySrz44otobm7GAw88gPb2djQ3N+Oll17CFVdc4ccxKigUDlbU6MyVzTx5ctDRQc+FEkCA8CeaNUuzubGKRodjJ5yt2c4G0DNn0nPeFWYmgBYtor8HBjQG0Gbg94wm7ZYpYF55AFlEqHL5TCcKIAA4r3knAOD57ZncFX0JeED7wwocpc1SwJQHUIGQZRdKAaRBOl24AkjGvn3idVBTmUoJKw+g2lohEg3auZNvF78IoKoqYSPT1eXNZys4h6wAMgITQENpRQA5Qb4S8IAqAz/ZoQgghfEAxwogADjzzDNx9913e30sCgr+YcUKen72Wa3Cw8KTRwPuyQupACZjzRrg8suBJ58ELrkESKfR+L4LgftygwZZAQRYEzVIpYCDB+m1RAD1dKcBhDT+uXqwt4fRpN0yBSzAHkAAcO6MPcAbwPO7p9Ol51kZL9MBuQSQ5oc6g0oB8wGplLjGrAAClAIog7ExISb0ggCSRZFBIzGCAKsgMBymYaK7m0h6u0NMMSDfLjyUeU0ATZkixhKlACod8iqAQBd+NF2OZF0jIoAigGzAYqqRBU8thodp7uJwjUxhnEOuAgaIMVitVykECY4VQBs3bsTmzZuzfz/44IN4//vfj3/913/FqEUAp6BQUixfTjOhzk5gzx6x3cKTBwBtnz1bsC9eKIAYkQjwzndmI4TG6HEAuQEXK4D0BJChAqirK7v0l164EAAQSibRfXhM879G4PesCCBNcOlSAVRMD6CODiBcHkEEYzjUPwVr1wIbNwIbsRQbI8uzwi6UlYkPLnCUVibQPkBuGxUVSgGkg0zuKALIf5h5AHV0UP/C/OQLL2T6m8wj29+UCHy7+HELycJKy0UKhaIgH1HBBBAAxGszki1FAOWFEwUQoNYoJiOUAkhhPMAxAfSpT30K27dvBwDs3r0b11xzDaqrq/H73/8eX/ziFz0/QAUFT1BVRSQQoE0DY08eIxNoxm23iejdKwWQjNmz6aPTNFs2I4D0KWCGk2uuADZ9uoas6jk0qvlfI1it2hqmgLlUALkpA89cUzhswtUZzHY7OkgEteLRryEJWga97DLgzE+dhTOxEWfu/T8sWiQFZR4ZQesVQEwEqRSwAqBnOJQCSAP59OgDE6eTz7ExbWasIoByYZQCxv3NmWcKAu0Tn6C/+aHpb0oA7tqqqz31vQegVQApAqj0MLHFy6IqLfKThqdkBn9FAOWFHQVQZaWYpygfoMkHRQApjAc4JoC2b9+OM844AwDw+9//Hm9729twzz334Fe/+hX+7//+z+vjU1DwDnIamIw1a4Czz87dv6KCvHrWrBETIy8VQIyMY2bjKJX7spsCZqgAYgJo1iwgEkEiMwL1HCYGpdAUMC8VQDkpYDYUQKZfZTDb7erKP+DG49Lv9SgiUgogH8BtIxwmwlEpgDSQCQk9Qep08tnZqeXDFQGUCyMVgOP+pgSQU3kVATSxkY+oiIyNoByZSmBVmYmBIoDywo4CKBRSPkCTGYoAUhgPcOwBlE6nkUqlAAB//vOfcdlllwEAZs+ejS7l+KcQZKxYAXz3u7kEUH8/8Oqr9PqXv6QlmxtvpJH+/PNpO0dBfhBArACKd2q+iuFKAZQxmE5WVSE6Ooruo8SguDGBlg1mvfQAykkBs+EBZEoA2VmWywefFEDjgQDq6BCBaSIB7NpVj02bxKVtbi5x+W/Z4TgUUgogHcwMoAEDxV0esHqltpYKrfX3Kx8LPewEgUGEIoAmD/IpgDAygioMYxQVigByALtTjSlTqP9UCqDJB30ZeEUAKQQRjgmgs846C9/+9rfxzne+E08//TTuvPNOAMCePXswgyUKCgpBxAUX0PObbwJHj4pSJQ89RDP6RYuAj32MAszf/hZ46SWgvR347GfFxMiPFLCMAmjq8bcAeKgAApCorERFX1/GBNqdAkgW5nhRBawQE2hTrilABNB4UwBx6oqYnJQBWKXZp7IS2LathCSQPudGKYA0sCKAnE4+uQLY4sXkYQNQ92dFHk82mHkABR3FJoAGBqhrLqRbVnCHvENihgDqQwOGKzPzGpWnnBd2yV+lAJq8yN57b2wCDr+Jyv53AJiuCCCFQMFxCthtt92GjRs34vrrr8dXvvIVLMwYzd5///04n9USCgpBxNSpFNUAwHPPie2/+x09X321yJ/4wAfo+f776bkYCqDePZqvYuhNoJ0ogBKZCKW7J6T5XyOYmUDLAYIm4MkryzFGIWXgg64AGhsT/z5ePIDGQ+pKDsOhFEAaGFbpy8ApAcQKoHnzRBCj0sC0sCoDH2T4SQDJJtD19ZStCSgVUKlgVwEEAMPlmUFKKYDywu5Ug/tOpQCafBjtJdav/IZPAddei8qnHwUAxF/ebPVvCgpFhWMC6LTTTsPmzZvR19eHf//3f89u/973voe77rrL04NTUPAceh+gvj7gUeqccfXVYr8rr6Tnp58GjhzxVwHEBNBRMleXlT3Dw0I5wilgThRAyUz019Mb0fyvEcxMoDlACId1k0lmZbwsA29ixm3JNaXTNma7NuBBRCSrfMZTCljgoZdcKAWQBl4qgJgAamsTfLcigLRQKWC5kBVA4XCehQoF32FXAQQAQ9HMIKUIoLywe+9zKXilAJpkaG/HyBFa7SsH3YR8n8V//TvKKlBQCAAcE0CM9evX4ze/+Q3uvvturF+/HpWVlSgrJPhSUCgGVq6kZyaAHnqIZkonnyzUQQAtf591FpBKAX/4Q3FMoA+/CYBWjJjPYPVPRYUgEnhi3dNDh6eBiQKopz+q+V8jmKWAyf4/GoNZlwogUw8gQPxwHSxTwJiI0n+WU3hIAFVVCS5KEUAeQCmALGGHALIQ2GnAKWCzZwu+W8WFWozXFDC+XfwmgADlA1Rq5F0TiceFAqislrapGz0vlAJIwRTJJHDjjRgFNQ4mgCpBA3QclcBNN4kJrYJCCeHYA2j//v34u7/7Ozz33HNoyATDvb29OP/883HvvfdidkbNoKAQSLACaMMGmrFy+tcHPpBbPucDHwDWrwd+/3t/U8BaWoBwGA1Jwbz09pJFkWwAzYfHE+tUigRMGlGSngDKzPK7B8o1/2sEfu/4ca1vg2EFMMC1AignBUxeSjMxjLBMAZO9g0pMAOn9f+TXx4/TNQu7pt0nMZQHkCX8UgBx36IUQFooBVAuFAEULNhRAFWDGMHhiGRYMzZWmJJ2gkMpgBRMsW4dsH+/BQFUQSss69YBq1aV6igVFAC4UAB9/OMfx9jYGLZu3Yqenh709PRg69atSKfT+Pu//3s/jlFBwTvEYhTZJBLA448Djz1G2+X0L8ZVV9Hzk0/6mwIWjQItLYgiidoptDLAAZfeABqgiQdPLjRpYMPD4h+lFLAxRHE8TgOSlQKoocHYt8GwAhhQsAIoxwMIMJUpWH6VCQHU3Jx/hb6yUiifvFQAyQQQK4AAIoEUXEApgCyhCKDiwsgDyHF/UwJw11ZdXTwCSBWHLQ0ceQChWmwPqlldQKAUQAqm6KRKvkwAVYDms0wADaNKs5+CQinhmABat24d7rzzTixatCi7bdGiRbjjjjuwbt06Tw9OQcFzhEKitPv11xunfzHmzweWLSPZBnvTvPaaP/JN9gGqogGDAy69ATTD0F+B1T9VVVmlUqKyEj2gnUMhawGT7NsgT9pNDWYL9ADKcj2RiGCeTCqB2SaApGOJxahy1YZvP4INWIabZ98HALi4eSM2YBk2fO0BbWUrPjAPFEAy6VNRISaLKg3MJfQMh1IAaeAVAZRIiLmpnAKmCCAtjFQA2f5mA/Dzn9O22bPpb36UtJIeimcCDZh7yikUB048gIZHI+LCqTQwSzhVACkCaBKhpQVpwDoFLLNfqdDRAWzcaP7o6CjZoSkUGY5TwGKxGMYMfDoSiQRmZVQHCgqBRXs7KX8A4OBBej5wgLavWZO7/8knU6/IuPRSWhq//Xbj/d2CfYAqBtGB6hwFEBtAM5qaSEmqUQDJ6V+ZfDGZAGpoyC/WaW4m8keetJumgHmlAAJoNjU8bKoAsuSa5KVOXRpfLAbEThoCsAk7qt4AAIyMRbAMm4DFI4AcjPmUAgYQIdTVpQgg19CbrigFkAZeEUCdncR3R6PA9OnjhwDq6LBWmjQ3e0u8mHkAxWL04H5qdJTWEIIClQI2ecDDoi0CaBg0QRgYUARQHjCxpsrAK+Rg5UokZ81B+gAtaBoSQLNnCy/SIqOjA1i0yHouUFlZ+oUKheLAMQH03e9+F5///Ofxox/9CGeeeSZCoRDWr1+PG2+8Ed///vf9OEYFBW/Q3k5pXfpKU8eP0/b779eSOu3twD335H7OgQPG+xcCVgCF+wBMK0wBJBGxiaqqLAFklf7FMJLtm6aAeeUBBNAsdXi4MAWQ2Uw3E6W1hIhN64xnolqOVBgepoDJCiCACKGgEkCcupJvUlDK1BXlAWQNKwLI8H4zAad/zZpForxSEUBOCJ1STGrzlYEPqvG7IoAmD3hYNEoB6+gAug7OxGAm9WvnTmBjxXkAdgIvJ9E8XQWAZmDyN18KmFIATUJEIhj93u3AtfSnIQF0222OF029QldX/nlAPE77qft/4sNW5NbY2IiQtLI+ODiIc845B9FM4JdIJBCNRvHxj38c73//+305UAWFgpBx5zcsM55Ok3LkppuAyy+nztnp/oWCFUApkvToCSAjBRBgoQDKIFlZiW7QznYIICPZvmkKmNcKIMAfAijz2S1pUnwdHM38SF6iY/isAJLfDxI4daWri5o8F8j75jcTeM97qI/3WkHhGMoDyBJeKYDkCmBAaQggp4ROKSa1+dJA+H4fHg6Wp64igCYPzBRA4v76dnbbD38I/BCZghifVSoAKygFkIIVRt51efZ1DgG07AJgzUzD/1NQKDZsEUC33Xabz4ehoOAzMu78pkinte78TvcvFKwAGjsCwNoEGnCgAJJSwKwqgDGMSsEbpoCl06IGfaEeQICYpeYxgTb8KrsEUIrOz2C6GsdRg9oiKoCCqghgcOqKfPorK0PBSV9RHkCW8IoAkg2ggdIQQONhldIuAQTQPW+n7y0GjAigRIIeDrvxHCgCKFgwUwCNh/sryFAKIAUraCwpQSr5yk9/DPgJEG9Q5I9CcGBryP/IRz7i93EoKPgLu677vJ/T/QsFE0DDpFLJlwLmTAFEM31PU8BkI2yHCiDDlJQ8CiDLMvD5zA4yn10z2oPaWsr460QLakugAOrvTQFPPUPtpqWFcsFLJAc2wpEj4nWgClUoDyBL+EUAsWl80D2Aig0zDyBGNEoc5dBQsAggvl1kAgigLq+2trDP1ptAKwKotMjrAaTgCkoBpGCF7HpkWQqhzD1YeSLN7+1W4lRQKAYKWvMZHh7OMYSu0y99KygEAXZd93k/p/sXikzENXWQLPgNTaCTSVIcdXZi6rHlABbaVADRUpQTBVDeFDBmZADXCqAcDyCgsDLwZnkWPFMbGUFLiyCATiyyBxAA9H3xP4C+fxNv+GEo7hLptJ4ACpnvXGwoBZAlTH26YKK4M4FZCpjyhdUinwcQQH0AE0BBgdyXy+SVFwSQUgAFC/mGRQV3UAogBStkCcLyNJAJj6sitFERQApBguMy8IODg7j++usxffp01NTUoLGxUfNQUAgkVq6kYDtkEtSGQlp3fqf7F4qWFiASQWOKZss9PTSh5snDjBf/CMydC1x0EXDttWi6k/L3u7ccFp+RJwXMrQLIMAWsAAWQHJBmLZaK4AGEkRG0zKQv7ERLcT2AunYBAPr7Uto32FC8vd31d3qFwUHtTw+UAkgfcSsFkAamlfow/lLAxgPslILOkr4B8v3idlJdTSbf3Da84FHNCKCeHpEtrFA85C0Dr+AKSgGkYIXsfRcVnV5lmJggRQApBAmOCaAvfvGL+Otf/4of//jHqKiowC9+8Qt84xvfQGtrK37961/7cYwKCoUjEiGlBZBL6vDfsju/0/29OL6WFjSCIq1jx0T6V1V5ArX/7/0aT6KpoNyvnlfeIvIglRJl7eUUsKqqgk2g86aAuawClkpJQqI8CiDLgmNOCKBpNBAfRGvxqoAlk6h77hF6HzppEDNgN92kPaclwNGj2r+VAmj8wG8PoN5eFcTLyJcCBgTT90uv5vTKCDqVEp+hJ4BSqWCRYJMFLM5XCiBvYVcBxASQUgBNLhgTQLRRTVcUggTHBNBDDz2EH//4x7jqqqsQjUaxcuVKfPWrX8V//ud/4re//a0fx6ig4A3WrKHS7RJBAoCiHaOS7k73LxSzZxsSQDOSBxGCthpZE4ih6UYTkQeHDhFLEgpp0tJ8M4GWU8BcKoAAKSgtlgJoKu3bGZqVu79fCqB161B3nNRZOQQQoDUULyE4/SsUyqikgqQAsvIAMqrUN8ngBQGUSAgOWZ8Clk4Hi8goNewogCYTASQL8ZgAKi8XQbBKAys+lALIH9hVAPF9oBRAkwtZgjAiEUAh2lhqBVBzs/WiBUDvcxygMLHh2AOop6cH8+bNA0B+Pz0ZF9oVK1bgM5/5jLdHp6DgNdasodLtGS+dvEa8TvcvBG1taMReALkEkB5MAPVgKpEHDz9Mb0yfrlnySzgsA2+VAua1CTRAA2JtLQrzAMq31MkjXiqFlrpBADXojBqk93moANIQQJ2dqAcxQ32oz/0nab9SggmgE04Atm8Hjh8PYXAwVyhVEpgpgABqM/lmNRMcXhBAhw6RWiMapW4EoHu1qopuiWPHhCl0kMCT2nxl472a1KbT9jyAgpwC5jUBxCqHUEg7TjQ10Xvd3cDChYV9h4IzKAWQPxiPCqCODu2cTo/mZlXxzSsIBZCYI2fLwJeYAIrFgG3bqC18+tPAyy/T9oceAlpb6bVqC5MHjgmg+fPnY+/evZgzZw5OOeUU/O53v8PZZ5+Nhx56CA1BnB0qKOgRiTgr3e50f7eYPRuN2ASAgq2sATQO5ezKKWC9aEQCEUS3b6c3dGoljQKoPoF8tzwHSf39NIEsKzNJAWMFUDhs7pNkgkiEPndsTOJ7eDaVRwFUUAoYgNaqYwBmoDM8K3c/DxVAmhSwlhbUgZghQwWQtF8pwQTQggVpvPVWEiMjUXR2BiRwM/MAAkh+oAggAManwbDqngHYALq1VUu0NjYKAiiz9uMrnBI68qT2mmuAnTvpNzz0kPYzvZrUynUvlAKIwCoH9hZiNDUBb71lHXwq+AOzYbHYhOlEg1MF0NAQEethx/kW3qCjA1i0KP/13rZNBf5eIHvfRSQCKBwcE+hYjB6yiL+lBVi2rHTHpFAaOO6SPvaxj+HVV18FAPzLv/xL1gvoC1/4Av75n//Z8wNUUJg0aGvLpoANDAg/jhk4nLMrE0AA0IsGYdChI4CSVVXCBLoq/yy/oUHwOSzbtzSBduj/w8gJSgspA++AAGopo0ikMz0zd78Co6F02iQFbOVK1DXRsRkSQF4birsEE0DTpwNTp9KFOZgrPisN9AxHWZloeyqx3hMFEPc3nP7FKLYRNBM6GzYAX/qS2P7xj9O2DRtyg5VYjCaw3BUMD9Pf/PAysJFFisoDiKA3gGYYecopFAdmCqDs/dXwDmzAMtz8ETJ/e9uy49iAZdgw/d2KDLCAUwVQOl3aIaqrK3/fH48rktYrZAlCEwVQUDLW5fG8p8d8P4WJC8fR2xe+8IXs64suughvvvkm1q9fjwULFuD000/39OAUFCYVZs9GA3qzf27bRs8za4eAgZBm5IgiiTr0oR/16J55Kpp5Jq8jgEbSZRgA1fedWnYcgHWt30iEUsW6u+kxc2aeMvAuU+EqK4nkyk5MvCgDbzYji0Zp+S2VQkuI1FQHkzNy9yswGhoeFsepUQBFIqi74aPAvxsQQH4YirsEm0A3N6fR2BhHZ2dNqbPSBIwYjqoq4PhxVQkM9gig0VHrlWi9ATSjFJXAeJXy/vvFturq/KuUTMD29fm36i4HU+MtBYxvFT0BVOgtZEYAqVLwpYPVsBiLAbHkywCO4/jFI7j1LmDPoUoswyZgqAZQ5I8p7Ph/Adr50sBAQFKpFXxH9r4LSwRQmuaU6TQRs0Hw5ZLHc9U/T064W76XEIvFEFNLBQoKhaOtDVEkURs6juPpWrz5Jm2e8cGLgJ/nLhs0oRv9qEfPDV8HdmQq8OkIoIFBmqWEkEJD5Litw2hupgGBV4Qsq4C5VADJpeABFGYCzUudVqNqRQUwPIyWNEla+pK1GB7W/qaOY7XowlJgYAqwMfcj8qWRcKAXCuVWmK9/74XAvwN94UZArqbU1kbkj9eG4i5gqgBKJovjgWUFo7JL1dVEACkFkC0CCKDTqLmPJXAKmJ4A4szuUpSClwof5iVSZKPqVIqCrjoDwV2h4KbIvLIZlAJIEUClRF4PoExDPv0MWoToOFiGHjRi6sAxWuBxObZPdNg11w6H6X4YHFRG0JMJIgVM5FixAgigsbrUBFAyqR1PlQJockL18AoKQUEm96Ix3YPjqAXb+sy49Axg+Drg7rs1u08NHcOeNNC9ZBXw1C20UU8ADdBI04hjCA/bm4XojaAtq4C5JAJyUsC8KANv5XaZIYDqBw+iEsOIowqdncD8+fR2Rwew6NK5iGMjMATgzNyPyJcnL5eA19siZYPByun0+QBwww3ArbeWXPnDYAJo2rQ0GhvpOnQ+vR249R3aSLytDbj99uKSVkauuybyhaAYXhbzOOwSQPG4OQGULwWst7egQ3SFAwfE63wE0MCAVl7f2+svAZRPARA0AiiZFKQAe6h7bQKtJ74VAVQ6WBIVqVR2h4bp5Zg3D9izB3gFZ+DteJJuNjtlQych7N7/gCCAgmAErVAcCAWQIIAq0loCyI9xyQn0Y6nqnycnFAGkoBAUzJwJRCJoTB5DB+ZkB5KZMyGW3z/7WeCMM4Drr0fTKEWX3d0QkZKOAOrvJ1JkKnpsz0L0vg2WVcAKVAAVpQy89PmhYz1oxUHsxgINAdTVBcRHrM2sOU/eLGg39P/JgAf8gaEIkggjglT2egcFhgqgB18CsF+744EDwFVXUX5OsUggI4aDo1gpeg2K4WWxj8OKAJIyIM34VQDBSgFjOCGA9O/7lXplJEYzAt/zQUkBk0kepQCa+LAUxsrjbEUFli4lAmhT+Tl4++iTxJ4qAsgQdhVAABGiR44oBdBkQtYjKiQIoNDYaNZ4PQhG0HrFj1IATU4oAkhBISiIRIDWVkzdp+2NZzQngWefpT8+9jHgrLOAF1/E1F/Sfj09MCWAWAHUhG7bBJBeAWRZBawADyD5s331AAIEwdTdjRZ0ZgkgLyErgPSQtx1HLRrQFxxpQAbsATRtWhqN9aSq6YRBZbJ0miRON90EXH55cUgsMw8gQKMAcmJ46ScB5PQ4ClULGd6jGYRCdNqGhqyPySwFrFQEUDrtLAVMfzv5pViyUwIeEERwUG5zmeTh20gRQBMXlsJYeZytqMAZZwDt7cCmyHLaVgq53ziBUwUQoBRAkwlGCiCMBosA0o/lqn+enFAEkIJCkDB7Nhr3aXvnmT1bKPqpqSH1DwB87nNo+uVzAIDuncfEhE0XvR0/TqSIFwogwypgBRJATj2AXJWBl7+wpwctIObH6wpXVgqgigp6jIyQEXQD+si/JiBIp+UUMGDu8W0AluMgWs3/Yd8+8gZatcr/AzTzAALGvQeQF2ohKwUQb7cigBIJZAnRUlcBY/T3a1fO8xEpeoLIrxh2vKaA8W1SUSG8ixQBNHFhqQCSCaDycixdSi9fSS2hF4oAMoVTBRCgFECTCdn2ERoTG8fGsmNzEKYr+rE86AqgoKT1TzS4IoBSqRR27tyJI0eOIMXlpzO48MILPTkwBYVJCakUPEAxbs36p+iP888XDMjSpZja9gqwH+j54zraVlmZMwMfGKDlP1IAjcEOHCmAvCoDb9MDyNIEOp8HEJBVAAHwTgGUMUnuf7wSwLmoq00DyE0nq6sjlU22ElhQIkPQfJ/P8bRpQGuKFGWGCiAZxSoT5sADaLzBC9WSIUkrIV8p+MOHqRlHIsAMXYG8UhFAcvoX4DwFzG8CaLymgMn9uNcEkPIACg5sKYDKy4FQKEsAvTkyD8OoRJUigEwx3hRAzc3Iqk/MEI3SUL5RV/xCBdbOkS0DHx7VbMw3BhcT44kACkpa/0SE4+jthRdewLXXXou33noL6bS2MlEoFEKSl+oVFBScY/ZsDQE0YwZIZQEAOnK1aUEDsB/o3p+ZvcfjwLx5GoNerQLI2uOG4cgDyOsUMJ89gDwngNrbgRtvBPbvRx9uBHAu6p/+I9CezPHHySGAAqQAYvVPfT2dqto2kgj0oQFDqEI1TCLEljwEkVew6QE0GSH5uZqSEjmEqw6c/tXamnuPlYoA4vSvhgYic/r6RPahEYrtATReU8D8IIA4wFUKoODAlgIo02G0thLxf/RoFJuxBGcrAsgU400BFItRcNzVRcd+3nm0/b77gL/7Oxo/Egngssty/1cF1s6RbR8Y02wMIgE0dSqRP0Hun4OS1j8RYVHE1Bif/vSncdZZZ+H1119HT08Pjh07ln30BJlGVFAYD9ApgGbOTAPPPEN/yARQezuanm4HAPRgqtjOBr3t9F4hKWC2qoAVuQy86xQwPwig9nY615lIlYmd+uFDmmvA4ICwD5kXASSApk+n5/jSBagK0YU3VAGFQpQrtHJlcQ7QpgfQZIQsmnOrADKrAAaUXgF0yin0nEhYExVB8wBiBdDIiLX5drFQDAWQGQE0PDzpb9Oiw5YCiIsjhER2+Ss4Q6WAWWC8KYAACoyXLQMWLhTb5s4l8scKHFgr2IdIAQuuAohDdW4PKnSfnHAcve3YsQP3338/Fso9iYKCgjeYPRuN2Jb9c8aUQcrPKC8HlmcMGpNJ4MYbMRWUr98NqVqHbNC7erUuBcxe7UlbKWAFKoA8TQFzQgCNjKAVZP5TEAGUuQZy3WkmduqQkR7oTJKzniABTAETBtD0HIpG0Do9gV2HgYOYhQXYLXZmCcZtt+W9/p7kbqdSYjlbKYByIE8oCyWA9AbQQOkJoEWLgBdeoGbQ1ycuux5B8wCqrRWv+/vFvVUqMAFTTAKotpZI+0SCVpnNrp2C97AcFg1YzKVLgSeeADZhKdDrsUHeBAGrZQB7BFAQFEAyeMpRXe167U4hD7LZlZAIIMkDKAgEEI/lCxcCL71EBFAqJbzhFCYHHHcB55xzDnbu3KkIIAUFP6BXAI1lcjPOOUdEcevWAfv3oylj0KtRAAFZg97Qs8/i+PHTAbACyF7vLqeAJZMi9vbSA8jTMvCWWnfd5wOGCiA7efKVleLc8DWQkVUAoc/QJDmHAAqwAggAZi6cgl2Hgc6pi4GedeKNtjYif/KUgPcsd9tM4qIUQADE+Q2HzW/HfJNPswpgAKVgAUSoWKVgeQ2ZlKqrE2lgZlmHQfMAikQoABwYCAYBVAoFUChEfeahQzSeGCnMSoWJbixqaY1nwGKyD9AmLAX6tnp6LBPlXMvTEycpYKVWADGsKpUqeIPxlAK2YAE9p1LUNnisV5gccBy9ff7zn8c//uM/4tChQ1iyZAnKdKPLaaed5tnBKShMJnR0AF2989ElKXpSBw9hI5YCJ1yD5o7MJCnDXEwF6TY1CiAZnZ04fny52HcgT8SSASuAenu1HIUfVcA8LQNvxwQaggDinPjycilP/l3X4ftb34178SF88IPAI49QYPmznwGXXipNUg3kQ0IBJCl7pP3GGwHEgfbBr/wIuONRYO9e4IILgKeftnXdPcvdlj9EXnY1UAA5JvJ8gpPjKFRiL2fHmZEzXqSAJZPUZIsVPLACSCaArERz/F59Pd2zfnkA2U0BA+i4mQAqNfg2kVU4fptAAzSeMAEUFEwGY1FLBZABAcQpYK/hNCR77oS7kT0XE+lcywSQkxSwoCmAFAHkH7L3XXpEszGIBNCMGdRGBwepf1YE0OSCYwLoyiuvBAB8/OMfz24LhUJIp9PKBFpBwSXEJGkagB9lt/9sx0X4GTYC/w1U3pOZJGUi8ybQjHoAtRhFmXbFAQBaWlylgDU2UiCZTmtLpU8IDyDQuSiLpjCWCOPQITHpjMWAWHMHjoJYkHe+k47zV78CtmwBPvlJ6fMMZAhMANWjz3C/HA+gIESFGRgTQJTe1nk4LJiFmhrXpJ9rmElcDBRATOQdPQqsWCH+9T//kwg8oDirzXwc//APwGOPASecAOzYQZLr++7THoeXBJAZcu43HaxSwKqq6NYaHSUSptgE0KxZ0r1jQerwe7EYsHlz6VPAADpXBw8GoxJYKUyggWAaQU8GY1GnCqATTgCqy8cwNFqN7Qem4GSPjmMinWu5/7Rab2IETQHEa06KAPIP2Spg0BJA3NcGiQCaOpX658FBSgNjRZDC5IDjjL89e/bkPHbv3p19VlBQcA4nkySsXAm0taEe/QiBXPw0aWAZg970ihWuTKCjUbHqz6khZWW6uH+8eQBJ0XEIwMwmmh3nCHkqK/EGFgMAFi8mCx8AeOABjd1P9hrIkgtW9tSh39AkOUcBNDCg+9DSgQkgOU0lqwA6CLGEWQq/HTnnRpa4mHgAxWJ06uX7qaqKTDCXLStekNHWBmzYQK+//nV63ruX2pV8HKwWsoKVaskJAeQmBSwUKo0PEJNSbgggoPQpYECwKoGVIgUMCCYBNBlgSwEkNeJIBDh9LjXUTZ0zfT668QlZbGzHLyWoCiDZn0zBWxgqgALmAcSmz42NRAIBqn+ejHBMAM2ZM8fyoaCg4DMiEeD22xEJpbJ+Qdk0MMmgNz4WwcgIKSZIAWR/GYon7RyEafx/gGB5ADlUAAFA6wz6QD0BdCzSjM6Mt9IppwCXXEK/fe9e4LXXpB0z10CGUABlZlk6k+QcAiidDszMkE2gNR5AMzMKoE6ItlMKvx0zhsPCA0i/FlFwxTcXeOUVImxraqgoXGMj3TZbtmj3Y7XQiy9qm/C8eUQgbdhgnR5RKAGUTAqlnxEBBBSfABoZEW2yrc0eAcTBDU9DgqIAAhQBBKgAo5hIp8UQbVcBBABLF1Ffuqk74FKcEiFr8GvD/wcIngJIpYD5D0EAxTUbeQwOQs0KHsdlAiiolcAKXSBTMIdrH/gtW7ago6MDo7qA7X3ve1/BB6WgoJAHa9YA99+Pqdf0oyfRJBRAkkFvz1ukcgmH06hL9TuahTQ3U8qKKQHkkQdQVvBj0wPIkG+y1LpnoJvotsxMA6/lEgNbRsncvq3hOOrqaJnskkuABx+kx+mnSztnrgE+8hFgYEAogGZUAT++P8ckOYcAAmhGZmScUWQYpYC1Eg+GgwfTgmQpxezFzHTFogrYrl3avw8d8uG48uDxx+n57W+n5n3GGcCTTxIxxIarjFiMyA15OD16lPbLZ7rshgCSTVmPHqX7Kxym++HIkdw0uWITQHxfVlQQgeBEAeQ3AeTUAwiY+ClgigAKFsakbHC7VcAA4IwlSeAhYNNxD4u8JJOAHUchu/uVENn0Hhv3PhCcMvAMmQAKil/eREOWAEoF3wOosTH4/XPWn7ML+N3vgO98h7Z/6EPAzTfT6/FiIh80OCaAdu/ejSuuuAKbN2/Oev8A5AMEQHkAKSgUC2vWoGlZGjtfArq/8B/A+1KUcpQhZbIyz5oEwv3pghRAOcGlJSNjDg48mXA4eBDYuBHAW00AlqJ5YCqM+nHPysBn0DIrnP1+GW8MzwcALJ52FAARQJdfTuTPAw8A//Zvus9ds4be+M1vhALo6T8Ci3IPNMcDCAiMEbRhFTBZAcQoJQHkQgHEE9xSEkAXX0zPTAC9+qrx/hs30vNZZwHr19Pt2tsryBcz8OnJIWklyCmXZqasqRRw9tn0Wm/KWmwCiPud1lYiwNykgPX1+VO1zIkCaLKlgJmZQAPBDTAmImQCyJEC6EwaF18ZPdm7e2fTJgBn2dtvuY39Sgi3CqCACH01BJAcWAPkcbhxI3DLLbToBajA2g2ybURWAAUoBSyRENPO8aAAAjL+nDHgT3/Sbl+2rDTHM1HgOAXsxhtvxLx583D48GFUV1fjjTfewDPPPIOzzjoLTz31lA+HqKCgYIamZpqh9Zx6IZUblxiSY8fovakNGfbEwSyEV33YG8Q0BcyBAogDzzPPBG69lbY9/jj9feanl+NMbMSinQ+joyP3f71OAWtpI+JKrwB6Y4DkA4ubBGNw2WWkjti0CXjrLYPP7utDEmEMZAijukbjc2KoAAoAAZRIiODMSAHU2xvCMDKzlyClgFkogJgAWk5F8IpOAA0OAs8+S695Ms3qsVdeMf4f9gtasUJ4MRndC3o4VQA58hvLoNgEkFwBDLCXSqVXAI2N+cNXOvEAClIKGN+6ygR64iNvuXITAujU5VWIIIHudBP27014czB2Xe4LdcMvAsa7AkhvAh2LCW88rgDZ2Fh8v7yJhOx0NGmcAlZqAkhWxo4HBZAM+Rh50VLBPRwTQM8//zy++c1vYtq0aQiHwwiHw1ixYgVuueUW3HDDDX4co4KCggmsDNx429TGjNGwwxQwwEYKmAMFkK3AM11pOA/0lAAKh9Ey24QA6psFAFjcsD+7bdo0CsoBUgLl4NgxHIdwVayvN9gHFilgJUZ3t1BK8GQAoN/Bk5ZOZByhHUSKnuVum0XcNhRA559Pz8UmgJ55hgiIOXOoug4gyiy/8oqx9zcrgM48U0y8swRQMgk89RRw7730LClt+ZIUYgKdD6UigGbR7ejIA6i1VRi0+pEG5sYDaCKngCWT4pwoAigYkBVAhkO0SSOunFGPk7EVALDpbx6xp3ZziMZBrtFEUQAZmUBzCfAg9FXjGSIFLJgEECt9amupbxgPCiCGPIYcPly645gocJwClkwmUZPp1Zqbm3Hw4EEsWrQIc+bMwbZt2zw/QAWFSQGXefI8uTbqvDlYa2rK6Li56pQNXXfeFDAXCqBCYOk5zbNduwTQlClonUXnIIcA6iaiY3GNkF50dFBQ/swzwN13CzKI0XykEsiQOuVlKVRUGPPq2WAQ9fRDZC1uCcFmu01NdDlTVFgOoRAF07t3AwfRivnY4yhSZIn5v/0bcNdd5IXz/PP0Ee3tRI7Ykpi78ABiAuiCC8RvTCRce5Y7Bqd/XXKJuN1OPpnSMfr6qE3JNROSyUymBMTK64YNGQKovR248UZxMwIkjbn9dmDNGk+qgOUDBwfFTgGzSwCNjIjgrL6ejrenhwggVrJ5BSceQEFMAePbRn49MkL3vZ3KRnrIwa0fBJDsV2UEN2kqE93/RK5WZTjcG5DqdJ7LEQvvx+upJVi7NoU2qRa823Sg5ouXohJxxGHeQVUijuaLl5q+HxSMdwWQlQk09/F+eadNFmTbSHJIszEoBJDs/wOML4JeHgeUAqhwOJ4On3rqqXjttdcwf/58nHPOOfjud7+L8vJy/OxnP8P8+fP9OEYFhQmP5t0voRJnIA5zI49KDKN59yvA8vOy26wVQDTza2zOzOpTKRp9rMxC+HgyE18OuLxQABUCWwoguybQNTXZEucyAdTTAxwapKWxU6r2AMj1S3n5ZSKDZFTij3gQ7wUA1E9JADAmorLBIOqAGTNI5hCAyNDI/4fR0kJkSlYBNDpKF8Mm8Td7NrBuHb3+h3+g8711K01AbedvO/QAiseFgmT5cjrUZJJ+p9dkgBlkAohRXk4l4F95hR4yAbR9O/2M6mpqb1kF0J+3AQ9elSsZOnCASovdfz/icTIbn4gKIE4By0cAydtrawUB5Mdq9kSsAgZQ25DJIbtgAigUMm6DhQQYZn5VMvR+VXYg+590dlKaLwBccQXw1a/S6/Hsf5J3TUTXiLXn+d0AgJ/eU4+f3iP+xc15BoDYvAi2/eRxdH36q/gBbsY9+BAA4Fv4ClbjEQAhNP/k24jNe7fl58hEYCIB7NpVj02bxBSkGNerEAWQH35kTqEIIP8hUsCkhakAeQDpCaDxqgA6etT9ooUCwXH09tWvfhWDmRH/29/+Ni677DKsXLkSTU1NuO+++zw/QAWFyYBYai+24Rp0wXzJsRldiKW+A0AQQFYKIN42dZoUrA8M2CKA5FQgwBsPoELgaQrYlClZAujwYaEM4fLcMbyF2mQvAJtpa6jEflCkWl89BjMCiCddg6hBckYrIgcOBEIBZEUAZSuBQWJOhodtVy7btIkIpMpK4D3vAf77v4kAYm8pW3DoAbR3L022a2qIZ5s+nYK8Q4eKQwDt309tKRwm1ZOM008XBNDll4vt7P9zxhnUxrME0GNvGueLcTRx002I3/B+AOGiEEDFCg6cpoDJqQ2RiNjfzxQwJx5AQUiryEcADQ8XRgDV1BgHuDyWHDvmXIXnxK/KMTGRMRZ97TWxLRqdGMaieddEdDI2P88zAMQ+9W7Epg0D16aAzP1TiwEsi24G/vd/gSvzkz9aIrAMwCrNPm4JKidwqwBysPbmK/QeQDIUAeQNgp4CZqYAGm8EUDJJf7NfooJzOCaALr300uzr+fPnY8uWLejp6UFjY2O2EpiCgoJDtLQghn2IIU9kzMxFBlYKoKwJdHOIZvZDQ0QA2egx9dJ3r6qAuYXl19khgOQfUFODadMoQE+lhDLkjTfo7VOwxbEpxgCIEKmrGAFgkAcBoLZapO8db56HBrwcKALIqFlklVKQ2p0DAuj3v6fn1avpX9ho0hEB5NADiNO/FiyggHTmTEEAFQNPPEHPy5eL+5NxxhmUDqc3gpb9fwCJABq2yEFJp4F9+xB/cy+A+bYIID6VTlGqKmB2CSDezoGNn8HMeE8Bk4PQSIRIgkIMs60MoAHtPXDsWPAm7PK1mSjBr1MFUFGwZg0OLzoKZAi37sgMYgRt5Nn5TVDZhVMFkHxPDA6WngCy8gDykzSfTMi2kYQ2BYyvfVAIIO6XrWKIoEF/jEeOBG88GU9wHb3t3LkTu3btwoUXXoipU6dmy8ErKCi4wMqVlO9w4IDxin8oRO+vXKnZrJfXyzLpXbvoeXAQ2FhxHjDUg+YdI4jNy384JVUApVLQ+9N7Wga+pgaRCKlDOjvpIRNAi/GG42hoMEP61FeYj+4VySFUoAwjqERfwxw0AIGIDNkDyLYCyGYlsHRaEEAf+AA9uyKA7HgASfp6JoA4I3nmTHr2iwDSe5T87//S85IlROzIqQlsBK0vBc8KIFYfZAkg5I9m4j10PSZKClgqBRw8SK/tVgFjAoiDGD8JoImUAsZ/F0IAsQLIjACKRul69PYGc8VWJhWDoNTyAnkVQKUggAAcPibG6K5F5wNbAPz0p8Db3lbU43ALpwqgSITur+FhIkqZ6/LD18oOVAqY/8hORxPB9ABipY9eAdTb6yi7v+hIJET/PG0azVsPH6a0egV3cEwAdXd34+qrr8aTTz6JUCiEHTt2YP78+fjEJz6BhoYG/OAHP/DjOBUUJjYiETJ1veoqCmRlEoiVdbfdltM7y/m7uTJpIlG+//0Ivo8/AwAq35vCth35Jxf6RbmiegCNjQHQzrAsU8B4udOuB1AmUmlpEQQQUBgBlFUAlVn839AQ6gEcQSX6azPShgApgMw8gAADBZANvPIKkZCVlcJjoyACyEwBxPtk/jYjgPSG317AyqPkF7+gh5yawKXg9+yhCVdDAxEebACtVwAdRCvGEEUZzEsyx8tpNm+XAHJjgFtMAqiri27pUEi0P7spYHoCyE8PoImQAsZ/9/f7QwBxoFtTQ+39b3/T8sdmFROLCfnaTJTgN++aSIkIoCN94oC6Z51GBND//R81knHguO1UAQTQfTE8LO4Tv3yt7EARQP7DkACSPIAKqbjoBfQpYPycTtO11y/+BgVMXIVCwEknCQJIwT0c2yd94QtfQFlZGTo6OlAtJYxfc801ePTRRz09OAWFSYU1a4D77xd5D4y2Ntq+Zk3Ov8gKIFsy6dGw5coTQ5+64kUVMFtlwTGM5rrRnO2eegBl0pdY3cLEAHsAuSOASFNdH7Wo9zo4iDrQDKy/LHPhAk4AmXoA2QCrf979bpEx5hsBJB2TngBiEsEPBZCT1ASAJls8qWfvkZ07qRlUVlKlMICuRXl5GilEcBCzcj8UoJnQ7NmITyOZjF0CiA1wN2wAvv512r58Of3ND33wIRNAfot9Of1rxgzB6TJREI+L213GeFAAlVokzcSLEQEEeE8AcaB75pnimv7939Pf/Dj11CiOHi1tXsxEJIDyrok4YTE9QjIJdB0XN01Xcio1gtFRyosdB3DDm/HYx6mSTscMr5BOKw+gYiDoCiA9AVRWJlICg+wDxPdDQ4OYl6pKYIXBMQH0+OOP4zvf+Q7aWJudwQknnIC33nrLswNTUJiUWLOGXGyffBK45x563rPHkPwBBFETj3s7sLBsn+GFAkgOPPlx0kn03je/nsIGLMM2LEJsRq5RiWUZeBcm0IAgBg4ezFQAyxAE7jyA6DPrwjYJoHADbQtAbohjBZBJClhHB6U8bdxI1/Y3v6HtZ51F2zo6PPYAKisTDUI6Jk59LFYKmFNwGhj7ALH/z+mni58TDgNtbaT8M0wDk1SB8REaxq1iOW7+3EfEYpRuxrfxGWfQ3/zQrzzzZHFszHYGoGvoDaABbcBipKbRewD56WfhxgNobMy9/5JXsFIAye87hWwCLcNeoBtCf78DOYUPkLvgICi1vEAQFUBdXUAqLUKO7m4An/oU/fHTn9Jc5957gaeeEh1TwGBnqqEHE6ODFlODYoArkQHWBNBEuQdKhWya4NiAZmPQCCB5kXc8lILnY2tqEnNVpQAqDI4JoMHBQY3yh9HV1YWKIstJFRQmJCIRYNUq4O/+jp4NZC8cbO/cKd5mHxGvICuyvfIA4sCTH1dcQdvf3B7GsuhmMsE2iJT8UADJpeA5/WvOzDhqMOh4lOYUsPqQBaEzOIh60OyqD5nIMEAKICNvDl5pOYapGIa5hlle7T/zTCJ9eNX/K1+hbYsWiQlof78D7ssq4tZVAkun/fMAkgkufmzd6vxz9D5AfN9y+hcj6wN04w9yc2UkVSCfHiuDUbPJJ5NlCxZYH/OUKYKc8jsNzIgAikQEwWBFAAVNASSTIqXmevm21U/fTLzUbSOfCXTQIbenkZHSB2heIK8CyAmL6RH0wVp3N2iOU1kJ7NhBJROvvRa46CJg7lygvb1ox2YXXiiASgXuf8Jh47GC+8yhIWOVpYI95EsBK3X/olcAAeOjFLxMAM2YQa+VAqgwOCaALrzwQvz617/O/h0KhZBKpfC9730PF110kacHp6CgkAs52D7rLEGO3HCDt98j5wKbVgEr0DHuXe+i58cfB1LlmS8xmH2Yfl0yKVgFlwogmQA6ZX5mhpeJluymrSUydmp1sFg+kxVA6Yzm1gMCyIiYkB8dHdb/b2UC3dAAVEQomjiEDJNiQADZlbUPD4uJpm0VkFkKGJATvR45Qi9DIYohAG8IID3BxY/rrnP+WXoFkN4AmpElgGYsB266SbzxwAMaVaDV6WEUSgCFQuK6FYsA0omMLX2AguoBFA4LeX2pV9b9VgD5QQDZ6n8rC7OP0V+XUl8nL+BUAVSM88zBWg1ozOvqAg38RgPHgQPkhxgwEqgQBVBQCKC6OiEglZFPZalgD9k2kgxmCpjeBBpQCqDJCscOrt/73vewatUqrF+/HqOjo/jiF7+IN954Az09PXjuuef8OEYFBQUJdoJtL2BLAVSgCfR551GA1NUFbKxdjrPwpKUCKOfrZLLIrgm0hQJo8aIx4G/IRkOctibn4x85Qr42APDQh3+P0379j7gB/wUAqE/1mh/D0JAggFKZWWGBsoBCDSVHRsRkz4gACoWA1qpe7BmYhoNoxTzsLTgHaPZsUmbs32+zgoMVw6FTALH6Z/ZsMUn3wgTay3uOjaBff52ar74EPCNLAHUAmCJFD8uWaZjQYhBAAE0Yu7r8J4D0JeAZdXUUFxrdMk7KwBdagcepCqC+nnjeoCiAxhMBJPe/H/6w6KdffFGMBYVWTNIHu729YoV5vMK2B1CmEWvGuSeewGtfvhsfw12YORP4059o10LPMwdrJ2MrXsbZiMeBoc9/Cbn5BBBVHW+6Cbj8cjQ3Rxwb1/uBQhRApU4BszKABmhIqa2lvqq3N3jV+sYDUilx75VjVPNGZVkSQKTkBNB4VwA1N4v+WRFAhcFx9HbKKafgtddew5133olIJILBwUGsWbMGn/vc59DCEZWCgsK4hyUB5JECqKwMeMc7SNTwaPpSIoAMFECmGWfyvlbLcnJ0nIlUZBPorAH0yRk1kRQNxWK5E9+3vx3461+B1/bU4jLsQ390KpAA6pIW0bGsAEpkpr0GCiAnAaoTQ0mjyTurf/SeTzJaKnqwZ2Ca8AEqsIzF7NnA5s0OFEBWkgudAkif/gUIom9wkFZh9V4lxcbcuTQJ7+8HHnmEAtDycuCUU7T7aQigNqmd6Ag4vhxOCaD+ftHO7BJAgP8moUYpYIC1AkifAmbmAeRFBR6n2TNBKAWfTIqucjwRQIDof2VbmFhMELuFQn9dJoIJrhsPoOw415VGE54CQEHX0qXGihGn4GBtIXbilfAyjKWi6Do4YuRwRkinaZBYtw6xVauyBNU3vwk8+CDt8v/7/yVw8cUUxvhVOl2G0zLwQDAVQGZoaBAEkIJzMPkD6AggAJWRMQSVABpvCiCVAuYNXC3fz5w5E9/4xje8PhYFBYUAwTIFzCMFEABceikRQI+NXYSvAs48gDxQAB06JD5m8ZLMTHd4WKxCGuC664gAunvzafgXAH1lzUACqE9YjKCyB9CoMQFU7BKxsgG02SS/tewogEWiEpgHCiDAoxQwnQJIbwAN0OWeMoUC1UOHgIULnR+zlwiHSQW0bh3w3/9N2047LTdY0xBA9VI70S0lO1EAybcWn6tp06yDAoZRKXiZrEwkgF276rFpU2HqDC9TwPSBTKGEKeBcBRCEUvDyby6WCbTXkLvK7m7vCKCJmAJWUBWwhgbMxKHs53R3e6Os4bFmBg6jqXoYhwZq0Y0m8v2zQka6yQSVHGRPnZqbOusn3JSBD4oCyKoCGKOhgcZlRQC5g2Y90pAAqsToKCmFwo4NWArH2Jhoh7IJ9HhQAPE8Q58CZjFNV8gDV9FbPB7Ha6+9hiNHjiCVSmnee9/73ufJgSkoKHiPysgYmpstiBIJxVAAAUQAAcDzI8vQhzrUW3gAmaaARaPWI6qBB9CMGTRwJBJicnryksy5Safps02ivDVrgM98Btja24pXcAb6Qw0AgPrRo+bHICuARjKfy/WhMyOYFwGqE1gZQDNaIrR02xluA1LwRAEEuCCAjK6FDQUQQMHirl2lIYCMUhPOOIMIIE6v0Kd/AeL67tsHYK65AshpChg3NyfpX0AuAZRLVpYBWJXzvU7JSrMUMDsKIDspYIUgnXZeQZuPu5QKIPmW9ZoAKpYJtHz+vFypNkoBG+8oqApYQwMqMIrmUBe60s3o7PSGAGIF0AwcRnNNPEsA5YUus0BO5T12rLiRnxcKIPZbKnY6G98/7ElmBFUKvjBYEUBV4REAdPJHRqyLNvgFefFGrisxXhVA8TgRm3YWsBRy4ZgAevTRR/HhD38YXQY5CqFQCMmAlm9UUJhsuOuuMXR1PYcVKy5A9H/vA/6/W9H83pWIxW639f/FUgDNm0eB5LZtUfwF78AaAwWQaQpY3qVO5B7n3r1AMomysgiam0Ua1Ny5QM00aVQeHjad6dXXA+97H/D73wN34zr0pWhgrxuxSQDFM8ebStH3GFRWtIUk5ZW73c/KAJrRCppxH6yYBwyjdASQAw8gKwLIT9x9N3DyydptsgqGFTM80ebhsrmZvIDkffk89fUBfT1JZOdrBRBAqRTdS2VlhRNAfpCVAwMiUCkkBYzPbzxOk22vih0lEnQOgfGVAsZNprw8lyf3KwXMXqCbRl1d/pJDqVSuAsgryB5oR45MjOA360NiRgBZkeoZhqAlfRBdaMbBfUksWVL4Qg8TQNNxBE01dM27pi4Cjv1VFHKQEQqRDHDlSs1muQ8v9rXyQgEk+y39/d+LYgA33AB85CP02o90NrspYMDEUMGVAkwARSJpRJIpur+SSSCRQGVY9HPxeGkIIFb41Ndr59LjQQEkE0DV1XRfDQxQn60IIHdwLEK7/vrr8YEPfACdnZ1IpVKahyJ/FBSCg5NOAhYs6MPSpcCyk4awDJsQS7+V9/+4qpQcsOzfr6sq5aECCBAqoEfxLmdVwOyU5WhvJyMDxte+li0zKy8unnIKKDLmCClPRMQVoO7F36FvjEbz+riFK51kAt03GBW61UIiw02bCtpPTgEzQ0uKcnI6I5mcnCClgJkogPSkhhdG0HZw8smUkiA/ZPKHK4l961va//uP/6DtixaJqm01NWJitq9Hiq4LSAGT9y+UAPIDnP5VV5e7Uu2EAJIr3XgZzMjc9HhKATMzgJa3eU0AcaC7YQOlyzJeeIG2bdgAvP56AtOm5f9ivX+KlUeaU3D3y/fpRAh+eVi0awKdRXs7sHw5AKAVBwEAB6/7omE1LqfVJzUKoHo6wO41nzQ+Pr55b7tNM+gnk1rj12ITQF55AMViNDYcldaLyspyxwwv4YQAmggkaCmQnY6WSZVpM3PTaGo025QLXENzDSP/H2D8EUCAqgTmBRwv3x85cgQ333wzZoz3MgkKCpMJvAyVx4nQzIPms58VrysrgW1X1JF5owcKIIDKwf/XfxEBlB55BXpht2sCqL2dysnqVhg79ofRdeV/YMqiCwGQ1rq5Gdi4KQSUn4vm+D7E8ozSp5wC1IX60ZluBTLHt+d4M7oyVZ1yVvEkD6D+/hBdk+PH6eHW0MJuJGSynx0CqDVBM/mDafMy8E5k7TwB3bfPZv62Vc6NpACKxwWBoFcAyX5PpYIbxUwsRpOyjr56nMo7uVAAybdHPE7kys6d9HeQCCCz9C/AWkmjD264/Hp/PwUzVu3bCdwQQEFKATMSGvppAs2+LakU9d3JJBHAbMA/NkbV8PJBf+68UgCl04LwmTMHWL9+YgS/eRVARgSQbqzMEkDHqmj7/fdT7jPcedVpPIDqacDsajuDPvdTn9KOUW1tRP5kvo9x9KhQ4AFAb29xU8C89AAaGQEOHhR/+x3I2vUAAibGPVAKZNtHWRqIgxoKy9fHxlBZSe2gVEbQZgTQeEoB49TIGTNowU8ZQbuH4+jtqquuwlNPPYUFdmeNCgoKnsJusN3UJCkebBJAtoPUwSoigDxQAHV00KSkDKPYhxjan9mPebPF+83NNjyAjGZkySRw44255A9mYxHeRBxVwDax/de/pgfwHCoxjG279yGmIxLkY16yBIintbOpVcOPABk/lxz/EzkFrB/0o5kAcgu7RgEm+9nyABrZCwDoHMt8hkGkyKv927YBl1xC2/72N218wYQYt6+hIZqQyGaEhrDpAbSXDhO1tdr0RUDwa24JoFL5NsRilCLQMSCdJBcEUDhMt8jo6PhQABkRQGYKoGRS3EKyr0FDgyCAvAJP8CMR+9x3EFLAiqEAsjKBDoepjzl0iPocJoDsQt9FehWoDA2JsYX76YkQ/DpWABmMlUwAdSLTeWZKsiMScUxmp9PSYgOOoKmBTnp3N4jkaWyk0potLcA991Dal8HcQq/gHA8KILOp11tvaacmfgeySgHkP7LT0WiGpZQV5aOjgSGA9HOuoCuA0mmlAPIDjgmgH/7wh/jABz6AdevWYcmSJSjTjTA33HCDZwenoKCQCzmH3AzNzTSXyq6u2iSAbMOUkXEG7UoikThX3Xo+cKvYp7JSmL6ZegAZEUDr1glJgYQuNBP5Y4E4qtB1KGFaotbpBLijA+jaNw0HMgqg7m5gY805APYA61Ouc/6bL16KSsQRh3n0X4k4mi9eavielQKooyPjPzNES/s9o7V4HuegYt80YGOuwikWo0ktQBl2551ncjyVFAwePUoqINsEUB4FkFwBTK8qKpQAku+5W26hReuPfhT4/OfFPn74NmTTx4Ylhs5FChi/zwTQyIhIwbNLAHFwUAwCSF8BDDAngGRyQE8AcRv2Ck5LwAMTPwXMrgk0E0BHLWzSzOCXAoivSTgsSMeJkAJmWwHEnYbBWNnC3m9o1ZRkx6pVjo+nt1cEx9NxBM1NxHxkryPne0ajlp+v77/HgwcQ3xd6BRAvWDD8DmTtmEBz/6kIIHcQBJCUAsZz5QwBBJSeADJTAPX1kWDJI2G/Z+jrE6eRj5VjAkUAuYfjy3zPPffgscceQ1VVFZ566imEpJl2KBRSBJCCQhHA0noryOVSPSeAWIddoALILpHCv8U0BcxoqbNQwxePRmlBcn07u62rCziz6//oj0/RPKG93fnEKzYvgjfvfBxnfeYsdGEafojP4jy8gP/F1fgevoxyDOPnN2xG17Gz0SUF7kxWmJlAHz1ahVNPjWZOwePZ7efjBWAtgLXGFZ527KDnE06wPu7ZswUBdPrpeX6kTQ8gMwNooHACCBD3HH/GxRf7X4I4SwAlJLMqEwVQPlPJykoKAuJxCj7SaQpO7GZzlzoFzIwA4sCmokJLzBitZheq5HJaAh4IVgpYMT2A9GCVYZAIIFkVMZHUD5YKoIwpLQDRkA3GymwKGCS5lssxlRca6sP9qEyNZIO47CKWzUbIX19VlcbwcGhcVAEzm3rt2UPPs2YR8a0UQOMfOQoggxQwoHQEECt89AQQX3eAxncrRXgpwP19dbWYBvK8RaWAuYdjAuirX/0qvvnNb+LLX/4ywlZllxUUFIKDgCqA7IL5JkcpYLrysY5hUI3MDeyQXKOjwGWX2fs8fYDac8670QWgGoP4BH6Jw5iBO3AjfS6q8P/+62zgv3I/Y9s2cwVQf3854nHrybVRhaft2+n5xBOtf8Ps2WQUassI2qYHkB0CqFBOMJ0WqrpTT7Xe1wtkCSBZiyYRQImEmF/aUQABdN34vBuppcwQ1BQwfQl4/f5yMCMrua67Dti6lbZfey3wj/9Ir62UXE5LwMvHpQggenYzYdefO69MoGXz8IlUAclSAWRkZGUwVhoSQC7H1KwBdPgokAKap1GnkyXyuB/PU2CA++9Fiyg1djwrgJgAOuccWvw5coTmOX6FVYoA8h9ZgrAsMz+Wyy56oADiKqJmyKdCNlMARaN07Xt76Z4MKgEkp/arFLDC4Th6Gx0dxTXXXKPIHwWF8QS7BJDdsuKmddn9genXWRFAK1dSLsmBA8ZlZvPBIwKoUPz618AXvkCD4B13UPl5eZD/05/o+Z3zd6Ni96i9FLc4rcTbMYF2AicEEGCTALLpAbQ7Y6hplNLEccuRI9TE3TbbAwdokhSNUpU9v2FIAEmRhNxEnRBATv1/ADFp5OCguZkuidVt4tQXyU0KmL4CGMMsmGEll6wiicftqbncKIAmegqYXQKI+5hCFEDV1cQReJ0CJhNAEyH4tVQAGRFABmOl8ABqQQphhGfPyinJbhfZEvAhuvhN06kDzgazMgFkURmACaCTTkrjlVdC49oDiAmgs88mAiiZJIWG1z5yDCcm0BOBBC0FstPRiKQA8ogAcmO8rocZAQRQKn5vbzB9gIwIIJUCVjgcszgf+chHcN999/lxLAoKCn6BZyEjI7rcMB3slhXnUaJICiAeWLdv15WZtSKAIhHg9tvptV2Zg4yAEECLFwNXX02vX3kld3Bfu5ae39P6iqPPHR4WQZ9XKz5OUsAAhwRQAQqgadOoCSSThQWPrP458URnq8Buwdd6P9qQ5OFaWiWXJ4P5ghI+fSMjggBauND+sfCkMR6nRywG/PKXtG3qVGD5cpr0fuUriWyZb6vJqBHcVAHjv80IIKNgZmREq0Rh76p8cOMBFIQUMG4yXhNAY2OiC7YygQa8SQGbN4+e/SCAJpL/iWVxTB7XQiExfhuMlTNBua4JlKEbTTkl2Z0gqwBK04umGfS92esoN0yLcZfTb086iUiqeDxU1HSaQhRAZgTQiSeKvtXPdBalAPIfggCSFEDcWAokgJz4TprBzAQaCHYlMH0FMEAsKKgUMPdwHL0lk0l897vfxWOPPYbTTjstxwT61ltvNflPBQWFkkGenQ8OapN+ZdjV1vNIVCQFEE9ePvhBsa2yEth2a5S0EWblTtasIcfeG280NIS2REAIIICq8N55J/DAA8BPfiLm7V1dwAsv0OvVU19w9Jk8Gaiqyr96bweplCgt7pkCKJUShKWFB1B60NoDqKyMJg9Hj1IQ4VbxtHkzPS9Z4vx/3fjPzJwJRCMpJJJRdKIFbTigIYA4aC8ry38rFqoAqq2lxcxUitpOSwtVegOAK68EysrSePllCsqceCOxrD2REAFedzeRvICQtXOAPjCgVXGZpYBZBTNy+WXAPgGkUsC0kNNa/EwBY/XCvHnAG2/Q+oMX6TJGHkATQf3AXaalAqiiQrswohsry5DANBzBUUzHwR/ci2lr3uH6eLIl4FN04zW30IENDNDhVMgNc2jI9AZjBdCJJ6YRCqWRTpMKiFN8/UYhCqDBQa24iQmgefNIzXDsGBFlp5zi3fHKsGMCrQigwpAlCCMZyXpZmbjgY2PZvjZoJtBAsCuBcVjihwIoX1qdfmFpIsExAbR582YsXUoVZV7PlhgihNyssisoKPiP8nIajMbGaNZlQgA1L6hHJYYtU4gqMYzmysxyVgnLBcTjQFdPmAggqyW5NWuofO26dTSDPH4C8CmbXxAQXHghBcJdXcDTTwPvyMzFH32UJpWnnQa0JW1GsRnwQD99ujuBlB7799Mpi0aBOXOs97VNAOXLccoogA73VWJoiH6H2XfPnEkEUGcnnS83KMT/x271PlkxE4kAbc0j2Hu4Ch2I5RBAdiuAyfu4JYDCYeo2enpoIjljBvDgg/Te+98v1F/bttlvTGay9ksu0R73tm3aIK+/X0xinaaAAYIL5nuqq4sCtHwkRqEpYBbZLb6CyR0WzMnwggCKRPKrIrxIAWMFUCpF1zVvBcE8MEoBO348mJVwnMCWAsio0+Cx8n3vA9auRevUOI72AAdPfgdkr36nZHY2BSxFDG/99IosmdzdDbS2ltEJTyQsGyITQK2twJQpYxgYKMexY8UjgApRACUSdF0qKmgKxuPAvHl0b7z5ZnAUQAMD4/8eKAUMFUAGKWBu020LhZkJNCD60iArgIwIoL6+DInsYExm2Euri+KOO/JU2BincHx7P/nkk34ch4KCgt+oqaHIzcIHKHbV2dg283x0HUoAMPLNCaG5pQyxaZlZRJEUQKbIW+82g0gkW162ucPG5BXDaI72mr7f3AxURhOIJ8y7UJ4Ae2FYGo1SkP2LX9AiLRNA2fSv9wB47rjZvxuCV4O89v9ZsCD/xJEJoP37tSv5Oasx/WMAMiXst1SgeaYupSgTve7unZr9XLOmMHMmKXgKqQRWiAIIsFe9L+d/mgayBND5eF4ju3BCAPEEaWgIWbWUEwIIoIkjE0AbNpBlSE0N8Pa3A+Ew9Rfbt9tnOJzI2mMxcd/29eUngKxSeph4XLyYsl77+6ntnXxy/mMB3KWAJZM08TciYfyGlQJIyqJ0DNn/Jx+x5UUKWHMzKRiOH6egwEsCSG4//f2Ff3YpYVsBZIRIJCujbG0cxqs9uYo5JrMffxz45CfF9ptvBj70IXotk9nZFDDQi/CUKjQ1UVsgAgjUEPv7TY2g02lBAM2cmc4SQMVUq7hRAMmk8uAg/S+XgG9spHbnt5/J2Jjou6wIIPm9vj5twK2QH1kCKOyPCXShsFIA8bUOogLIiABqaBBr2keOiDmlE9ibf4TQ31+EfP8SQPG7CgqTBTYIIEQiiP3oS4hddVWucTLP8H94P/DjH9PrApeI7KwkWiJhkwCSkFeJ8a1vofmBnyNW+Q/Wn/HZ29H1X78FPnA18OUvA1/8IvCXPwNf+hJw9TXZCbBXFWuuuooIoD/8AfjhD+nyPPoovbd6NYBHnRFAPNB77f+TL/0LoAl/KEQTpqNHaQJsvBpTByCTC3SO1uSwowPoOjADwFL8tfu07G/Rpw4x2AjaLQGUTAJbttDrYlQAY8Tq+wFME0bQBSqAdu+mGDAadU5GyZXAnn+eXr/73fTZJ56Yzn7+2Jh5VmYhqK8XBBDDbGXbKqWHFUCzZ9N9sHkzpYHlI4DcKICYHEmn6ViDRgB5oQCyk0LqRRWw2loKApgAyuc1lg8yAVRWJkym+/rGNwFkqQCyw2JmGkVrVS8A4+qJsVju8G9mpp5NAcsQQKiszBJAmlLw/f2mDbG/Xxz6zJmkAAL8rUqohxsFUFkZ7T86SlOvqVO16V+A/34mx6WpgVUKWFkZ3cuDg0ScKwLIGbIEYUSal/K8OUAEkFHfNt4UQKEQ3TcHDhBx6oYAmuxQBJCCwmSB3Upg7AVw7bXaFJy2NjKCXLMG+K9MXfECFUAaMuanPwV+9lPgA1dj6+VfxnXX2fgALg/m0JHXUokx+yiAfXkjolhqL2LYBJy4GljG/7cJaNxLf2dAJFc6b1n1fLjoIgpqDx8GnnuOTv2xYxSUn3sutLM8G5BTwPSoqxvNe8x6vxpWANkJysrKiJA5eJDUGDNmODc5JLLoPAAbkfErxYYNwJlniuOTTYg5TUAmgJyUVd25k26H6moxcS8GYrU9ABagI7oASKBgAuiNN+h5zhzn/C2TKseOkR8VQMo0gIybKyoSGBmJYvduuj5eo76e2r9M6hSSAtbWRr+FCaB8cOMBFAoROdXXR49ipavI8JsAymcADYh+pq+PAiUnXbZM8jU1kYLCi0BFTx42NNDtNd49UApSAAHZRtFSQSdZrwBicCopkwbsAadHNgUMR7KGZTmms3lKwTMJVVdHuzIBFHQFEED3R0+PuF+YAJo7l579VgBxO6+szE/MNzQIAkjBGbLEa0ial0oeQKUkgEZGRB8/ERRAgCCAlBG0O6ha7goKkwW8TCs7d5phzRptRHXqqTRrWbOG/k5mJK4eJInHYrRquGxON5ZhE5bV7cy7Ep/FmGS25xXsRkR6Pa0JwRaLAdtePo4NWEaP50exYQPw8L8+h3JYG03LJEt5OdkzAMTPcfn3Sy/NXIYMAdSMLlSGrT83EhFBcCqlq6wGYNq0Ybz+egIbvvx7OuaL/gkf/zuamF+OP2DD+nROhSe7JeAZXOrbViUwHdxUxNATQKw4OvNM88eiReKcsP/P4sWFm886QayKfkRHeaZkl8sUMN6Hf4fT9C9ANPWXXyY1VDSaUZ+BzsmsWdT2t21z/tl2YGSoXCgBxJ5RfJ2t4EYBBJTeCNouAaQXfeYDd3V2FEANDWK9wKkqUk8AAd4QQPq2M1EqgdnyALKjACqjC5WPALroIu3femhSwDKfzeOaYSl4AzABxErOmprxoQACciuBFVsBZMf/h6GMoN1DpIBJCiCPqoAVCr5PeEFCj/GgAJIXHAFVCr5QKAWQgsJkgV0FEEA9qjwbOXZMq/Zh5Y2XHkA8IeVR1A7segA5gV0CiGdIPGOyOL+xqQOkFgqHgXPKgBCAnmHs+M8T0LXwPOC++wy/QlagdHQAZ5wB3HUX8L//K4KVxYuJvGnuq0cMhxHDPmw74b3ouudxzWd1dpJaI5Eg/o4NfH/9a3oARBIwQRCLAWVNbwHYBMxajPeuDuG/7wV2YwGWLR7JYR3sloBnzJ4NvPSSOwLIDZgA4kDCqf9Mof4/bhErowPuCHmTAsbXqRAC6Le/pedVq7R+8rNmDWD37gbfCCBu83ZSwKyCeZkAYj7NjgLIjQcQH8u+fcEmgNJpYVJrF05SwMJh6s94aGlttf89LG6UCSAvUmv1BNBEqQTmlQKoNUpzgHwE0CWXAA8/TMosffrn4KBoJ0QAUWPJIfLyjLt6AqjYKWB8fwDuFEBArgKICaBiKYCcEEDj/R4oBbIEYUi6AT1KAXNTRVQGK3saGowXsIKsADKqAgYoAqhQKAJIQWGywAkBxNFuUxPN0A4e1Frte6gAyoJJHCfl10tJANlUAAEwdkutrUUM+xAbC2tSxoyg98c5elSYqX7ta/SoxCvYhkX0mcffQEz3mRs3Ct7ODPG4bgWIf0tNDZafT7P6N7AYg0f7MGW2YB3GxoSxsF0FkO1KYB7BKAXMCQqpAFYIYlGKvjpGMz/AgAAyCuz14Mkn37pOCCBOleNbkyeJZ56ZIR+bKTBrbaX28uab9j/bCYwIoHwKIKOKNtzmZs8W59BJCphbBVCpgio7BBDv5xcBBJDS4fBh50bQcgDLAY5SAJnDdRUwBhNAYeosjTyAAEEArVxJ/zI8TPfRwoViH15HqqxIoWZkAKikKC7nOuZRAHG/LRRA9COLda14qgE4n27opwZsAl1sDyClAPIXfqaAsV3C0aPA+eeL73r4YXFP6H0PZVgZQAPBLgNvlQIGqBQwt1ApYAoKkwVOCKDXXqPnVatoYpZOa3MkfFYA8WqHFSorgeayzAx+PBFADJ6N2fDusaVWQRW6IM2qneZzGEE67llzomjFAaQQwab1Sc1ue/cSsVBdbX9lv9gEUKEm0KVSAM1O0313bKwWx1FTcAoYwy4BJKfK3XWX9r3vfEebKtfW5m8KmBMCSF/ViTE6KlYM5RQwvzyAgNKngHFMbUQAlZWJFWGnPkBOCSC3lcD8SgEz8gACxr/6wXJdxA6LmWngrSDyubOTUoVl9PaKa7BwoehP9D5A2fSvhlGEgGwjzFFyBVwBJAuTnRLAcvZ9Oj0+FECKAHIOQQBJDKyHKWCxGI1Xcltsbc1YKCyzLupgZQANeNuveonhYdElKAWQt1AEkILCZIEbAuj004VTIS9bAf4qgEZHs6sdGzaYP7ZtA2LVmdljKTyAHKSAGUZKXI6jv98bskaG7PhXCHTHvTy6CQDw0stac2j2/1m40L4/TqkUQH19zk/N8LAIbIqtAKobOYoG0OxtH2bTwWSisWIQQHZT5bq7nXsA2SZ6M7ymkxQwrmgDaIOZzk663crL6XOZ04xTWAAA6ElJREFUADpwQLvKbwS3CiA+7iCmgIVC7o2gnZhAA4UTQFwFDPBHATRRgl8OEA2HRQdVwGakOhEK0XCvv2as/pkxg64/9yd6HyBBAGnlik4VQKIEPD0X2wRaFiYXogA6dky0Z55asZJhaMieRaNTyPdPPkwUFVwpkCWAYOwBxP1sIR5A+vmS3X7QrgJoYMCZC4Pf4N8XjeaO8YUqgOzNP9KoqwvQCfEQKgVMQWGywAkB9Oqr9HzaacALL5Djq0wA+akAysy0LCt1MSy17i7hhwKIJ7VGBFAiQb/ZqazACLV1QLyMItnu7sJrTkspYACwvGIzHkxchpc3aYcOpwbQQPEJoPp6amIjI85XjLZuJc6luVmsOhUN/f2IoQO9aEQHYqjBALqeHwGqqrJ+PsPDlIoFmMvA9c1r/nzvD5VTwLq6qPnlKyPMRO911wHr1gE33wx86EPafeTf48QEmrfpK9qw/8+sWURWzpghyjQfOCCCMiO49QAKSgqYWXdQVUXnySkB5MQEGnA3YR8ZEd283x5AEyX4LVgBlBkDo/GBbNrewYPavo+JHiZ+OO1LrwDiaz29VstCFqoAKrYJNJ+2SMT5tEdWALH6Z8YM8ZNrakQK3eHD3vfNSgFUHGQ9ori4hw9l4Hn8YtjtB/MRQPX1dKjpNKWBlaJapRGYAJo6VZxKRqEKILkK8XvfS33cL34BLF0q9qmvT+D11z1YTA0gFAGkoDBZYJcAGhsjwgcgAshKAeQlASStlNiGnwSQ1Sgdj4v3nSiA5AhMXjY/ftwbAmjKFKB6Ko2I3d2CZXELnQLo7JotwCDw8uvGBtBuCKCDB6k5OTE5dBP8hUI0qXnrLQomnATxsv+PfhKSRTJJLEZnJ0UpK1cWfH90dABdh1pRD4pU/4TVuBwPYnSF9uCfeIIeAJ0jfYU2QPt7W1rsB+1OUFmZRFtbGvv3h7BtG3kV5ENbmyhN/8EPkpTdDHoFUDptTQA1NFD7koMZ2f8HIBIoFqPA9a23rAmg8ZoCZqUAkrcHMQVMPmdeKoBGR0VfM9FMoC0VQA4IIAwPo7WVhpPOTm1gZJcAyiqAajKNJXPzOC0Dr/cAKrYCyK0BNKCdGujTvwAaU2bMoCnWkSOKABqvEAoggxtQ8gAqRJztVgHE3j5mBFAkQu/19ASTADIyt/YiBSwWo7kAf8/b3669N8fGxPxvokERQAoKkwV2CaDt22kkq62l/AjuDXnmAggFkJcpYDoFkC2USgHEsyO5pqbTFLBIhP4eHKQZGkdHhaC6mkw2mQAqFLrjPqthJ3AY2LW/Ej09QjbMCiC7FcAAmmBEo9SUOjtpIL7zTuBjH6OA7KtfBf75n4F52IX7z/v/gB/+UKMGcVMRgwmgQ4dE6o8d5PX/aW8HbrxRuzzX1gbcfjuwZo39L5IgjL9/k932Q9yQ9//kymUyZNLCTQUwu1i0yBkBtH07TTirqqjKnRX0BNDwsOiKzAggeX9AWwGMIRNAVpiIKWDydpPY2xTFIIDYIm3KFOoyvTKB1hNLwMQJfr1SACEeR+tcYNOm3EpgjgmgKYOaz3abAlZqBZCbqYZcBt6IAAJIHbd3rz9+JsoE2h642IEZrEyWAWk6mvZPAeRXChhA87menvyfWeh5cgKzCmCAUJR2ddH6m9v1tp4ecX87qU453qEIIAWFyQK7BBD7/yxZQsvjQVYAlaoKGI+mck1NpwQQQDOywUFbRtC2MKUaaPDQJEN33I01Y1iIHdiJE/Dyy8Cll9LbbhRAkQgNth0dFJS3tQF//CO99/GPA9deSwTQW5iLk5qOolpShrB0d9cuWrEBgKd+vgO1ywQDZTQJkY2gzzzTPonEBJCh/097O3DVVbk+TgcO0Pb773dFAtnx3nGCYhFAJ56Yxl/+Yr8S2N/+Rs/Ll+e38tITQBzEh0KZJqpTYTXUvw1AyDAFTCaAmAyUfe6NMN5TwIKiAHKSAqZXL8jKkXTaQpGXB3wtpkwR6xgTJQXMlgLISsYmSRW4z8xHAPHz7t3aYIyv9YyqzIXUpYD19maq9Fk0wnhcDLl6D6Bim0AXogCS01H1BBCrGfyoaKTKwOeHvtKqEczUtYwsSQhpYdInAojT2Z0SQGYm0ADdkzt3WlcC8+I8OYFZBTBAjCepFO3HhJBTHDhAz83N7u7v8QplAq2gMFnglAA67TR6NiKA/FAAuSkDbznTdQknCiCeLQHOPYAAsfTsFQFUPUWMlLpR3K7hrmag1XkAoaoKy/EyAOBlesLwsAicnSiAAK0P0KFDwEMP0d9///dE1syoHUQKEbwWz2WWYjFRmWY+duFti7uy1TDMKmLIpeCZRDrlFNr2z/9M5uKs8vnEJ8QkhiXAOQqgZJKUP0Ym3rztppsEYVoCdHSQP5BcyrmqirZt3Jif9HAKJgHtGkEzAWRHLaQngPi5rg4IP9BOfdVFFxF7eNFFaHjqAQDGHkBGBJBfCqCJngJm1wSaJ+huUsD0BNDIiHPFkgyj1MGJEvzaKgPvIAUMyE8AzZ5NwzB7aTFY0TK9opdeZAahxkYRG/f0wFIBxOlfFRWy5R4RQP39uRXK/IBXCiB9CXgG3xt+KICcmEBPVgWQ3WIHVsoXQwUQz0099gDixSivFUD5PtOL8+QEVgRQNCq2F3LfcH81mdQ/gCKAFBQmD9wSQDxT6ewUEYIfCiCpDLxtlCoFzGg0lc+vnhAwWyqXK4FZwBZ5g2E0NyZNTTJsV1aTiRP9cVdX42y8BEAQQBwINDQY52lbQSaA7rqLeMXzzgMWL6bgYFkrzfw3HV9o+P9sfLwMG21FrzIBBNC/bNlCzfif/omIo699jd574AFaYTp2TEwQFi/WfeC6dbmujDLSafpx69blPTY/IJdw598FAD/5CW2TS7h7hUWLqO3bJYCee46eL7gg/75mBFB92RCprXTXon6YLnTv81uz2/QeQIBzAsipB9B4SQHz2wS6EA8g7iqnTBHdfSFBhhEBNFEUQCyMLbQKmEwAyQRyPC5uNSaAolExVZDTwLIpYOW9ms+ORgXZ0NUFy0bI/fXMmYI0YgWQ7APmJ7xSAJmlgAVNATTe74FSQBBAmXtMrgImeQB5oQDidGkvCSCTtcOSwooAAry5b5jcnjXL/WeMR6gUMAWFyQK3BNDUqfS/AwMiogyaAqiUKWAMPr+JBB2XPFM0MoEGxIwsjwJIrlZgiLvuQvN/fQ2xGW8HpmaWEg1mBnYqq2lKYesJIEkB9NJLNPmWK4A5TcfgILyjA/jTn+j1Jz8p3l86/SAe2bYAG/uMc5Y0BNBQfgaBCSAOZn77W3q+9FKxAnvFFXSOOjro/UWLaPucOQYTaDkqsoLd/TyGk9U6s3Zh15y7qYl+5oknEgG0cye1JStxXne3SBU791zr4wRylTTZwKa3w1CF1QC6T/se+RuQPBGIRCadAiiZFMcdlBSw3l7qIu30F/rgNRSiNnnwILUfJ15eVp8LTJzg1zMFUDyO1pY0gJBGAbRnD91uNTVa67qFC2k82LlTpOZmCaBot/azQX3GsWOZocpCAaT3/wGAsrIUqqrSGB6mFE+rwNYLeKEAOn5cKID0ZvPFUADZIYAmCglaCmRJwpREAElvFkoApVKCeD39dHr2ygQasKcAKjasTKABIoC2bPFGAaQIIAUFhYkJOwRQT0+uxjQUotnK66/T7GXRouAogErlAcSzI3k0laOggQFjAqiAFDBL8uYPOwHs87ZMDmCYArYUmxAJp3DoUBgHDrgzgNabCN5zD6kCqqvpczo66LcuayZpysYe4yhPqwCyKB+VgawASqeBu++mv6+7TuwTjdLf//mfwC23AB/4AG2fPdug1LockVjB7n4BRF7yEXQ+Wlqoi2hrEyWN9+yx9oV64QV6XrTInnpMVtJoKoAljA+uAb0AgN6BCLBuHcYuWJUNJs08gKx8ZcajB5AcbJSaAGpspCEjmaT2ZMf33ih4bWoSBJBb5EsBK8RfqNSwVAA5IYAAtDaNAKjUEEBy+pd8jlgNxO+Pjoq1kumRXAKouZnIoq4u2CKA9JWJGhupzR47lquo8RpeKIB27aL7kSsPyvBTAeTGBLq/vzBj3cmILPHKBJB8A3pAAB09KohzTkef7AogJk75vnFjUD1ZU8AUAaSgMFlghwBit9u5c7UzY5kAAgQB5IcCyE0KmB8eQKOj5jMgo9E0GhVSiYEB7YhVYApYXvAMr6bGu1E8nTZMAavGMBZPP4rXDs3Ayy87N4A2MhHklJChIaqeziaCy6buBQC83t2C0VEtz9ffL8inpdhkyxBENoF+/nkiKGpqgMsv1x7fD35Ar3fvBr7zHXr97LOUMgVIJocrVxKTcOCAsQ9QKETvr1yZ99iCDCfKsXCYru8rr9A5smoXTtK/ANElpVJ0i2WDeBgzK1kCCA1AZ2eW+Csr0xpGtrXRpYrHaSLJwZge47EKmEzqlJoACodpAn74MN3zdgggo+DVC47bKgUsmaTfZtfbKEhIpz1UAAFoaYwDqMShQ2I4ZIKHK38x9JXAuF+PRICpyIxHUv6k5jrWmDdCIwUQQNfr4MHiqFW8UADxWNnWljtlCZoCiP/Pb2XVREIOASQ3Fg9SwHhtduZMQYZ6aQIdRAWQVRUwQFsK3q1B9WRNAVMeQAoKkwWyE6EZ9OlfDH0peE4B80MBFJQUMMB8JDEygQbMSTYzE2ibKWB5wf/vpQKICTBAkwIGAGe3UCL6yy87VwA5SUuaW34QDTiG0WQUW7Zo93n1VXpuq+rCdBx17AHE6p81a7SZeV1d+Ztg1uQwEqFS70CuXID/vu22oi6jcuWyUoLT5vJVAnNiAA1Q82POua9PMoGGMbPCxFAvGoCWlqx/wqxZongfQN0Hr/5ZpYG59QCSU8CMeEI/wbdFebl5MyyWCTTgvBKYmQII8J4Aqq7Wtq/xCNlv3nUVsGg0e4NMrxlCOEykK18zvQE0Q08AZQ2gpwPheGYM1CmAgPwpYOwBpCeAGhvpZipGJTAvFEBsVm2kViqGB5AdE+iKCnGJVBqYMxgSQNLCppRZ6Qqyfx33gX19YjpuhuFhcdvbSQEbjwqgw4fdG1RP1hQwRQApKEwWyE6EZlGIGQGkrwQWNAWQXwSQWURkpqc1I4DMPIC8qgImE0BeLePwMQM5BNDy5r0AyAfITQl4uwiNxEndA5F+xcimf03NROwWCiCuhMUrPWNjwP/8D70+55wCTZDXrKFS7/oapG1trkvAAxnvnXLr6mHl5cDDD+cx8i4BmACyMoIeG6P2A9gngEIhrRE0Bzb1UxKG+TpZBVDZNGDlSkP/H4adUvCFegClUtrbqhjIZwAtv+e3CTTgvBKYFQFUiAm00eeGQuPfB0gePl0rgEIhYdY8NpwlJ1iJk48A2rWLphhMZkyfDsOGqLmOFo3QTAHE16oYBJAXCiCGEQHE90V3t86Hr0Ck084UQMDEqYZXbGTbSFJi3aV5LXOuw8PuFgJkAkieeuYjbPj9SMSaBByPKWBeEKcqBUxBQWFig8mJdJpGID0ZAdgngPxUACWT9pPP/SCAwmH6vNFR7wkgv1PAvFQA8W+QS5lm2szyBmJ9nn9e8C5OS8DbQpwIoCfxdmzapH0rSwDNOAAcgOm1MpMF89+f+xzwj/9YIHGyZg3NRFasEB96++0F3R+xGLDtR39B1ye/DJy6hMqkffvbwB/agc98FvjEJwzz2YOAk06iZysC6JVX6JI1NgrCyA7q66lpywqg+ovPBh7M3bchowDqa5xragDNiMVIkWSlAHLrAVRdLbxv+vupm3DjVeAGfhJATlPAAOeVwIzUCxrliEsYKYD4766u8UsAyeSB6ypgADWKwcFsJbDOTiLQly0zJ4DmzqXhc3CQVuSzBtAzIBqXWQqYCw+gYpJ1XiiAGEYEUFMTskqro0e9C0aHhoTyyAkB1Nk5fu+BfOjoyCW37FStzKeuzU5HZQKImR6JAEqlaArt1LmACaC2NlFFr7eX7h/9+pMMuWaJla+ZnbVDu0UhvFAhJxKiDdpJAXODsTFBHk02BZAigBQUJgtkwmdgIJcASibJ5wcQJQYY+hQwPxVAAI2kVhELww8TaIC+24oAcpoCZhYp+ZkCduwYzTTCLoWeRsdcVYUOzMbYcALl5WKuPnWqkP17SkqMjJDBMywUQK2HgI0wVQB5UQnLFmRpx6xZnpCjscojiGETMLMJWAYg1gVgE9Cwm/4OKOykgMnpX06aqJxOlU0BO2sR8P/uB665RqOHb5hZCRwCekepDdtRAPmRAhYK0XEfO0bHnUi48ypwA78IoNFRcardEEBBTAEDxr/6QVYAuTaBBjSNgpU3Bw/S0M/TAD0BVF5O7XXvXhoPNATQ4bj2cyGCRLcKoGKmgBWiANITQPoKYAD1gdOm0Tk7csQ7AoinBqGQ/ft0vKvgrHD0aBVOPTVq2feWlwNf+hLwrW8BJ58s0sXzzW0sCSDJAwigvt8pAcTjF1dPbWoSBJAV7Pj/8OcB1gogLgrx2GPAP/yD2P6ZzwCf+AS99moOKN/XZsdeqHcW9y1lZaVPnS82FAGkoDBZEA7TDGBwkAgK/ZLB7t0URFdVGS/tATQzGRgQg5qXCiB5ZjUyYo8A8sMEGqDv7uvzTgFk5gHkpwIolaLf4NLFMWRwzB3x6ViEbYg/rL02PT0GBslekEDxOJbhDQCkGGFh2NAQsp5Ay2IZGYVT+YLXkK+hV3k+8nUFBGlr8/OLuVong9MBu7qobRhN3pz6/zAMU8DqQSqshgbB5N11FxpOXAnMon1TKa2EXg8nBJAbFQATQH191H6LQkrCPwLIKEPUDrxMAfNLAQSM3+CX10QkGx8tnBJA8XiWjDh4kNIlRkdpyDW6jxYuzCWApk8HsNc8BcxKAZRMCrLQyAQaKPxa2VHjFaIAspMCBhBRJiunvICsoLNb1W683wNW6O8vRzxufSJGR0UR3M5OUr3ZQbaNJDKdY1mZRgEkt5143J4nkwz9+NXURGo8uwRQvqkgj9M8PpktdMRiuSlsIyP2z5Nd8O9qaDBfa5ZTwNyk1XH6V0uL+7XS8QpFACkoTCbU1AgCSA9O/zr11Fxip6GBZuD9/UQUMbxUAOlKZtqCHylgADTJ2kaQNbUySqUA4u+rraVzUVND27q73Zfx0JeAB9CVaEAc1sScV4Erf9iJ2I7qigSGhqLYsYPSizZvpoB++nSgdVom4rFRBcxX+EkAcTvh9mPzt9ot4e51GllNDals9u+n7z/vvNx9vCCANEF8KiWWLqNRYNUq1GdIlnSaTqVXCiA3QaBcCcxMzu4HuKn4RQCVlTnrfp2mgFlVASvEAyirHtOlxYx39UPeNREXCiAmgDo7RfrX3LnG6z8LFwJ//jPtx8SNJgXMoQl0VxeRQKFQ7poVD22FKIDsVg76whfotRcKIDMCSF/S2gs49f8Bxv894AU4Hai3l9qXnWmUoQJIelN2F3BjBG1EAAH5+8F8BBAToOm0SEN8+mnRVxvNEThlbvp0aq+sCvQS+SqA8fcD1K1Z1bcxw2StAAYoAkhBYXKhpoaWl4x6Si6rpPf/AWj2NXcukUSc6wN4qwAKhcToaLcSmF8EUL6IiGdGQTSBBmgphwkgfa1euzAirZzmvhSKeBwRpHD63D48v60JGzcSAZRN/1oGhKZkzmmpFUByzohXBJDeAMXCJ8MMdkq4+4FFi4hwefNNIoDkVfbOTnovHKZAdeNG+0SUKQHEMh8gez9UVlKcOzJCbxdKALn1AAK0qWt2CaCtW3O3OSXs/FIAuTGABoKTAqZRj0nwIgWsWP5ORsibFW2XAJIWQWQFEA//epEwg7fv3Cmuz4wZEDePgQeQJgVsZESTuswpGtOm5a43NTTQkr+eqHBy/u2mCHN7cHLvy8fBHmDRKFU1O3Iktx0U6mdiBEUAuUNVlVBk7d4tFM5WyE5HE5nxWecBBFDzd0MAJZNCrcLjl10vNF4XMSKAzAjQd71LvDZSdXN696WXAr/5jT8EUD4DaICmRLze6YYInqwVwABFACkoTC6YERSAuQE0Y968XALISwUQQLOr0VH7CiA/PYAA44gomRSzwSCaQAM0YnZ0FBYhGR2zm8hXB0dpSZmdlp1wPEsAXXutlgDKXiuPFECu06YCmAJWCrDBJsvJn36aVunWrMm9rVMp4ZttN3XQKAWsrg7aiE8iVBsaRIlYDiatCKDeXvpcfcDE3vR8rE7Bn+eEWLjuutxtTlMsuQsz8vxnFKIAckoAeZEC5rcJNOA++LWrKPGrWp9tBVC+RmygADp40NwAmiGXgudjyVcF7NgxIFlRjexy0vBwtmGZlYAHjKuA+XX+na41mR1HIgEsX258HH4ogIwUdPmgCCDCggXOCKCsT9RYpnPUeQABdM37+50TQEeOUNsJh8W9YJcIt1IAufVIZAXQu95FBNC+fXR8XoYEdggggIi6gQEan8vKrKvo6eduigBSUFCYHDAiKJJJYN06kZOxeLHx/7IPkF8KIMB5KXg/PICSSfG5L79MSxzy75QDfTspYOm0vylgiYQYwWUCCCisnicTKrJ+3QMFkKO0pMyMaumiYeBhZCuBaQigPm8VQK7TpuR24VU6mp4AcpgCVmwYGWzedRc98sFu6qCpAkieBcfjNAssK8sSQG++KVbgeaVdRk0NkVY9PaQCWrJE+74sSiw0BawQOE2x9NsDyK0CqJAqYNy9HT9OXbUb/j+fCbTb4LdopvMmyLsm4qQKGEAm0BlPL6cEEA8XZilgsl1d70gVsnGeRACZGUADxtfKr/PP59Xuve/mOJQCKFiYP5+mxbLrgRXsKoAAuvZOlGqc/tXaKkgWpwRQPhNouxgZEYqft71NqGz37TNPb9TDzm/PRwDxZ/Dixs6ddH7eeouIqeuvBz75SepDfv5zmi/q526cAjbZSsADigBSUJhc0BMU7e3AjTeK3AgA+PCHgTvuoCV7GUwA8QwQ8EcBBJQuBUx/Pr7+deAXv6CS3nw+eDStrs79XiMCaHRUpKaYKYAKIYDk/9UTQAUskYeMcjw8UAABDtKSWAG0mNrDxo3UNDZvpreXLQPwgrcKIEfHJ6MYHkAuUsCKCTsGm4XCqApYfT2ALbrZ5PHjwNSp2QCfCxy2tprz1nPmEAHU0ZFLAMnBXKEpYMWEHQKo2gWHWigB1Nubn+dPpYwVDA0Nwquipye3PHg+JJPmyoiSVQHjhZjOTmI7Vq50tcDipwfQkSPA9u302owAmj+fnmXywKwMfHk5DVnHjwPdx8Jo4khS6t+sCaDiVQHzS2wsw08PICeGw+O9Ep5X4LYsT3mtkJ2OygognvvpCKC33gIuvNC+Us2ogIEXCiA32LWLflZtLY2n8+bRAsvu3fYIILsqvY99jF4bFakw+owvf1m8fvRR4KmngLPPFn2IkUn1ZFYATTLPawWFSQ6ZoGhvB666Skv+ANRbXnUVvS+De3ZZAeS1bb5bBZAXszKz83HggPZ8mBlAA8YEkEwGmHkAjYzY/816cCRTUSFm/bzUE8AUMEfIjO6LT06hrIyCirVraTLe0JDhJPNEr5zSZQVPKmH5QQCZeQAFOAXMbzCh090t4sS6OuS29cx9wbfpG1RMzjD9i8Gkn5EPEMfNoZA73ttNCpgX8FsBpDe4zYfGRsFr5DMvlbtRmagJh0Uw48YIWv7cQFQBa2+nzuyiiyjH9aKL6G/9GGwDeYdEF1XApk2ja5ZKCSLVzFquujp3NX3aNIhITdcQNel8Bum8HLwZkXyyCbSbCkBO4FQB5AZKARQsMAFkRwGUTAqup2I0MyeTHfIzDYib+JEj9hVigCCA5PHLigDq6KAFs40bqSofQG2Bt3V05P9NZuD0r0WLaDzk0MCuD5BddRzf+0YKILufwcQxE9d6TGYCSCmAFBQmE3i23t8P3HKL8awpnaZe/aabgMsvF7N1VgDxSOS1+gdwpgBKpYQpR6EEUDJJyh8758PMABoQgboRAVRWlrssKy/LHT/urjyQPk0I8MYlNSAm0ABQXluBU0+lFLBf/ILeWrYsU9Y2jwdQ0Sph+WECPc5SwIoBDtC5G8pu019gHQHEgasVAWRlBC1bp9gtpyxDVgDZ8ZnyCkEzgQ6H6fcfPpw/DYybfzSa2/U0NVH35qaL41u1vDz3c4se/PLCg37s4YWH++/PVeNagIkKLxVAkQgRMAcOiCDXaqV/4UKRWjF1KlAWTZs2xKYmChy7ukDsUW+vpiHa8QBiU12rNl4oCikDbxdBqQI2kcvA19WNorIybalU5QUhJwSQvH5XnpKqgJmkgNkVuTN4XdKOAshMYfPNb9KDj4OJHKdgA+hFi+jZKQFkF9z+CqmayWGLGQE0mVPAlAJIQWEygQmgLVtylS4y0mmKsNatE9s4OuIBzWv/H8CZAkh2eiuUAFq3zv75sNLTWimAjCKlaFTMWt2mgVkRQB57ADW3lKES1lGiJ2oahhR1s3z30UfpOSvntZG/EovR/mYPT7w4VApYUaAngKqqMsFuHgUQT+ILJYDcBoCyB1AsBvz0p8ge34svAhs2AHff7e6zrRA0DyBApIF1dVkzaXLwqifdCjGCNvP/AYqc/pJv4QGghQde6LABzxRAUhUwQEvAzJpl3Z5kddCMGdBGuzrGLV8peKsUsNpaIUL2Ow2sGClgrAA6csQ7RZMygdZi2rRhvP56Ahs2AL//PW2rq6P+lx+cdsVpjh0d1sbCgI4AgnQTynPadNo1AeQkBcyJ/5QbyAogwD8CiPvgQgggntsZkV39/WKqPhkVQCUlgG655RYsX74ctbW1mD59Ot7//vdjm3SVxsbG8KUvfQlLlizBlClT0Nraig9/+MM4yJSdgoKCM/AEiyt+5QPPvgCaFchpT6VWAMkjbqEm0PLvzLef0xQwnsyaRUqFVgLjGZ6ci+GTB1BsQRm2YRE2RM7WTJiMJk+eIB5HB2Zj4/aabKDAK9CNjRkpc19mZltqUqQYJtAqBSwbtPNtmA1s8iiAGPIEWg8rAqiQEvBAbgrYn/9Mzx/6EPkULFsGnHyyu8+2AjfFIBJA+ZQOVuqFQro4vgZGn1tU9YOThQebsFQAJRKiA3VQBQzQrpCb+f9w2onc1qqrgY0vjmEjlqIDsw0VQICuFLzUEK0IoFCocLKiuTn/9EFW/fmpAOL7YmzMu/anUsBywQtCPKdobTVeEJo5k659MqlVnBpBMx2FxBbKjSuRyN52TjP+8xFAfqdAyigWAeSFAojH9F27qPuTwelf9fXuxrHxjpKmgD399NP43Oc+h+XLlyORSOArX/kKLrnkEmzZsgVTpkzB0NAQNm7ciK997Ws4/fTTcezYMdx000143/veh/Xr15fy0BUUxh/a28Wy86uv2vsf/axr3jxRiqnUCiDNkkuBy3JGs0uz/V5+mV57oQACaGZ25Ig/CiCvU8CqqxHDPsSS+4AlY95WX9MjmUTH2EwswjbEV+dGr1/5Cj0qy0/FNsxGbLjEpEgxPIBUCpipZ4uZAki/vxcpYG4gp4ANDQF/+AP9fe217j7PLoKoAOJUl66ukKEKh2FlYKshDjKwW1WHP7fkCiAnCw82YakAclLKLtMoOo5UomujtquvrxeVGPmcmqWdbNgAnLmqFsBGVGIY2zrLEJsj3tcMVToFUDpt7QEE0DDc0+NeARSLAeeeSxzbxz9Ow/vmzcD3vge8/e3iN954I732UwFUWUnntq+PUiS9MO0t1AQ6lfLe6jEoYAKa+yM9wmGa8m7dSgQCp4QZgW+tsrI0QqwWkk2gAWBsDJWVdCM5JYCYJzbyAEokaLhzQvIx7KQjy6rudFoQQCedRM9BVgDNmCF+3969WnUiE0CTMf0LKDEB9Chr+TP4n//5H0yfPh0bNmzAhRdeiPr6ejzxxBOafe644w6cffbZ6OjoQMyPGpoKChMRZj4DZgiFaKRZuVK7fe5c/wigZFJEFRs3Au99r/V38AgaDhd+LCtX0u89cMD4HMnn4/HHaZtTAkhvAM0otBKYEQHkpQm0rCySo8jhYX8JoJERdKEZcVgbO8RHw+hCM2JDNutK+wWvCaB02lwBNDJC94sfJGyJYDd1UD/JzQbxNhVAZgRQR4eYcHZ2Ai+8oA322DTTixSwhx+mLmLuXOC888Q+TifjdsCkjln3A4jbOpGghx1xp1sTaEBbCt5MTQI4UwDZrSyzbZt1ChhvGx6m28zp9XZ0DfsdLDzYhKUCyEkpu6oqdGA2Ft3774jrUhMfeogegDinttJOUIWubmgIIG7LRgqg48dF+zU7BXq1itN7aPduIn9CIeCrX6VKQps3U9cqVw1ymgLq9l6eMYPa55EjIsAuBIUogHgIsiJpxzPyEUAAkT5bt+b3AcoSr2VpYAzUoCIR7SAyOorKSuqInaSAJZPCq0ZWAFVXizbW3e2OADLySHzgAeBb3wKWLiXPRdkjsauLyNZQCDjhBNrGBNDhw8TdWo01TsD9dCGWAuEwHefmzeQDJBNAfE4nY/oXEDAT6L7M1Z7KwYvJPqFQCA1G6RcARkZGMCLdWf2Z3m9sbAxj+ZI4Awo+7vF6/AqlQbbdxOOI3nADkE7DyHEhDWi2pzNa5+T3v490KqVZwQjHYuCQMx2NIuFRmwz94Q+I3HwzQkzJf+tbSP/3fyN5661IX3GF8T8NDaEMQLq83JPjCP3gB4h88INAKISQRALxKz4f4Z4eRAAka2uR0n9vRQUd08BA9phCfX2IAkhVVyNpcJyR2lqEASR6epB28TvCvb2IAEhNmSI+v66OjqO72/G54XaTzgTQiYoKcVzhMKKZ8zPW3++v66ZMotlBPI7E448jfeGFxSdGUilE+/vFfZRIYGxwsLDl4ngcZRnN8lhVFUV2ZWXguG6sr8/Zsq7PGBsbQ13dKCoq0hgZMfd2KS9P43e/S+QEdE1NFOTla640uRTRbW1tCmNjSUS7uhACkG5qQqi7G8neXqTGxlBTE4I81ZkxYyznOzo6gFNPjWqMQWViBqCVXSCE8vI0xsZ0WnIbqK6m4+jrS+Puu9MAwrjmmiQSCdG/trSQWTWTGvffH8b3vhfB2WencMcd5ANj9zwxBgcjAMIoL09ibCxluA8RPnRO+/vHbDWr/v4wgAgqK80/1wxTp9L/Hj5MvavZ3Ka3l84ZX2MZDQ30GUeP0nuHDgHxuDUhHY8Dhw6NoaeH/tfoc6lLo8/p6hqzDA6N0NJCwcbKlVEcOhTCt7+dwNe/HkEiEcIf/jCG1lbpGk4/F9FZs4CDBzVjDiMdCgGzZiFx7rm2L/jQEJ2zsrLc34aBARoXIhEkdGO7HuHyciLgk9Z9GJ9TQv4FgURCe//J1zFVVUVj4fHjSI+NZUjXMtTVpVFWlsj+nzwnbmig9n30aAJjY2nNPXTbbWHce28E116bxHnnpfH5z0dRWZnGunWJ7D3005/S9198cQptbUm0tdHfe/dq23U8Tt8TDtP35IP+XjaC0b08bVoE27eHceCAve/Jh74+Ou7qavufF4kAFRVRjIyE0NU15llAX2roY6nOTrrWzc3mfdjcubTPjh3W/RwR4mVEAEGal6bTYsweHER5eR2AMIaHkwDyz1MSCboPkskyRKNpTJ2a0LSXpqYoDhwI4fDhBNra0pn/oWOx89ljY9QG5fE4GgW+9a0yvPlmGiedlEBZmWijb7xB/UsslkY0SsdSUwM0NETR2xvC9u1jWLw43/faOz62Pquryx2znfzGE06IYPPmMLZsSeLii8U17Oiga9vSYtBXZjDe4m8nxxkYAiidTuPmm2/GihUrcOqppxruE4/H8eUvfxnXXnst6kyozltuuQXf+MY3crY//vjjqB7nvZheDaWgYAcbb78dK5hYMYA+VBtuasLrf//36KyooJrbEuYNDuK0zOuRRAKP6d53g5bnn8fy73wn940DBxC55hq8/KUvoVMfjQGY0tmJdwJIhEJY68FxoKICLV/8Ipb84heokmZtyYoKbLzppuz5OHPLFrQB2NLZid267606ehSXAEj192ePafbzz2MZgK6hITxvcJznDA1hJoDNf/sbOlzkU5ywfj1OAbCvrw+vZD6/7PhxrAb5+Dzy4INIu1Dq9HV2YiqADW++iUPScb+nvBzRkRE8tXYthti10gdU9PTAYeyF6KWXYripCZs/8QnDNuMXosPDeI8ugHvigQcw5kYekUF5Xx/enXm99plnaCkrncblmW1/eeghjJgshJQK06YBP/zhE+jvNw8a6+pGAQznZLV0dopKXVZIpYBQ6H1Ip6nnGho6hLVrX8alBw+iEkBfQwMauruxbf167Fi7Fjt2TAdAbSEcTmHTprU5Fmi7dtUjHl9l+b1jY/R98Xgv1q59Jv+B6nDgwBQA78Thwyk88gh91qxZT2PtWnPlX0tLPYBVeP31JA4cWItw2P55Yuzbdy6AGdi+/VWsXWtsZEFNl1rWQw/9GQ0NxvkJR49WZa/thg0nAZiJV17ZgzvuoPyEurpRTJuWP4/syJG5AE7Hli1Hcfnl5nObF16YD2AJBgYOYu3aDZr3OjvnADgDW7cextq1L2HXLjpX+fDss8/h1VenAViM48f3Y+3aTTn7VFevxtBQGf74x6fR2upczbdnTx0OHboI5eUJnHDCo5g79wLs3NmI5557BStWHNRcw5brrsPy73wndyEGANJpvPyhD6Hzscdsf/fGjTEAS3Hs2BGsXfui9ncdPoyLASSj0bxj5pydO21/57PPPpd5tcrWvp2dIr+uo6MVwHLs3NmDQ3W9aAWw5eWXsWfaNGze3ARgBWprB7B27V9zPuuJJ57A8PBZAGbhuee2oLFRm4Oyc+fZAFpQU/M62tr2Yv78t2H37gbceutOXHPNdiQSIfzsZ5cAiGDp0vVYu7YTx4/PA3AaXnrpMNaufTn7WYcOrQDQhDfe2Ii1a+2n5FnB6F5OpZYDaMVTT21BdXXhOTWHDr0DQA3eeON5APaLQlRVXYqRkUo8/PCzmDvXpT9hQMH9zYYNpwGYh97eHVi71rgkVjxOfdDzzx/C2rXm1iN799YBuAihNEm+EuFw9h57bzSKcCKBvz76KI4ceTuAedi3bzfKyuZjbMycBCorS+K1155Ed3clgAvR2DiMxx57QrfPKgD1ePTRl3D4MKmgnfSF8r3ISKWAKVPejcHBctx559+wcGFv9r0nnqD+pbHxKNaufT67ferUt6G3twH3378Bb7112PJ7jx6tQlnZOyx/ezSaRCIRQXl5Ak8+mdtX2fkMPn/h8FwAJ+Ivf+nACSeIwf/555cAmI+hoZ1Yu3ar5TGPl/h7yIE9QGAIoOuvvx6vvfYann32WcP3x8bG8MEPfhCpVAo//vGPTT/nX/7lX3DzzTdn/+7v78fs2bNxySWXmJJGQcfY2BieeOIJXHzxxSjzM+VCYUKB281yK9MLCcnPfAbpNWtQtmIFlkYiWGqwTyiVytbhrpgyBatXry7sIJNJRD/3Ofps/XeBVkCX//a3SHz967mqji1bAADR6urCj4OxejXw9a8j8eyzCD38MCK3347IggVY+q1vZc9HJNP/nHz++ThJ/72ZqluR0VGsvuQSIBpFOJO83TxnjuFxRu69F1i/HqfNnYtTXfyO8N/+BgBoO/lktPL/p1JIf/jDCKXTePc555gbKBiA201DJg/kzLe9Del3vEMcb00NMDKCVeecA5xyiuPjtY09e7AZdzj+t8qeHiz/7neR/N//NVePeY0MwZqOREhBlkjg4vPPtzacyYddu+gzp0zB6ssuy25OV1cjNDSEd5x3nnUt5iKD2821167wfZyqqxPy8EWLZmL1u9+NaEYxVnf66cCuXVjU2ooTVq9GQ0MI3/427dvaGsJ735t7j23K5QBMMWNGvaP+pqODVAAsBuMJ68KFaZxzzko0NZmbpicSwNe+lsbgYBnmzl0Nk7UxS/zgB/R955xzGlavXmK6H5dGvuCCd2a9kPS/Q6+SAoCHHlqIhx5amP2M119P5DWBj8dD+MlPgHCYKF6zuc0rr5D5yKJFrVi9Wks2j4yE8OMfA9HoDKxevdr2NVyx4gIcOUKfe8ops7B6dW5uUVNTFENDwBlnrMJZZzlXYXz72/T5l1wSxhVXXIonnwxj504gmVyG1avP0O68ejWSy5YhcvPNwpQCANrakPzBD7D0iisMx2Iz7N9P3z1r1vTcdpqp3xyxMWaGurvxGl6w9Z0rVlxg+/hWrLgAS6UfVFkZwve/D6RSTZg5fz46nt+PkYrz0NKyGq+9Rm1t+vQpaGmh4yXVjJgTP/RQJf72N2DWrMVYvVrrov4v/0Jj2OWXL8bFF5+CvXtD+MIXgEceOQmf+tRCPP98CL29UTQ1pfHe9y7FzJlLkUyG8POfA6OjMzXn6Nvfpvvo3HOXYfVq/xx3H3kkjOefB5qbc3+PG6RSdA4uueRcnH66/f+bPj2K3l5gyZKVWLmyiA7DPkIfS/3P/9A1veCCE7B6tXEuaioVwi9/CQwNtVreMxs2UFutmVIG9GvnpaGKCiCRwNtXrsSfXo3hsceAk06ajxkzgJ//HDjppBR+9askXn45hM9/Porm5jQefjiRSb26CPffT599wgmVOcdw220R7N0LzJ9/drZdOukLl5p0LitXRvDoo0AksgKrVwvVzDPPhDP/26Q5ll/9KoLdu4Hm5uWa/c1w0UUp3HhjCH/6Uxgf/WgSn/lMCp/6VASvvBLGhz6UxJVXprFmDTB9esT0vF90UQrd3ebfRWPrRQiHQ7j/fiAen4PVq8WcjK//hRcuwOrVxnOp8RZ/9zsoJhMIAujzn/88/vjHP+KZZ55Bm8GEeWxsDFdffTX27NmDv/71r5ZETkVFBSoMknTLysrGxcWzwkT4DQrFR8RmEBq5+mpg1SrrnaQE2lAkUnh7fO457aRXh1A6Dezfj7IXXsg9tkx6TCiZRNlzz5E/jxepP2VlwDvfCSxZAtx+O0Jbt6JscDDHHTRqVD5E8gUqGx2lfIKMCUC4pgZho/OV+dzI0BAibs5nxiQhUl+v/f+MO2ZZf7916SMThDKfG62v1/7OTNpXWSLhuwm0G4TSaSAUQvSf/gm48sripINlzlWoro6Wz/r6UDZWoEl2pt2Eamu191l1NaU/jo76e/5dohjjFBulApRCUjY8nO0PwhmnzgOHK9C1uUxTaaqxMYTNm+nYZF8DJwUNKyvDKCuz54pKpImxD8jOnSGcc05Z1kPFiDQpKwOWLweeegpYv77MdLJuBf7u2tqoZXPhriqRKDPcr6/PTmnhEPr6jP9fBqcbHD1K59GszbDPUEND7jln8WF3N71n9xpGo2XZ7NLGxgjKynL7h4YGqrozMGB9zszw8MP0fMUVdGznnAP85CfAhg3G3wcee/lHffzjCP3sZ4i66LtEkS+Ddpp5M1RZmf8edZBeGo3aP0nRqLZ98E/u6Qlhf3o2mf7fUQWZ+9+0KYxzzqHfUlkpVDNlZWVoaqLt/f3ac5tKCVPaRYui6OwE/uVf6O/e3hBWrRIH0d0dwooVdC+yOXtHh/b8cWbFlCnu2oRd8L3R3W3SVhyC48GpU/PflzJ4uuP2HggyuL9h35uWFvNzfeKJ9Lx7dwjRaFm2GpwefN+VR4mECZWXi3usvBwdg1PR9Xo5+vvpezZvjuDJJ+ntT30qjJaWMD75SeCLXyRz/Orqsqw/GqtlY7Hce5r9cXp7xXXi6mX5/KdmzjRvE+efDzz6KPDiixHcdJM4Nzt20PPJJ2vPGR9rR4e9drtggfBVuvLKCM4+O4L/+A/gPe8BHnwwgve8h95ragqZ9lULFlh7yDF4nXLHDu35E+c1/zGPl/jbyTGW1Ns9nU7j+uuvR3t7O/76179insFqJpM/O3bswJ///Gc0FWIHrqAwCZFesYKUCGYjVyhEBIHe8NkIc+eK116UgXdbBaW9ndQ6ALk/XnQRHVt7e+HHxJgxgwivdJocYRlcbsTIBFou+8lRRr5yOX6YQAOFVwIzKAMPIKdSi29w4pKoh4vyyQVBdtrk81WoETRfV/2Ch6oEpjElra+HaOPV1cC0aWRee/fXcOaZFFszNm8GzjyTHosWCWNnJ3BiCmzLGDduXbmKMxmff958HyvYqQImv1+MZiWqgFnvZ6cKWCFl4M3MbQupBLZvH9UwCIUAFu6dfTY9r1+fW4o4C7kEW2ura+KazWgN4wAnTsZ++rtJ4AC2uxs4mrZh+h/XXnOzkuUHD9K+kQiRq3bvRa7y19WlvRf41PlZBQwQ98Zh6ywaW0gkxG9wmgAx0UvBA8IEmk3pjcBhaX+/daW5bPuIZhaupIbSEZ6LRdiGM6+ci7vuom2PPCLa4xe+QOPR4cNinVPO+jQqAc+Q7x8GGztv2ABckBHnfeUr9Dc/zBYdGOefT88ZgXkW+hLwDKeVwHp7yVwbAM45h54XL6Yp98AAGbIDdBo3bqSHm/EaECTegQNaa8nJXgWspATQ5z73Odx999245557UFtbi0OHDuHQoUMYzgyEiUQCV111FdavX4/f/va3SCaT2X1GndbQU1CYrIhEgNtvp9d6Eoj/vu02exPO2lpRYWpwkJamXSo1ADgrv87gimby0j5AvflVV3lLAvEo+NxzYhvPAsz8V/SVwOwSQA6kmxrkI4B67Of9a2B23G5qRrtBvtm6HTgon1wQ/CCAzKLfYhFwAYYczNTXQzAJzc1AbS2Z16bym9fmIyCM4LYMvFsUSgBxM7FLAPl9WwMi4OrtDWW9lYxgpwrYsWOWXsaGYGLHLChmYshN8PvHP9Lz+eeLYH7RIrqNh4ZE0JMDOTIp4CKwUsWQqOA+NUAEkFzKeiDs3NSe12H0wXkmgxZz5zoTStbWii5XDjg55HBbBdAuWBHF05uODhEAGz2sgmK5STmtFzCZCCAro/fqajH9tKoElq0CFs10RlKj64rMsEVsdnUBl15Kf3OxWcCaADIjwmMxqmLH079Vq+hvfuRL0z37bLId7OgQRMnYmDgHhRJAL71Ez/Pn03jQ0UFV79h6jL/n5ZcLX7SZOlUQZaxgSiaBQ4fo9WStAlZSAujOO+9EX18fVq1ahZaWluzjvvvuAwDs378ff/zjH7F//36cccYZmn3+pqclFRQUzLFmDXD//bk9XVsbbV+zxt7ntLcLwuHQocKVN1x+3a46KZkEbrzRuFQ7b7vppsJIKRm8fML9TTotZkRGCiDAOQHEUUiQFECplIgc9UbGTEAUgQBqRhcqQ9ZKoEoMoxkmkbyD8skFQZYUeK0AMiOAvCg1P05hqgBqavK9MprfAaAe555Lz2++6Y7LdaoAKgYB1Ngo1huOHzc/oWYiOEB0b6mU8yCViaV8CiA3we+DD9Lz5ZeLbZEIcNZZ9JoDnxzI0XoB5HepFEBc9twKleHRnJLOVVWiS+tLO683bnatmACykyIiIxQSwbEcbJZCAdTRQUEvB8BGD6ugmNt5RYXzfmuiE0AjI2LYzlfpL5NVbI8AinAumNRQHDCQl1xCz888I6ZgGRtJQ0tBq2leOg3s3UuvndoF1taSCwIgFh927SKidsqU3FBCJoCMpud6vJjxp+fxzQu1rBVYBbR9Oz0fOUJhQjgsSNfJhpKngBk9PvrRjwIA5s6da7rPqnxeJQoKClqsWUOjwZNPAvfcQ8979jgjf666KrccbSHKG6fqpHXrxGhoBK9Tf1gB9OKLQk/Nv9+uAohH8WKngLFSywUBFBkdFWWJzRRAfitQ4nHEsA/bTrlCI13esAHY8FISG6a/GxtwJrZhEWLQVTdyktboBWSpglcEjdl1VSlgmsC9rg45CiA/UWwCaNo04IQT6DVPmp0giARQOCxWZPv6zCNqKwVQebm41F1dNgmIStovXwoYb3eaAtbXR6JYAHj/+7XvcRqY3wSQpQLICQFUWUkEPKyPhc+pnHaS8/jX/8MGLMO2d37OUHnAQWxv2nmhFjMFECsJnBJAALIm6KVWANkOih9dD9x7b44i2+r+yYdC0iDHA45SwSxEo+ZTOQYTQEwqGiHbPqKZHE+XBNBJJxHRMzIiprFuFEAAkYjDw9Tf5lP8GIGnv0wAyelf+uk6u0P099tbqGBXBSaA/AYrlvg3sKpp5kxv3CzGIybpz1ZQmKSIRPIbPRshn/ImFCLlzeWXO/cuYHXSjTdqyZ1Zs4gckgkqt55BbnHKKcJx9rXXxOwsEslVxjDMFEBMDOjhdwqYGwJInnXqj7vIKWCxul7ElunfjAB3fpKIRyBTMzkDp2mNXkCeaXMEVihBYyZ/UClguQqgA4UpgJg8sAq2olHigItNAAGUBrZjB03E3/1uZ//Lt6lZ98MoJgEEELF1+DDQ329+QvMFsE1NdJt0d9M52raNTERff52e//QnmuD/6U+0PxMVdj2A8qkfOjq0K9KPPUa3/9y5dFwdHSLwckQAFXARvFQAxbAP2+qXo+uvm013k83UYzGTQPOZfQA2AU0naTbz+eO293qX86X4fClgUt0K2+Df8NZbYluxFUDHjzvgAT/1DwAypZ/a2rLzJisPrXyY6AogJoCmTSOCxArOFEC5HkBOGIZQiNLAfvlL6k/e/nYxnXVKAHE6Vlubu3oR550H3HmnEMCb+f8AdA+3tNCx7tkjjssI6bRYzGD/H7+hVwAdPEjPk9X/ByixAkhBQWGcwG/lDauT/vxnMRo/80yuOsmNZ1AhCIeFCcff/qY1gDZLW5sAKWBRnu1WV+fOjoptAm22rO9VWqMXKIUHkEoBE68LVAAZqRcWL6b3vvxl+vsf/oH+LrYHEODeByiVErdRkBRAgOwD5E4BBOR2cVVVwBtv0OtbbqHnQ4do8i/7XrgxgdZ7sfzpT6TMktNx/vVfad+9e3PTc5gA2rzZpOsspgLITiPONIjYyE6Nd4j+YUtZYCBDk9ObOCj73hM5TH9eeJ0CBpRWAVRXJ77DlX2fpMj2QgE0UQkgO/4/DEcEUNiAACpzprXgNLDHHyeiIp2mjzMyq7ZDADlN/2KwAmjDBuqSrAgg+Xvy+QDt2kXHW1EBnHGGu2NzCjMF0GT1/wEUAaSgoGAHxVDeRCLAO94hZl9GhJNTzyAvIBtB5zOABtybQPtFALmYRWYVQEbHXGwTaKsZNxOH111Hf19+ubO0Rq/gZxUwlQKWBQfhcqy8fz+w8c1qbMRSdETnu04BY9NMfnzkI7T9xRfpb46ZS6UA4mNxYm8m8wiFEkBOUqzsgAOvQhVAgAh+Hn2UgqWlS8m/YuZM2r5li/ifdDr/5+pNoI28WC67TAR9ZpA9K2bNonWJZBJ45RWDnYPqARSP2zP1sAI3KqkB2UlvsgNWAPX3i3sjnS4sBUyvAEqni6cACoXEveGKAJK8EI/30QlxQwAVYoQ+HuCEAOI2ZI8AMkgBizqT37zzndQO3nhDKGVmzTJWKvlJALFB89gYjbteEUCc/rV0qf/3E0NWAKXTigACFAGkoKBgB8VU3jABJOuvGbJnkB5+pf7IRtD5DKAB5x5APDsrNAVMn5JWiAIoSARQvqgzEqGIjPctVtqXDD9NoFUKGABtEP6jH4ntV10FnPl//4ozsRGLfvh5dBy3uDcdgLMLn36aggUnsTPDK9Lk1FPp9j5+XEtm5IN8ixZKAMkqqWuvpW3XXeestLAMXs3u78+vADLj9PQlkDnVa/VqemYV1+uvi/8ZHhal2O2mgHlBVoRCedLAPE4B87QKGDd+t+Dv9aCyWGWlNr1EXovhbrinR7xm9YaTe1FvAp1MCl7FTwKYCW4eyl991d7/bcVJ2Iil4pE+Ax37gP71VPJIKYBy4UYB1NGRa4HJyBKETADJDKxDk5mpU4Hly+n1f/83PRulfwHiXhgYyCWkCyWAQiFtOfg336TXXhFAxfL/ASgVNBSiMeXwYZUCBigPIAUFBTtg5c2BA8argaEQve+F8saKAAJE6s/VV2uXw9vaiPzxWv1x9tlEKnR0kH4fcKcAyucB5EYBNDIiZiRemkDzhN3I56hYBIRdAggQkaDbEhGFopgm0JM0BcyWIWoiiq54Tca8dtiy9G4+4mXePKrctH498Ic/OIudGUyaWDVLOeA0QyRC3dBf/0ppYFydJR+YRygry8+L2uF12eOFm96555I6yg1ECpjxCR0ZEQFNPgVQVxeROo89Rn+/5z30fOqpwF/+ItLCAEEMhMPmNm5+GeAuX05VwvISQB6kgHlaBWx4uLDcR7tO5Aa4+27g5JPF383NtM7EpF5ZGXHug4Mk0J06VaR/tbaK7tLJvchrSfv20RRD5r/8UiwwwS1f+ltvtfe/1+GenG2VGMY/7yIZ1ETyANL7bulhpz8FnBFAM2cKj7i33jL2lbJSADVPGXI8Hl16KfUTXA7ejABqaKC+LJWiqZ68BlsoAQQQAfTgg8DDD4upJKtp9LBLAOkrgBUDFRXkzbZnD6mAlAJIEUAKCgp2wMqbq66i2ZFMAnmtvMlHAAHAe98rjuFHPyKz5pUr/VF/1NQAp58ujB8AZwoguylgvDTtZLVIJo28VADxjLeUCiAnfhWFlLz3AkYpYIUSZGbyh0mcAmYLbF6LReh6fJOpG6WdQOGqq4gAuv9+kU7kNA42NcZ1iPPOEwQQ+xHlg5O428lt7UVgIRRAxmSE3LWZBbDybf/88xSsNjUJpQ0rgIwIoLo680xiv9JfbCuALAigfAEwZykXXAUsGhWR5fCw9ZiXDwUQQCefnEsy6lUYDQ00zPL1Mkv/snsvtrTQVCKRIA8pee3GLwWQVylxjDiqcDhBi0ATRQFkRJLpUVlpT4nohAAKhUgFtGULpYFZEkChXBOuWF0fjUf//kPgfe8z/A698oynwTzNLSujKah+33CYbs3ubn8IIE4/fvppep4923wqa8craXhYpMDKBtB2CjE4STE2woknKgJIhiKAFBQU7MGsWpfXyhs7BNC+fTQxrawEPv3p/GUcCsX559Poy9pVPwgggKIeJxNtjpKqqnKJI9kDiCu12USEJ+xBSAGzM+MOkgLIbw+gSZoCZhsZaUdsYB9i844BCy3KkeTBBz5AJtBPPglceCFtK4UHEODOCJqbiJcEUDotAgue8LuB8AAyllTwLTVlijmvLxNAzM2/611if6MUMDvGuH4Fv2edRc9sgqrhJm2kgNkJgHkoLFgBFApRoxgcLLyvd6LmdIHGRgromPwqpAIYQENpWxtNQd56S7TzcHh8lYwerCU2oNAy8A6nD77Blgo047vlJQEEaAkgI2RNwsMGLuzl5YhhH2Kth4A8ikmze/xXv6IHkEtyNTUJAoiRSIgURrcEUEcH9aWRiBDbt7QYE1Hy97z1Fk3PjablGzfSsc2YIab6gHdqWSssWkQq0W3bVAoYoAggBQUFJ1izhox2160jw+eWFu+VN3YIIB6F583zn/wByAfohz+kUQ3w1gS6vJwm5CMj7gkgoyVyji5GR+kYzPIdDGCpAApyCliQFEB+ewBNshQwR6itpfvPrbF6BvPnk/pg40axAloqAojl8tu2EafLGZ5W8EMB1N0tTuvcufk/Vw9WsHCwfvRoFTZtEoE1T/LtEDXybc8GpZz+BQgC6MABInMaGvJXAANE9378uOjyvUBjI61Cb98OvPwykVVZ2FAA2QmA+XgPHTII1JyoKgHvCKACFEB2wNdLTwC5MYBmxGI0BenoIDIIKJ5hrRXuvpueue6BFYaGaW5UCAGUTDqePowLOCWA8hlBCwWQgQkXs7H5XOPhjuQyEkDv30/XrqLCnTWnGRH10ktay0WZiGpro358dJQIFr5vZMjpX3pS0Su1rBk4de3VV0VfoRRACgoKCnYRiQCrVvn3+XINVrOlJx6FC1mCdgJ2wmPYVQCl0/lNoAEKWJkAcgIrAqi6miYho6M0M3Awg7P0AAqaCTQgZkDDw3S+zfyW/AJHq36YQKsUMOeorSWCukACqKNDiP8sA2ufwaRJLEav774bWLFCvG92HHyL2rkd7N7WrP5paXEu6DAKKrq6qjWpABxU2CGA+LbfvJm6uHCYvDMY9fUUhOzfT2lgF1xgjwDi9+SKYV7h7LOJAHrpJecEkBP8x3/QA5ACNadO5l719T4TQDwcs2LLCwJozhxa53rrLRHwlor8lSH7IeUDNyk3BFBVFfEWY2N0Xic7AcRTTW5bemQJIBgrgACYO0gXCCMCiPvpOXPcrZG6IaIiEXq9ezd9vxEBxCJ6uc8vFti8+tln6bm62nocmOhQBJCCgkKwwG53w8PA0aPGI3SxCaBYjJYKOHH4yBFaXjFSPskEkDxxtorC6upoJHUabfAMz4gACoVoZtDZSTMDWW+bB+POA6i2VsxWu7uLTwDJxiJeKXTMPIBUClh+FGKsnoHZCui//Rs9APt+E4XA6DhuvFG7T3k50N6eu9LLIkovFUCF+Eo4CSqsKoAxIcZBHAc+S5YAe/dSt8jX5NRTnRNAFRXCj6KQNDC9Z0VHh7hGTzxBpeSzODgTzZiNGPZ53rdmAzWnTuZyKfhCDwDQ9OVeen4wAcSr+uwB5DYFDND6sVhWVgsweAhyYwIdCtE90tVF94BRMD9ekU67J4DMFEDZKmDsASTnYHLDsaEAcgOjDHgv/H/cYN48QQAZ1YQpRQUwBiuAuHttbQ1GamOpoAggBQWFYIE1q52dFMEEgQBqb6e8C8attwK/+x0ZY+u9j2QCSCYBrEgJtwGrlQIIEASQfOw2kFUABSEFzK5fRVMTyTO6usxLZvgBWSZQTA8glQJmDg8IIC/9JgqBneMYHdWRCRlwDOIHAeR312uWAWnlg/Pqq6TWkIm5xYuBRx8VRtB2lEUABb/xOBFGzc0iS9cMRiSc3thVPu5nnxXKEsKdqMQwtmERYvEj1gfnFgFSABl6fsTjwAUZte3Tz6B5bo2te0v2bBocpGEAKFwBBNAUxOlpCwp4iHCjAALovDIBNJEwMCDuQzajzweZADISpgsFkAFb6DMBZKUAKgUBJH+/bFp/9CjZd4ZClCq2cWPxVLQAkZhVVaI7mszpX4AigBQUFIKIOXMEAbR8ee77xSSA2tupHJBc+QwgNdBVV5ExtkwCGRFAlZXWPkkcsDpVANkhgADH3jjR8ZYCBtBM4tCh4vsADQ6KtuFVFbBEQvx+/ex9kqaAOVIMeEAATQRwxsHYmEhbA4wn3cwr5rutZfs1P5FD1CSTwLp16PpbHPH4u0z/D9ASc3ojaDsKIICC38OHKfg9/XTg5puBW26h4egnP8ndP18gY4tQRBW60IzYyD5/nHedMhnc9/qUApbj+ZGuALCJXi8aBGbYyzuSFUDcPhsbCytcNpEUQIUQQMDEI4BY/VNdbZ2Zz+joEOegv5+KAsg2kM3NMgHEUiB3HkBuEFQCyIysT6dFUYViqGgZ4TBwwgnAa6/R34oAUlBQUAga5swhraiZEXSxCKBkkvIt9OQPICboN91ExthM8MgEkB3/H0DM0PxQAAGOSRFLBVBQCSD+rcWuBMaRajisnVEWotCxqoE9SVPATKuEPPII8NWvAMvPRvP9P6GJpCKANHjxRa3aRJ508wptZye9d/SoNVlUrMBCQwC1t0vVJ5cCsCaAZJx6Kj2zAsgJASTv/5e/0PPHPpZbltwXxOPee+aUWgGUry/nymPs5WYTMlHhRfoXoCWAiqEAcpoSZ2dfszUEu2ioTwMIofeR54GaEe8LfviErVtztzU3C3Xe0aNErNpJ/zIiMd7xDu0+lZXAu99NryvSBgRQCT2Aik0AyUqpoKhoATHOydecVUhAcZVIQYEigBQUFIIHq0pgx46JZH+/R7d167Ql7/VIp0nTum6dMMY2UgDl86TxKwWMSwW5VQAFIQXMiQIIKB0BVFdHAYwXBBB/ZkVFbj3n8ZICllFseFkt0LBKyLM7AGwC5p0A8HuKALIET7qB3OBm0yZzsggoAQF0dJexAtMm2DT38GH6zXYJIH6/t5eCh5deotv7iitcHYZz+EkAOakCBnhXBt7O76mupu9z8J2yAsgLA2hAtPe+PiJFAX8VQE7LYGf3/frXgYf+iCTCWF35JLritfjud4FrrgGWLqV9nRJAHR1A1+/+ivSzUQAXYvOPn8bGH/8OmD4D+Od/RvPVby9JsGyHJAOMK6RVVgoVoBP/H7skBtsxllsRQBNYAcQEC3cx27YZE3GlgJkS6de/pgdQXCVSUKAIIAUFheDBigDikW3GDHv63ULAy+JO9jMigOwqgAKSAhYJkgm03WXXUpWC10eUXhA0Vtd1PKSAaRQbGbS1GXtmFQq+3tzWAUUA2YTTFdpkUnTJfosvswTQs2tdkz8Adcdz55I59Btv2PcAklUl7e30esUKYOZM14fiDAYXZupUIqFcn45SK4DsEkDd3a4VQF4RQDU1dL57eoAdO2ib3x5ATspgZ/ct2wxOm/vkvL/glq3vx1NPAf/0T9ZG6mbo6AAWLUwiPvb27Lbv4sv4Lr4MHAHwz0DlvyaxbWek6MEyk2R/+hPw2c/SkP/oo8CbbxqTPjLicTFUMKFn1wDaDljckyWA5IUbBylgbszR9dO84WExJS0GAWREsBw5kv+aFAtBUiIFCYoAUlBQCB6sCKBi+v/oy+rY2U8mgHhZKB8B5KcJNODeBHo8eQCVOgWMI0qZoHHr42HmgAsEPgUs9Ic/AB/8oH3PrELB11ueESsCyBccPEiBTlmZ//4J2eD1+IGCP+vUUwUB5CYF7PHH6fWVVxZ8KHmxFSfRi5eTQJtW9fHii3RbVVcDf/wjKV+2bnUQaJWqCpgTAsjF+CIrgLxKAQNoGiITQIH0AOIGDeCjTQ/hFrwfjz5K06REgrY7UQB1HU4iPmat1IyPRdB1OIlYrPjpYLEY3csA8J73kFrR6RDrJAXMLnIIIJcKIKdKMCCXAOJpc22tEIE7hRMiyg7BohA8KAJIQUEheAgKAbRyJSkXDhwwXnYNheh9ud6lTJqw1jgfAcTvb9wIPPWU/XQZv0ygrRRAQU8BK7YCyIwASqfdp3FYLd3y+R8bE9F4UJBMInLzzc48swqFUgAVDdz1xmLuLp+ToCLLgcKhKtIAixcDDz9MKSBOU8C2bgWee45eey1eM8J1uIdeXE5PXF1s2jRSdQDA//t/ZGYaizlUDJTKBNpJX+5ifJEJIA7EC1UAAXR+N20qngLIFSQC6MTR13HBBdRef/QjsYvROo4pNm0CcJa9/Zbb2M8HPPEEPV98sbv/90MBlDWBTmfaegEeQE6UYIB2nS+V0qZ/ufWRd0JEFXvNTcEbKAJIQUEheGACqLeXgmF5CatYZWgAinJuv52UC3rtPY+st92mjYaqqsS+dgig9nbgv/6LXv/5z/Swmy7DUZLZDM+tBxBP+K1SwEZGaLYRDjv6bNsYrwog2e9pcNAdAWQnBQygIClfJFtENG3ZgtABC8WGkWdWoeDr7TEB5EaK7wfs+l4UA4X6SuiDirGxMaxaBcTjZbj3XuDEE0VQkb2tPCCAZCNo2wqguhSAMP5wfwLpdBTnnJ3G7NkeV+WygdFR4LLLtNt++lPgrruEZ4VtxUApUsASCSFFcaIAcpECduyYELt6QQDxNGS8KIDQ24vLP0EE0M9+Rpuqq4FXXhG75DW7tTt+lijqP3o0w1EBeOc73X3GkSPeK4C4iZenLAggnz2AUilqDtxPz51b2Oc6JaIUxhcUAaSgoBA81NbSst6xY6QCWrJEvFdMBRBAJMz99xt7mtx2Wy5JEwoRIXP8ODmPAuYm0E5LzOvhtweQVQoYQFFpPoNrt3BqWBoUBVAkIiL2wUF3DIHVdS0vJ9ItlQocAVTJ5uz5YNdbyw74enucAuZGiu8HzI6js5O6Bp9iCkN4YSwqBxVjY8CCBX14441mjI1pq2tlb6umcqBHkO/N6EIlhhGHOZmgJ+a4FPwbb1DlF8A8LYYNcPu/sxXA5xAfo384d8svsfH7810b4HpN5MmeFbYDtVIQQPL/2vUAcvidrACSeSa72dtW4HPKw3jQFUAd3VPwta/Ra7agGxqyNnXPgd3xym/m2wRcje+008gG0g189QBKGhBAPpeBr6igdaHBQRoOS1UBTGF8QRFACgoKwcScOcEggACKtC6/3H5VIz0BZKSkcVNiXg+/PYCsFEAAzS79IoCc+lWUSgFkJCmorhYEkBtYeQCFQvT5ssl4QBDnSCwfvIjOGD4pgIDgrICaHceOHbnN3ZEnjENwYOFl1ztnTj/eeKMZr72m3Z4lgG74KPD1X2W3x7AP27AIXZhGG773PeDtb9f8r56YO+kk4ky7u4Vw04g31Rrgaj/z9oFP4PYCDHCNiDw/r5UhSlEFTGa87PTlLhRAU6bQEJlM0t8LFrhPfZHBCiBG0BVAXX1RjCSsd89rdsulw/Jga9VSYKP4u1hltAtN/wL8UQAxAVSRytwrRSwDD9DwNx4JoGKoaBWMoQggBQWFYGLOHNIuyz5AxSxDo0ckYj9thZUzVgSQmxLzetglgI4do3Nn07jDsgx8JEITmtFRf42gx6sHEEDnrafHPUGTr3zLlClEAAXMCLr7lFOQnjULoYMH7XtmFfyl/iiAxgOMiCGn5p1O4Ef27dy51NZNCaDLLgTm/A/w0Y9m34thH2KzkVFgaokaI1RVESmwY4dolkYEkN8GuCUnFEupAKqosJcu7EIBFAqRCojbsxfpX0DutQqcAmhkRFxTQEigCoHNOcJ1H9buV4wy2um0NwSQEwWQ3f40laLX5clMu5W9+XxOAQNoqtfREWwC6O67gZNP1m4rFnGokAtFACkoKAQTRkbQ+/fTJKe8HGhtLc1x2QETQFYeQG5KzOuRjwBiD6B0mvyUZJWEGZJJRHilysxbqKoqeAQQ/7bBQTouN947bmBGAAHuCZp81zWolcAiESRvvRXRD34w9z0zz6xCMDQk2qAygQbgPHXNic+RH4FFPgKothaU78EoK6OyXHaN8jNYvFh4uQAmKWDjwAC3IPhRBSyZtFbGOqkABrju2xoaRJv3ogIYkBuYBk4BJPv/RCJAsnSHUowy2tu305pYebl2DcEuSdPURNn1TgggfX/6xS9SGtrNNwMf+pD4fvYjMvQA8jkFDNBm+weVADr5ZG2ab7EQFD+/oEERQAoKCsGEEQHES9Bz53oXRPoBOwogNyXm9eAy82ZEQThME+/hYWDtWuDaa/OfN1m1YmZeXV1Nk08/CQin6Qr19SIPoLublCbFgBUB5EcKGCCCpIClgAFA+ooryLvqmmu0K9JmnlmFgNU/ZWXae4DPG1+bSQa7ShN9cJNKARddRN0Kr9YyWRSPUxl4wNvAYvbsfoRCaRw6FMKRIxSUpVKia6urA7ClQ/zD2Bhw/vmO+//Fi4EHHqDX1dXCC0iDgBvgFgyvq4C1txt748kFDJwSQC5VR3L2qVcKoOnT6VQ5PW1FQ28vPdfW0sF50CyDZDqvB6t/VqzQZp7r+7GuLuDSS2nN4dlnRXDf0gL87W/lSKVoMcJuwC/3p2edRQTQyIiWzOA2Up7IzImKaAINiN+yezcJvoHiEUBBJ1iC4ucXNCgCSEFBIZiwIoCKnf7lFEwA8Yhj5JPjpsS8jHTaWinCk3OeSH/4w8C//mv+6mIZUiEdDiNkNuP1IjXACsmklFRvc9YdCtEofvjwxCGArFLAgOApgBjvfrcw5ADoePfs8Z60lf1/ZNMPPm9DQ45SHycj9GTRhRcSV9zdrQ1wuBuuqfF2Il9VlcSCBcDOnaQCeuc76bbhLrGuDpTbIKOvj+qiOwBXAgMsfNMDboBbMLxMAbNbwMCpktOhAqijg7oB+RZPpYCNGX+aQgK7cBiYPZvaJhBgBVB9PZ1fDwggTbD8la8Ajz6CrTgJ1+Gewj+8QFilf8n9WDpNQ0J3N50W7sfGxoC+Pmr7U6dqs7TsgtVlu3Zpt2fLwFsRQD57AAHA+vX03NxsLuD2GuOBYCl5+m0A4VP9XgUFBYUCMREIIJ4cm3np3H47vdY7VtpJl4nHRZCtJwp4cq73GOLJeXu7+bHz0vuUKeZOmn4TQLKvgd3AASiNETQTQHJUWSgBlM8DKKgpYIzXX6e2z+dkcFC0Ky9h5P8DaM+bH987gXHBBfT83HPa7bL/jxcGuzJOPZX6SU4D4+YfjWZufz0BxMoHm+jo0B5zRQURBPzIfrxNA1zb++UBr5wXBem0dwRQvgIGABUwSCbdK4Bs9G0dHcCiRVTl6oUXxPbrr6dtZ55J7+ubjxPIRtCBUwDJBJBdA34biMWINFlWtRXLsAkn403PPtstxsaAJ5+k1/n8f0IhUTdk82bte729RMY45I+zYHUZk4IMWwRQEVLAmAAqdvpXts2YPBT5EjwoAkhBQSGY4JnXoUNiFXG8EUAMs1QqLjE/a5Z2e1ub/RLw+s93Mjk3ApMWVstHfhMQspbYSYRUCiNonoTLCqBCU7TGqwcQY9Mmej7nHOFDVUgUZgajCmAARWqc4zMJfYAKgUwAyV2In74Sp51mTADV1WWIGyMFkE0wSSDbUu3dKwgCDUlgVynmkaKMV843fPaX2IBl2PD+b2HDe/4ND2M1yiPWhr6OUypk9UGhVcCcFDBw6wFkY3Ghuzt/qhJ707iFHLgGWgHU0OD95/vp8WcDHR2CpP3Nb6grr6sTCi+rIYUVf6+/rt3OCiC3FcBYAbR3rzbDmbmdikRmzC+RB9ChQ/QcNP8fheBBpYApKCgEE83Nwr9m3z7ghBMmHgEEiBLz738/8PDDwEc+Avzyl/mDDA5sa2q01VUKrC4WYlLB6pj9VgDxMXASv13D11IqgIrpAVTo5/uNV16h5zPOIMfNnh5S8vGyrFcwUwCFQkSeHTumCCCHWL6cuLMDByjAYh7eTwJoyRJzAghAQQqgri7/SYJCEIsBsfpdADYBc9+W6fsewY4bf4SuD91o+n+OUypkVWWhCiAnBQz4u3xKAfMb40YBVFODZryJymgC8YR5aOeIOCwhAcTErf7e7e8Hzj6bXltVHjNTABVKAM2aJXyhOjrEVDSrACphFTAZigBSyAdFACkoKAQToRDNvt58k4LH8UQA6ZUbRh5AMiIR4LzziAAKheyRHWYqkUKri3HKjNUx+0kAtbcDn/scvU6nyZVWbyxqhlIogFQVsFzIBND27aQIklM5vYKZAghQBJBLVFeTZP+ll0gFpCeA/Oh6mQB64w1aVc/JgGQCiBcEHCiAnKBkZqbc59bUZOtJxyoOI+ZlxRz5R9mVsphVAXNSwODAAe1n2f3OEqtPGDK5EGgCqK4OMezDths8JA4LuAbszeT2OJwQt8UkgMJh6gO3biUfoPnzaZqSJYDGDBRARfQAYigCSCEfFAGkoKAQXMgEUH+/mFEEfXRzogBiGHkeWcGMJCi0uhibQNfUwNTqwy8Cwq6xqBmKrQBKp/1RAI1nD6BkEnj1VXq9dKkw5/AjBcxMAQRM6lLwheKCCwQBdO21tM1PBdDcudRlDgzQir5GADc6KsjqU08FXn7ZsQeQXWjMTH/zG+C2/4/e+MlPSRoFn8xMZQKIg0SvyzCxAqisTKsYtYJZFTAnBQz+539om89l4L0GExiycOrwYW/MpT2DTABl/NZi6PCOOMxcg2Z0obIsifiY+cKUTIyaqXf0+5upd7zA4sX0fPAgCVA5E7mvj8gYtwQQQGlgW7eSD9DFF2tTwSwJIKUAUggQlAeQgoJCcCGTIhyBNDebp8YEBW4IIJ4J2Q2UzQggnpybObWGQlTaxKy6GJMWxU4BK9S7CCi+AmhoKLtiX5IqYEFMAdu5k85LVRWp9pwSm06QTwEEKALIBYyMoGUTaK8RDosV+9de03GqTDJUVAgDDp8UQIBkZtqwG8uwiR6th/w1M5UJICZd/CKAnMhYzPp5uYCBHvoCBj6aQPsF2Vz6M58R27//fe/MpT2BkQk01wD3AplrF8M+bPva3diwAdiwgTh9vsyPPkrbZDInCGmXdXVi6JF9gApVAAG5RtAySVg+mrmXS+QBxPC0n04mgaeeAu69l56t5mAK4waKAFJQUAgu5OBxvKR/AYUpgPbtE6SCFcxIAqvqYgyL6mJZDyA7KWBeTtKdeBeZodgKIJ6Ah8Paa1yICXQqJQJCM6IzIKvkRgix+ue006iN+UkAKQWQL2ACaPNmImN6e4XoZu5cf77ztNPoOYcA4ig7FhNBrk8KIA3kduN3GzIigLxOgfKSAAJEAQO9t4++gIHbMvAlTAELAoFhCzz+NDQIE2gv7w3pGsQiB7Ik6DnnCIKBy6yXXA1lACMjaC8IIH0peJnXMSSAfEwBY6Psffu027u78xtl20J7O3X6F11EctCLLqK/rSrJKowLKAJIQUEhuJhMBFBrKwXMo6OilIMVZBNoPcyqi1VV5U+jkoMRM/gxSS/UuwgovgIop1xRBoUodOSy5eMwBSwk+/8AzpVtTqAUQL5g5kzqZlMpWu1n8eW0adbdQiE4/XR6tiSAMmkufiqAspDvQ/m1n99VU2Puu1MomAByUlVRPhYjZeaaNRT9M9aupcYijy/jUAE0bmBUBcwHBZDmuzI44QR63rHDu6/zGkY+QH4ogJgACoXSiKTYDMj/FDBZqaav53HeeR4o1TglX78wxyn5igQa11AEkIKCQnAxUQigfCbQAJXeYcLGjloiX5rQmjVUq/TJJ4F/+zfaNmUKVRuzAnsAFTsFrFDvIkAQQMVamjXy/wEKM4Hm6xqJmAdrAU4BC3Epp6VL6Znv4c5O7yXwSgHkG+Q0MD8NoBmmCiDuC2Mxf1QOZpBJn1IogIKUAib/vx4yMXDKKbnKUh/LwDc15eezfDHtDgqMUsC8vDfk8WvCEEDeeAABNCVNpaQS8BUQvolyFTCfUsB8Vap5kZKvEGgoAkhBQSG44OBx/34x0xiPBJAdBRAgfq+dJZt8BBBAk/FVq4CvfIUm1l1dVGrHCk48gLxcpS3UuwgofgpYPgLIDUEjX1ezcxFkBRCngLECaNo0isI4hc9LKAWQb5AJID/9fxicrrF/v+B8amsh+sI5c1wpgLiylxUMSQK53RRTAeRXChhHim4JILPjkQkHo37XbQqYjb6NTbvZm8bo4afRcMnhpwIoldKSfuOQAJJTwLhS1+Bg4QTQnDnC3kpe19AU1zNSACUSxoRKEOFFSr5CoKGqgCkoKAQXra2kjEkkRDWh8UYAhUL2Vz/nzKEB1QsFkIzyciJOHnsM+MtfxNKYEZi0sFIt+ZECxt5FV16Z+57eWNQMHMUNDNDk1e+6vX4SQFZG5wElgCp6ehA6fFjr6hsKUQS2fTsF86yfLxTxuDi/SgHkOc4/n55feEGsePtJANXXk7XE3r3As8/Stro6AM9LKWDc7h2oHDSVvUxgWNGpVAogv1PAnPSJ0Sjdy6kU9fWsMpEhEwNGJ9ltCpjNsSUWm8AETz74qQDSt78iE0BM3OarJGal7jrpJGrCfX3EZbBYJRpNo6HBtMZpXpSV0VRt927yAeJjKC+TyB0jAgggHyANUxRQeJGSrxBoKAWQgoJCcBGJkCoEEJPw8UYAVVebKzn0cGKY64QAAoB3vIOe//IXy91CHFRbmX34kQIGUNra+96Xu11vLGqG+npR4rgYPkBMALEygVGICXS+EvBAYFPA6jlXaNEiLYHohxE0X99IJPf8A4oAKhCLF9NpHRwEHnqItvldWpjTwA4epOccDyBWOTj0AMpW9jJ5GBIIpfIAClIKmLx4YdTXJxLac+MFASST2+NFLVEqGCmA+vvtFZHIB/311t1zshGyF1+nBxO3115Lf199tXN1V3k5cOKJ9HrzZuDIEXo9bZqYJriF7APEt1aWAAqHtQtVMuHjYyUwT+FFSr5CoKEIIAUFhWCDg0eAlnOYEAoy9ASQXfBsxk6gzBNvpwTQ00/TxN0MdlLA/FKgpNPAli30+utfB+65hzyM9MaiZgiHRTpQMQggnhT7lQJmhoAqgLIEEKd/Mfwwgubr29RkTLAqAqgghMNkJAoIQsZv7p0JIEZdbdrYBLrYVcD8JIDS6eBWAQOsCSA9EedFChh/n2yuomAMIwIonfbGJD0PATR3rkiD4v6B4TrtUodYTNz+73mPTeJWBxaivv46cPQojRPTpuX/v3yQCbBsClg0QwDpFT7///bOO0yO8sz2p6YnKI3SKEdEEElCRkhkECLZYJMGTLZhbbO+14DBmLXX2BjWeI3XNjgsBvu5BmyvDTjQsGQQIAlkwAiJIITIQgLlPEqTeur+8c07VV1dOXV1z/k9zzwdpkN11dfV9Z0673nNeUCVMqbjKMknmYYCECEk25gFIDnqyDpmAchv/g8QfwaQmWnTlE18+3Zg4ULnx3WLCrqfNvBxT1KWLVOn1OrrgWuuAS64QGUYBdnmaeYAJRkCXU0CUBIOILf8H4ACUERWrix1/OzcqVoLx9Je2IYSAahmhyGijhtXnSHQu3cbTpesdQED3Pf11u0QpwPI6T1TIC4BI1Ha2oxtOmiQ+s0MUSLpiPW3xSIA1dUZ+wdrGZi4d266Sd0+6CBDu/1//89/NlNnp9rXAMDMmSE+A4wcILMDaMSI6M4yswOoRwCq67ZCmQUfQB2/iJBSKQKQlOQDpSKQ35J8kmkoABFCss348cb1wYMro+uA+SA2jACURAlYLgfMnq2uP/us8+P8tIFPSgD63/9Vlyec4P9zWUmzFXy5MoCyXgKWhgDk1gEMoAAUAWkvfMcdxfefcYZqLRy5vbAD0gpeGLizO19ixAi1z5FZZFxlLm6kVQImry3lVlkqAQPcBakkBKC6OqM+p0wCd0WES5sFGdnXxRkE7eEAAtxzgCZMMH4ejzlGOXgA5Zjx695ZtkwNgcZGtb8Jg50DKA7hzs4B1CACkNUBpGnGfR0d0d88LZqbVem9dYX5LcknmYYCECEku+TzwO23G7dfeUW5gPL5si2SL3I5QwQKIgDJUVFLi/dZvKACEOArB0grZwnYgw+qyzPOCP8aWXIAtbYGFyz9ZABl0QG0fTv6SyBkGiVgdAAlRqLthR1YuVLNMc36xMdLt2ExDsbippPU0JEJbldX8mVZ5nGT5BiSz9G/vxI+stQFDHBfniQEIE1LpslAQELlRqWJCDKNjYYLI84gaFn3ciJo+/YS0dUrCPqNN9TlQQcBp5yirj/+uP9FEKPyIYeEz+wRAWjZMiOvOG4HUE8GUM5BAAISaQWfilOtuRm46y7j9re/7b8kn2QadgEjhGSTfB4455zSIMhVq9T9WT8DMWCAmqAHEYD69VO/1hs3KreETHjsiCIAvfCCOsCzOygP0gY+zgP01auBl19W1087LfzrlMMB5BQCDRinMP0StARM1/2HjCeI9uab0HQd+pgx0Kw9ds2ljV1d0RM4AW8HkIhyso1IZlm5UpVqWEWn8346E8BiYBnQZ1/gnbf7YEJdnTqLvm2bu0suCu3txTlpaTiAZKKdpS5g5uUJKwAFzQAC1P5tx45sCdxZw5z/I8RZIinbe+RIY4xu3170fn4FoGnTVH6YpgGvv64O4caO9V4EEYBmzAix/N3ssYc6lNm5E3jhhfgygCQPbds2YO1adb2+tvtkj50AJPfFKACF7nAYFPN3f8wYln1VCXQAEUKyR6EAXHWVfRcQue/qq7NdDiYH9EFCoAH/OUBhBKDJk9WRV1sb8I9/2D+mWwDS0xaApNXQoYeqg4ywiCCQhgPIKQS6b19DlAlaphWkBKxQyEymgPbaawAA3VrHAxhhkm1tRhBDVOgAqho2bfLpONqkpZMDZBV80nAAye9FVkvA3AQgWeY4HEDmx1IAckbWvZ0AFGcJ2ODBhnjh0Ans/fdLn75hg3LcaJrqKDh8uJHj88QT/hZBBKCw+T+AOtdw4IHq+qJF6jc5DgdQv37GYYr0rXB1ACVUApaKU828P+QJlaqBAhAhJHs8/zzwySfO/9d14OOP1eOyiFmY2rkzmFDlNy8ljACkacDxx6vrTmVg5SoBk/yfM8+M9jpZKAEzlzEEXUdBHEBhXj8htNdfB+AgANXVGUfLcZWBMQOodyIT3jg6HTlhHTNpOoBETOnoiPcER5ICkNTDxCUAZaAELPPYOYDiLAGT3xVz9pblOycOILtW8EuWqMu99jKG9qmnqks/ZWBtbYaDKIoABBhB0IVCfA4gwBDADAEoXQdQapj3h0nud0mqUAAihGQPKdaO63Fpks8r3/GHH6rb8+YFyy3yIwCZWwcHDUuWMjCnIOhylIBt324IUlHyf4BshEAD4YKaCwV1NA2ose00AayrA2q7K7izIAAVCsCCBep6XZ39cscdBO3XAdTRYUx+SeVTLgeQnRs1zveyloAB8bqAkuwCJjPhjRtL11OYEjA6gLxxKwGL0wHUr5+jADRxovoZam0tPV/XfT6gqLOf5ADNmeNthHnjDfWYpiZ1+BQFyQESrBXKYRHd0xCAustGrV3AzPdVogBEB1BVQgGIEJI9Ro+O93FpIblF1qMhyS3yIwKJZ9dtorxzp3GgHVYAWrgQ+N3vlEAlE/b2dmiSfeFXAIpjYvTkk+rAaO+9gf33j/ZaWXAAAcEFIBEOxdX2y1+6C4dZ6QSWzwMTJ6Lm3XcBALmbbrJf7rgFIC8HkLmLHV1A1UMaDiCZ8MjYKhSSExGtApDZoZOEABRnFzDZBjIT7uwsnSDSAZQMSTuAzNvN4TtXW2tk4VhzgMwB0MKMGcp909KiYgjdMJd/RYm4W7myVHtcv17H4sWqxXwUQ6ronvKTVl9TpQ4gswBEB1DVQAGIEJI9jjnGyA2xQ9NUe/hjjkl3udyIK7fITwaQTGhraoIdWAMqaLm2Vi3TZZep1vAyYTf9uGuLFjkvqxygd3X5O6ApFJTQdO+9xYKT3P+LX6jbp50WPdC4Eh1AYYTDLHQCk+Vetar4frvljrMTWKGgSkABdfRtN05ra43vBgWg6iENB5CMl5EjS++LG6sAVFtruPviFECS7AI2erSxv7MK78wASoa0QqBdBCDAOQjaTgCqqQE+/Wl1/bHH3N8+jgDolStV+/j/+3+L729ursMhh6juYvvuG/4nSXRPoUEcQClmAKWCed9HB1DVQAGIEJI9cjnlgABKBQG5/YtfZKsbQVy5RX6cEvKDPGBAMMFEJuzmDjeAmrCffbY6Guqm9pRTnB0o5oN5r0mKOFtmzwYuvNAQnL71LeN+CaT+05/8l8o5kZYDSNedu4ABhkDjJQCFFQ7LIQCZhbxnngm23HE5gGQ8SeuVK690HqfMAQpFKu2FwyKT3DQcQIMGGd+zpHKArAIQkEwnsCQzgAYPtg/f7+oy3pcOoHiR8W/uFBpnCZiPDCDAcMGYBaDOTmDpUnXdLAAB/tvBxxEAvXGjz3D5kIcK8tmF+hofAhAdQCQjsA08ISSbNDerVu9XXVUsrIwbp8SfrLWAjyu3SJwSa9eqoxO7mViYAGg/QoP1wFGcHH//e/H6rqtTp/O6utRBulO7ehGcrO/5ySfAT39a+viNG+3fLwgyEWlpUWfb7Orx42DXLkPciOIACiIcHndc8NePi3y+9LvohnW54xCAnMaT0zhtbFRdxygABSK19sJhkMloGhlAjY1KmNm1Kz0HEKD2+du3V54AtGJF8aAxl80FbQMP0AHkRlolYP36Gftbnw6g995Tm75/f2DSJOP+lSuBUaPU9SVLlAhkNtnJPmXHDmDZMnVf1ADoJLE6gOq1bnePnQDEDCCSMSgAEUKyS3OzCgV+/nklnIwercq+suT8EeLKLWpqUgddu3apCbQcYZkJIwB5CQ126LpyGF19tdoOst6ly9WOHc4H6W6CU9D3C8LgwYY4tWmTccQZN3IgpGn2eUlyn9ckJqxwmOYkyUl48YMsd9QSMC8B027c0AEUmgkT0hN4mpqUPuCmd/Q4jtJwAJkdliIilsMBFKcDJkkBaNAgeweQ+TnVVgJWKJT3uCStEOi+fY2SRBcByNwKXsq/pk5VP8WAUY5l/o5LVzChTx8lPK9YoX6+x47NXsyjmcGD1b5Lqs3ra1wEIDqASMZgCRghJNvkcspBcMEF6jKL4g8QX26RpnnnAIURgMJ2THMqXfOapIQRnNzezy+5nHEmNMkcIHP+j9029+vQCSscpiUAhRHyzMhyy5jesiWcIBOmxJICUEUgjqNFi0x/X7sTizAdi067EYsWqf9PmIB0HUADBhjCTNoOIKByuoA5lYDJc8y5Rn7IegmYU1lz1PLlIJQjBNrG/WFuBS+GWLv8nyDlWHHk/6SF2QVUr7l0AWMGEMkYFIAIISQO4swt8iqXCdMCPuqpNKuA5CUAhRWc4ni+3WQkbtwCoAH/AlBY4TCtErCwQp51uRsbjQlKmDKwME4pCkAVw4QJwPTppr/OlzEdr2L6wTqmTze5kdJsA9/YaIyhNB1ASQpAcXYB8xKAwrSAN79nFh1AcXT6jIM0Q6DlN87G/TFhgtI22tuNXH47ASgIceT/pIU5B6jXlIB1dZVvWUhsUAAihJC4kNyisWOL7x83LliujVcr+DAOIC+hwYugDpSoglOU56cRBO0WAA34D4E2C4dW3ITDtBxAYYQ4p+WOUgYWxilFAahykTFirUNLow28uQRMhJlKLwGLuwtYZ6exngYPVv29AXsHUNBOlVl1AMXV6TMO3ASg3buL85fC4DMEOpcrbQXfmwSgIgcQusWdai4B0/X0cgdJolAAIoSQOGluBj76CJg7F7jnHnW5fHmwUGMvB1AYAcjNoeSGkwPFa5ISVnDyWyrnRhqt4OVgOKoDCDCEQxGuBDfhMC0BKIwQ57TcUYKgwzilKABVLk4CUJoOoGosAYsrA8hcCuKVARRWAMqaAyiuTp9xYCcAmcuRo34/zCHQHqKruRPY1q3GV3fq1OBv+8orqpwMUKaZxYvDx8YlycqVatnMlY2bttdjMQ7G4pa9S5e5WkrAAOYAVQkMgSaEkLiR3KKwJJEBBDh3VpMkQ00rPrvp5kDxEoBEcDrnnNLXdSJoqZwTaTqAvAQgv5OY5ma1vF/9KnDwwcCtt7oHi6ZVAibCy6pV9ttQ04CxY9F555147ckn8alTTkHt7Nn2yx3FAWQeT3bLAJSOmywJQOUOja0kdN0YI7IvFNJwALEEzMBpPy/rv18/Nbl1KwELKgBltQQsrk6fcWAnANXUqNtbt6qsNXOLraDYZQA5fOfMncCWLFHXJ0xwbg7qxle/alw//nh1KeHQQUPphw0LEC4fALtAawC4Y+EM3IHFwANAn8cty1wtDiCAOUBVAh1AhBCSNZJwAAl2DqV164D77w9WuubnLK0ITmPGFN8/fjzwb/+mXt/v+wUhDQdQXBlAZmTydPDB3oHnaZ0l91Oi9stfQp89G6uOPRb6rFnOyx21FbyMJ+sk1mncZEUAykJobCWxdasx6Rg/vvh/aTiA7ErA0nQA+SkBKxSAefOAe+9Vl15lR3ELQOb8H8DdARQ0AyirJWBxdfqMSlubsT2tJchxBUGHEIDefz96+ZcdEg4dFGu4/D//2YFbbpmHf/6zo+e+MMJSkEDrHio1A6hQMI4xZB9FB1BVQAcQIYRkDTki+fhjFbhXY9HqowhAgL1DqbkZOOMMdM6di9cef9zdyQH4z6lobgamTFGnzOrqgCefBI49Vr3uzTcn44rIkgMoiAC0fr26HDHC+7FplkmI8HLxxcXbe9w45bppbvZnbY8qAMmy7LknsGwZ8J3vACef7DxusiAASWis1T0lobFxCJ7Vhrh/hg8vdY/IZLS1VU2CgwoafjCLMll0AOXzpS7OceOUUOs0lqJ2AbMui5MAtGGD8ZiwJWBZdQD5cUOOGxetfNkP5gm49RggrlbwIR1Acq4nTgEoChMmGIdTHR3AmjXbcPDB9o26EqVSHUDm7+DYsUoxowOoKqADiBBCssaYMWpC29EBrF1b+v+oApATuRz0WbO8nRxAsIN0scSLC0JeV4SoCy7wdrwEIU0HUNQQaDNBBKC0SsCE5mbgsMPU9csvD5dtFaUEzMyqVeryi190HzflFoCyFBpbSTjl/wDFgmtSZ6LNJWBZywAK24UqLQfQ5s3GeK62EOiwgf1xI+O+sbH0veJyyNmFQLe02O7LRAD68EOViwOUCkBSjtVrqdQMINnv1dQYJYV0AFUFFIAIISRr1NYa5VFWt0ShoEq4AHXQX67JY5CDdJmsWEu+kiKNNvBxhkALWXUACevWqcuzzgon2IkDaPXq8AfCLS2G+OY1nsotAGUpNLaScBOAcjljuyY1ETGXgJXDAeQkukQRFOPuAiYCg4gDQ4cayyHuk2psAy9uSGunp7jKl/1gl/8jxF0CZg6B7uqy/R6MH6+GVUeHKqsCSgUgazmW/P3pT9EWs2Ko1BIw8/7JLASSiocCECGEZBG7chnJEnnpJXX7pz8tX5ZIkFbFaQtAUgKWhQygIJOYShGARo0K9/wRI9RMoavLXRhx4+OP1eXgwcWTZjtk8l6uA9YshcZWEm4CEJB8DlBaXcDa2w0h1I8DKIqgmLQDqK7OuC7Ce7U5gISzzir+TBddFNwNGQU3ASiJErC+fY12Vzaia02N0Qpe19UQE1eQmQkTgOnTi//23z/aYlYMlVoCZnZDyrEOHUBVAQUgQgjJIjL5EQEorPU/KYKcpZVltoZMJ0UaDqByZwClXQLW0aHKO4Dw3WVqaoxQ37BlYDKWrOHAdsi2KZcDKCuhseUmSGBxoQAsXKiut7fbP1YmuWmUgCXpADK/pnyfAWcBKIqgmLQABJTud6utDbywaVPx2KuvT7ejX5oOoL59VXmb7EstYrq0Qx8+3Lhv0iQVBp3VFu5loVIFILMbkg6gqoICECGEZBFzK/gsZokEOUsrmS1pO4C2bgU6O70fH7SjDhC/ANTVZQSoZtEBJOJULmeUe4RBhM377vO/rs2IA8iPAFTuEjAJjZV8ECuapj5H0qGx5SRIBzR57Ny56vYdd9g/ViYiSTiAdD09B5C8T58+hsMCcBZdwgqKHR2G0+iVV4J958wh0ObfHz8CUDWWgAGqlsmMXU5fkljL78zE5QAyZwCZ38skfEk79EMOAZ57znjq22+r+w45RP2fIhAqNwPIvC+kA6iqoABECCFZxFwClsUskSyXgA0ZYky6xbXiRNgW3V4CUNAQ6M2blQgEGBMpN9IWgKT8a8SI0q50fsnnjfLF3/wmXDv0IGOp3AJQVkJjy4WHa1F74AHfjy0aI0k6gHbvNr6HSWcA2eX/AM4OoDCCYj6vLBnCWWcF+86Z3TviIgLScQBltQTs3XfVpYh2aZdw+ikBiyKOFgqGUCHbwkYACtUO3YKfcOg+ffz9JKZFqGVmBhDJGBSACCEki5gFoCxmiYQpAUtLAKqtLc2jsCNKWZ1XF7CgDiBx2Awd6q9HbdolYCIAhS3/knVtHS9BSxjDOIB27LB3z6WBhMZax8no0dXdAt6HazH3zW+qxwV1OCbpAJIJj6apyW8aDiC/AlBQQVG+c+LAFIJ858wzXbMgI0JAEgKQ+eRCub63bogAdOih6jJtB5DduhfiKAEzb2cXB1AcOIVDm//eecc5DqwcOC7zkVdiEaZj0Q0PlS5zpZaAMQOoaqn1fgghhJDUkbyc99/3f4CZZpaI37O05lb2aQlAgJqMbNniHATtNenUNDXpPOMMe4eG3y5gnZ3qoM/aNcZKkPwfoHwOoDACUNR1bUYEoCAOIF1XQplXaHRSNDcDDz8M/P73xn2//jVw5pnlWZ408OFa1D75BE1vvQVt4ED/Dsfjjks2BFqEnv79ldOtHA4gN3elCIoXXljsyBk3Tok/IijG9Z2rq1ProatLLY9VYPBTAhbWASSvEfT5SSMlYLNmAS+8oPbdhUJ6Tr6kQ6DN404EwIQEIEAJJVkSePxgu8x9lwF4FZi8A7D+r1JLwJgBVLXQAUQIIVkjnwc+/Wl1vbUVuOYaZ9s/UJ4sEb8lYGvWqAlHXV1xUmTSSA6QkwMoSlmdrvvPAAL8iTTVLADFWcIYJAS6Xz+jXK1cZWDC+++rSzmIXry4fMuSBj7diH22bAnucExwMlp0xhswxJldu+LPWAvqABKam1ULJeGhh0q7UMX1ndM0+319kBKwsBlAQDZzgMQBdNRRhjgm+W1pkHQItGy3hgZj/5nkd65aEHeP3cmeSncAMQOo6qAARAghWcLJtu9khS9XlojfEjBzB7Cw2TFhkMmIkwMoSlnd7t3GZNBJAKqvNzIi/JRpBRWAzG3m0yiTiCIAxVXCKJNWwJ8ApGnJlvAEQVwDn/+8unz55fheO0yIeRKvYcanG7F1yJDg4cZpOIBk3IgQBMRfbhlWAAKKx/N++5Xu++MsG44qAAV18NTWGmWwWROACgVDzD3gAOOkRpplYEk7gKwB0Ob34uTfGTcBqNIzgBob6QCqMigAEUJIVnCz7QvWA/1x48qTJeK3BCzt/B9BOlU9/bT9hDZKi245ANK0YqePlSBB0GEdQLruncTpRJBJfxQBKK526C0txgGp3/FU7iBoQE3GxCFw0UXqcuHCeIS7sCHmcb+GFR+Bxfq4cdh0wAHQjz46WLhxGg4gEWUaGox9btxlYGFKwATzJMzO5RjXd85peZIUgIDsBkGvXKlK7+rrVQ2QrL808/f8hkCH3b/IOjeX4lEA8kbKu+wy/CrVAWQWxOkAqiooABFCSFbwsu0DapL+858D99yj2iVbrf9p4bcELO0W8ICauMrk9S9/sZ/QRmnRbS7/cnM1BQlqDisAAeHOkged9EcRgOJqhy7un6FDiz+/G1kQgKRkZOxY4Igj1GRg82b13Y1ClBDzOF/DDh+BxYVbblGPCxpunKQDyFoClqSLLIoDyEsAius7BxS3ggdUyZNdCH5cbeDN75k1B5B8l/feW43HUaPU7aw4gKQErKsrvGBpJ9xx8u+NnxKwSssAYhewqoUCECGEZAW/ZxFHjgQuuEAFoparhXSYErA0kAmt9eDXOqGN0qLbKwBaCCIAmdus+yGXU+4Ev69vJsykP4oAZF7X1glpkBLGIAHQQhYEICn/2ndftc2mTVO3o5SBBe2cldRruNHcrLarlW7Xon7WWcWPteuWZudwTNKNYC0BA5ILgg4rAJkzyAB7ASjK/s2KLI8IAy0txvhwE4Cq0QFk/i4D2XMA9eljiA1hy8DstpvN5L8SW7gnSjWXgJkdQLt2VZ6QRUqgAEQIIVkhTtt+0mSxBCzohFYmnZLVI3iV1XkFQAvmnB4vgjqAgHBB0GEn/XKGO2wbeFnXViEwSAljkABoIQsCkLgGJk9WlzNnqsuFC8O/Zhwhv3GGczsxaZJxva7O3bXY3Az8n/+jrn/6086PTcMBZBZl0nYAebkrd+9WDg/BKehevnPmHCMgeNmwdXlkvffpU6wAyEx/2zY1QYwiAGXdASTf5aw5gDQtehC0mwBkEl0rsYV7olRzCLS5DTxQ/kw9EhkKQIQQkhXitO0njd8SsDQFoDAT2k9/WrVqF/bf372srlBQrX/l9dzcEUmWgAHhBKAw66iz0wjTDisAAWqdfvSRaoEOqFKuICWMQQKghSwIQFbXwKGHqssoAlAcIb9xBgU7IYG5gBIFDj/c3XUiE8zDDnN2OKbZBcx8PSsOIGsJhlPQPaC+W2efra6fe264smEnAcic/yO3pSR206bwbeCB7DqAsi4AAdGDoAOEQE+YoBrSOf31GvEHqE4ByOyIrKszxgRLASseCkCEEJIV4iqVSYOgJWBpCEBhJrRvvln8v507ndev5OZ8//vq9ltvuefmJC0ABXl9Icw62rBBCUM1NdH9/Lkc8MUvquubNwebpIQZS1kSgKwOoEWLisXHIMThFkzDcWgWgABvV4KMB3Ex2CET3G3bip0wcWBXApa1DCCrAOTkABJEIDrxxHBlw34FoFzOCN/fuDF8G3jze2bNAVTuErC2NvUHeAtAUR1ADIEORrVnAAHMAaoiKAARQkiWiKNUJg0kf6ajA3jmGXsnTKEArF6trqchAIWZ0L7+urrcbz91uWaNfXlUmNwcv13AWluNA6qkHUBh1pHk/wwfHo/4OGAAsOee6vqSJf6fV4kOoK4u4L331HWZNO67r1oHu3YBy5aFe9043IJpOA6DCkDyfz8CkK6n48pJ2wFkFlzs9kVBBaAw4rLT8gCGCGAVgIDiHKA4MoCyJADt3q26gAHlcwCZBRhraZ+QUgkYseDWBazSM4BkrDEMvGqgAEQIIVlDSmXmzi1/ty878nnl7xZOPNHeCbN+vXI41NQYB8pJEmZCKwLQZz6jLjs6Sksqwubm+HXoSIvw2lr7SZUTYSZJYdZRlABoJw46SF2+8Yb/51RiCPTHHyuBr65OfUcAJaLNmKGuhy0Dcwv5BdS49HILxhkU7ISIX4KX40v+7/Y9MAfdxp0DZFcCVi4HUFeXvUOsXAKQOJKcHEBA/AJQlkrARMwcPNj4nGk7gGTi3djo/L2MWgLmJQCFbS9f7VR7CRhAB1AVQQGIEEKySC6n7Prl7vZlRZww0t5dsHPCyGNGjy4NWk6CMCV0r72mLmfONA7qrQfzYcNy/YZAmydoTsKMlULBKAV45RX/nZrCrKMkBKCpU9WlXweQrldmCLS1bbQgZWBROoGJW9AujHz8eOCUU4B584B771WXdmMkbBC6H9rbgRUr1HURgONwAAHFZWBxkqUuYIB9GVhQAUgE5uHDgy2fdXm8SsCAYgGo2trAm8u/ZF8p43rnzvjHhx1e+T9AdAeQWwZQZ2e2RLks0RtKwOgAqhooABFCCPFHUCdMmvk/QpASuq4uw4EybZrz2dywYbl+HUBBz9BLFtGiRer2j37knkVkRdaRtRxsxAj7SX8WHEBbtxrrsZIcQNbMECGOIGhAbasvfUld/9zngAcfBJqalCA5ahQwezZw4YXq0mmMnH568Xe6pgZ4++3ojsOPPlLfsX79VLg6EI8DCDAmpEk5gLKQAQTYT7ZlOWQf5yYA7d5tvE9cJWB+BKANG6rPAWQNgAbUtpPtl0YZmB8BKC4HkDkDaMAAQ/Ti5L+UQsE47qmWNvCdnYaISwdQ1UEBiBBCiD+COmHksVYxJmmkhO7BB437Xn65dEK7fLmaHDU0qAm6CCKSWySEDctNQgAKk0VkR3Mz8Oijxffdfrv9pD9JB9DSpf7cS1L+1dQUbEJZbgHIbtIIGA6gN95wDvv1i0zIjzoKOOMM4OKL1W3rQbrTGFm5Um2DhgY1eezqMoSrKEjJzN57G64Et0mprgd3AKVRApa2A0jTjIw1NweQ5Ght3uz8HRL3T329c2aMF04CkJ0IYXZRSkB3tbSBd/ouiwsojTKwIAJQnBlAmkb3hxtmZ0+1lICZj1uYAVR1UAAihBDij6BOmHI4gIRcTk2GDzxQ3X7xxdLHSPnXlCmqBGbMGHXb+jnDhuX6DYH2KwCFzSJywvo5pVzHShIC0N57K6fDrl3Ahx96Pz5M+RdgHLiW64ylkwNowgRVktPZaYzDsEhmVVOT2vb332//OKcxIkLNXnsBn/qUui7ZWFGwE4DcJqW7dhkTKb8OoDRKwNJ2AAHuncBkLEumlK47C2thykuthHEAmQXqagmBdvoupxkEHaQELM4MIPN7cvJfSjUKQLK/q601lp8OoKqBAhAhhBB/BHXClFMAEkSUsebzAMYkd9o0denkAAqTmwPE7wAKm0XkhDXHyUmISUIAyuUMcc5PDlCYDmCAccay3CVgVteApsVXBrZ5s7ocOjTcGBGhZp99jO9C3AKQn7IUERZyOXtRxEzSDqByZgABpaKLGZl8DR1qrAdrcL0QNQDabln8CEDyfdU0+wlx0PfMAk4OoDSDoN3cV0ISDiDze3LyX4pZ2LHrAibfga4u/ydoyo15/yTHOXQAVQ0UgAghhPgjqBMmSwLQc8+V/k+cF+J6cHIAAUZujrWbmVtYbtwCUNgsIidk+4jbIE0BCAiWAxR2LJWzBMzcNtrqGgCMMrA4BaAwY8Qs1IgAFNWVZH1dPw4gEYeGDPF2qyTlRkirC1ihYEy0wzqABg5Uri/AOQcoagA0EKwLmLyPCEB9+oRzHmXNAbRpk/E922ef4v+VwwHk5pBLIgQaoAPIDRGAamrsG3aYRaFKCYK22xdSBKwaKAARQgjxR1AnTJYEoFdfLZ3AOTmAnCbRzc3APfeo68OHA3Pnqhwhp7DcMF3A3AibReSEbJ/DDlOXaQtAQTqBhXUAlVMAev995bgZMsRwRpiJoxMYUCwAhRkjZqHGXAIWtd2z2VnkpyzFbwC0+TFxO4DS6gJmFoWjCEDmrlt2xOEACtMFTBxJYcq/gOyFQIuTb/z44nBkwPguZaUELIkQaPN7UgAqxa0DmPX+SikDs9sX0gFUNVAAIoQQ4h+nLlvDhxc7YXTdKDEqpwA0frzKyujqKs4B2rLFcGeIE8WpBMyMiCYHHggcd5z92T4hbgeQlwMLsM8ickK2z7HHqsvly43gVqFQMFwE5XQAiQBUSQ4gc8mI3TYTAeidd4A773Ru1e6GrhcLQGHyqswC0AEHqMyHLVvcS8m86OxU40leN0gJmFcANJDMZLRQMMRauwygOAUgeS1zvoYZPyVgaQlA1mVxc6FYhc4wLeDN75kVB5BT+RfQO0Kgze/JyX8pXgKQ2QFUKQKQXYkqHUBVAwUgQgghwZAuW3PnGjkm3/hGsRNm82bj7LWUVpULuxwgcf/ssYdxwGwuAXNyP0hQ8sSJ3u8bdwi0mwNLuOUWd1HKjEzwDz9cPaetrXQSs3GjEoU0LVoZiR3iAPrgA+91FDYEWrZBayvwzDPp5i84hcYKzz9vbKuvfMW9VbsTO3caJQVDhwZ36RUKav0DSqhpaAD220/djpIDtGKFEoH69FHfqyAlYOVyAJnFhqRLwOzyNcy4OYBkOfwIQHGWgAVxAFmfG5SsOoDsvstZDYHesSNcuREFoOB4CUC5nCoPAyqvBMxOAOIYqHgoABFCCAlOLqccMJ//vLptLWORCfuIEUZL43JhlwNkLf8CjAP5tjZnp4IIQNKBxw0/DiBdD3aW3smBJZNIpzBYO8QBtMcehqBlLQOT8q+mJuVWiJMRI5SrSNdVO3gnJLgYCCYA5fPA9OnG7RNPNASWQkE5bu69N5zzxg9OAdCybOecU/q+Tq3anRD3T329MWl2GiN2eVWffKImL3V1xrqVMjCnHCA/687cWaymJn4HkLxenBMREVZyueJ9VhIlYG4B0EC2SsDMAlBXl7sDqLGx2O0QVgBycgAVCtDmz8fY556DNn9+eoKumwMozRBoPwKQ+X9hvh8UgIIjoo5dALRQaZ3A7DKApASMDqCKhwIQIYSQ8Bx+uLp88cVi10wW8n8EKXH65z+VuAOUBkADatI1dKi67nQwH8QB5EcAamkxDgj9nqU3O7DuuUdd/vzn6n/f+x7wyCPewsauXcZkfOxYYM891XUnASju8i/BTw7Qli3GpMQqajghAou109mqVcDZZ6vPM3s2cOGF4Zw3fpBJo9U1UCgAV11l7zJzatXuhLn8y+wkkTFy/vnq9mmn2edViVCz556GK8itE1g+r9aV17ozl5UB8TuAZDIapwPIyZVjdgBFzUWyey87/JSANTam6wBqbVXLLWWidttJ04pdQGFLwOxCoLvHXu1JJ2HGrbei9qSTkvne2uGnBGzDhuQFKT8CUG2tMWkP8/2ohBDoNAT8IHg5gMz/qxQByC4DKEtjgESCAhAhhJDwHHKIOuBcu9bI1AEMAcjvhD1JJk9WZ8Db2oBXXlH32TmAAO8coDACkFuOhZyhHzCgNHTTDXFgXXCBuvza19S63rRJTfa9hA0RRgYMUGf1vAQga/ezuPCTAyTun+HD/U0o/QgsVqdUUOeNF7ruXDYSplW7E2YByEoup8YCoAQCu9JAq1ADOAtAIqpZl91u3TkJQNu2leZMCeV2ANmd8Tbf7uyMb/JWSQ4gcwi0bKP6eufvolkAiqsELMjYi5tCAXjvPXXdrgRs+HDlcuvqMgS3pPAjAAHRgqCdQqCzEgDsV4ROkyACUCWXgJkdQHGJ4aQsUAAihBASnr59DRfNSy8Z92fJAaRpwNFHq+vPP68OwKTkyCoAubWC1/XwDiCng6U4JmgA8PDDpW4XwHmCZN4+mpZtB1DQAGgvgcWOoM4bLzZtUpMvTSsWV4BwrdqdcBOAAOO7+cYb9sKLmwD0/vvGJCCoa8ncAQwwJqS67lw+YG4D70USDiC7M96A8T02PyYqfh1AfgUgu9LPoOWlTpjdSG75P0IcApC5BCxOx1xQCgXgb39TJw9yOft9UC5nrN+ky8CCCkBhvh9ZLgErpxDohh8BSMrDKsUB5NYGvqPDft9EKgYKQIQQQqIhZWBZFYCA4iDot99WB2EDB5Zm+bjlOaxfrw56pJOSF3IGVdedD5bimKDJBMkOpwmS1aE1aZK6TFsAMjuAnESyoAHQYSdhQZw3Xoj7Z8KE0olUmFbtTngJQJMnqzybnTuNsGczVqEGUGNx9Gi1PkSYC+pasgpLDQ3GenByJYQJgU7CAWQVZWprjWWPKwfIrwPIWgLW2WncN3CgyuYC7B1AO3ca+524QqDTEoDMDqA4HXOA//IhcZpccIHxvL32shcZ0gqC9isAiYgaxQGUNQGonEKgF72lBKx/f6M8ljlAFQ0FIEIIIdGwE4Cy0ALejOQALVgALF6srh90kNGZQ3ArARP3z+jR7gd6gtk54JQDFIcAFGaCZN0+5XIA7b+/2gabNjlPnoIGQPsVWJyI4yy+WwB0mFbtTngJQLW1wJQp6rpdpo+dAwgoLQML4loqFIxxZH5dr7KUMG3gW1vjOxPtVAIGxN8JTN7LvI8w41QCZn5/rwwg2bf06+f8Pn6IIgDF0QY+Tsec3/KhoE6TNIKg29qMDDsvAUj+/9RTwTNyvDKAyjXxj1sIjJNqFIDsROqamuyUApJIUAAihBASDRGAFi82DlCz5gCaNk1NmFpagD/9ybjPilsJWJAOYEBxN6EkBaAwEySrA0gEoLVrizOLkhaA+vY1RBKnMrCgJWBeAosXUQUkwDkAGnBv1Q6oicwtt6iJjJdLQQQgcYLY4ZTp09VV3ALe7TlBXEsff6wmOfX1xdvMKwg6iANo4EBj3cU1EXEqAQPi7wQWtgRMJt99+qj1K2LLli3KHWRG9i1R3D/WZfGzjeJ0ALW3+983eo1Rv6JOGKdJGg4g8zi3EymFfB545hl1/c47DZHrb3/zdj51dBj3WzOAyu0AilMIjJsgXcAqOQMIYCewKoECECGEkGjsuac66G9vN7prZU0AyuWAI45Q159+Wl1K+ZEZPw4gP/k/glcQdBwCUJiSIqsDaMgQ4wD/o4+MxyUtAAFGDpBTEHTQEjAvgcWJIM4bL9wcQIBzq3bha1/zF3Iq2S9ODiDAWQBas0a5OmprS8e0tRV8ENeSXWcxIF4HUE2NMQmOa0LqJsok5QAKWgJmzv8B1LqSbSJioCCBxFHzxcwijuyv0soAAoAZM9ybCfj53gYRdcI4TWTfmoYA1NhoH+gOGCKX9ffmk0+Ac8/13qeYx1vWSsDiLJ2Nm96SAQSUfxyQWKAARAghJBqaVlwG1tJiTJSy0AUMUAe65hI1ALj++tIDYD8OoDACUJIOoDAlRVYHkFMQdBoCkAhxXg4gvwIQ4CywiFPGuq7k9i9+4Ty58kuhALz6qrre2urs3pFW7XPnAvfcoy5POUX9z1rS41R64lUCBhhijlUAks5Ge+yhRCAzIhotWaKcQiKquXV+kXXnVFYWpwPI/Li4gqDdSsDSdgA5lYCZW8ADarvJerWOmbgC5s1lXLJfTKsEDFCuUidxx+/3NoioE8ZpIg6gJN0nXvk/biKXHXb7FBGANM1wrwryvuZStDSJs3Q2bqqxBMzJEUkHUFVAAYgQQkh0zAKQHGgPGRIteyIu5Kyo9YBlw4bSA2BzloP1QFqcMVkTgNwcL04TJLuMJqsA1NVlLF8aDqB//KO0PEHXw7vJ7ASWdeuA++8vFYbGjFGCUXNzlE9iZIyIWPitb7m3KM7lgOOOU0Gzxxzj7IJyKj3xIwCJwLZyZbFLxEmoAVQodJ8+xeHRRx9dKhQBaozdc4+x7rwEIDsHUGenIYr4cQAB8Z+JdisBS9sB5FUCJpMwwDkHSBxAUUvA6uqMrLSgAlBYB1BNjSEeLV+uuhwCpeN83Dh/39sgok4Yp0maJWBOAlDQ7od2+xQRgPr0Kf0tMQuj5XB/hPmdS4tqFICc9lF0AFUFFIAIIYREx04AyoL7J2iegxzU795deoATxgEkOQpJCkCAs+Nl7NjSCVJHhzFRMT/eKgBt2mSsl6jL54aU233wQWl5wqZNxiQ4zHgyCyzHHadum4UhEZV+9rN4xJ8oLYqff94Q5uywKz3xIwANHmyMWbPA5CYA1dYawpyUgd1+uxJqZs4Enn1WZWkNG6aWyzzxsessJssB2Dt2zPeV2wGUhQwgvyVggLMAFNe+RdMMISctAahQMMTGyy5T+8/DDgPWrUPXzJnqIddeq8QhP9/bIKJOGKdJGiHQXgJQmPe27lOcAqABte+Mu+wyKPI7J4Kb4FcITIogJWCVlgFkdUTSAVQVUAAihBASnZkz1YHxRx8Bixap+7KQ/xM0z6FvX2NyYz2gzmoJmCDCxrPPGgfwjzxSelC8dq363HV1xe4AqwAk5V9Dh7qHW0Yhnwcuv7z0fhFNfv97dXvEiNKShCiIMHTOOeq2hKaGJY4WxWFKT/wIQIB9DpCbAGR9zu7dwK9/rW5fe60S6S66CLj0UnXfvfd6v66bA0juGzDA3mVkR9xnosvRBSxsCZhZAJKyRsmDEuLctwQRgMwOrlWrgrflFhedrCMpDT39dDU29tpL3R4xwr/bI4ioE8ZpkgUHUJTsG9muIjhaA6CFLHSAam4GHn/cuL3XXv6FwKQQUaeaHEBOjkg6gKoCCkCEEEKiM3AgcOCB6vr996vLLAhAYSbVdkHQW7cak6+4BKDOTmPSFpfDJpdTk3OZvEsYsRmzQ6vGdBjgJAAlVf7lRzT5r/9Sl0Hyf4Jw0knqcs4c/9kZdsTRojhM6UkaAtAzzwBXXqkcJhMmFE+0LrxQXT78sPp+uHUWcwuBDhIAbX29uBxAldAFTJYxzRIw8/LIftJJhMjni50xv/mNewmk3fPtXHQA8L3vAfk8dDch0QmzqGPFTtQRp4n1O+nkNBEBaOfO+MaIFZlwO4lvUbofmp2vgLNzKyuTf3Mpa2trecq+zIio46cLWKUIQOwCVtVQACKEEBIPUgaWJQdQmEm1XRC0uH+GDQuWa+TWBWzTJiUMaFpx2UQc7L+/uly2rPR/TiV6ZgFI15MXgPyIJjKp7dMnuJPAD7NmqYP2FSsMQSQMcbQoDlp6snu3IRAEFYB03blUSxBh5aWXVDtpQE38HnrIeMynPqVa3be1AQ8+qETT1lbl1Jgwofj13EKggwZAmx+bZhew3lgCBhiCgAhQdttJxBtrGaPfEkg/IcZXX2189qDCn4g61mBqJ1GnuVkJw4D6/HPnOjtNBgwwtmUSZWCFglGKuWOH/b4wTPdDu30KkH0BSMRNuR5FvI+DIBlAlVAC1t5ufCY6gKoSCkCEEELiQQQgIQsCUJQ8B7MDKEz5F+DuAJIJ2rBh8Z/BPOAAdfnWW6X/swuABtSEvaZGTQLWrUteAAoyUfrHP4I5CfzSvz9w5JHq+tNPh3+dOFoUBy09kbPg5mwOJ6QT2JtvqgnIunVqTNbUqPVqJZ8Hvv/90vtbWoon85pmuIDuvdfoLDZpUmkpV9wOIJmIpNEFLGslYOZl9BKA4nAAWUUTqwAURwmkXxdd9/jRgjiAhObm4v3e9de7lw/J+h450sgQcyKpMjApifvDH9Tthx923hc6ZcHZYbdPqUQBqL09vu9lWKqtDbz5eIUOoKqEAhAhhJB4sApA5hDhchEmz8HOARSmAxjgHgId5xl6K24CkJMDqL7eKLX68ENDALIGbsZF0MwKv06CoJjLwOwoFFRnMmuHMjNxtSgOEnJqLv/yOuM/aZI6kG9vV2WB4v6ZOLF00hJ0Mn/BBepyzhzgxRfVdbuysqw7gCqhBMyvA0jXjUlynA4gwbqd4iiB9CsId3WpyzDCX0eHEnyE0aPdRR35jvkRJpMIgg4TLG/X/fBvfysV/O32KW4h0IAhAJV78i+/nYJZECoH1dYFTPaF9fWlnykrIiCJBAUgQggh8bBsWfFE9NvfTsa1ERSns6JO1n+7A/kkHUBJCkDvvKOyhsw4OYCA4jKwpB1AQTMr/DoJgiIC0LPPlq4rOfs+e3ZphzIzQTNG3GhuVuNN8pn++ld7l4Lf/B9AvZa0g3/9dcOpYyfUBJ3M77MPMGOG2iY//am6r2/f0m3klt2SJQdQFtrARy0B27bNKDWJMwNIsApAcZRA+hWEZT8exgG0fHnxuDRnydgh7+HnOxa3AyiKq8ra/fCcc5Qo9O1vq//PnGm/T/EKgc7K5N8q+FAAihe3/RMdQFUBBSBCCCHRyeeBc88tPVhNyrURFLuzok7W/7RLwJIQgCZMUAfxHR1GKK/g5AAC0hWAwmRW+HESBOWQQ9SEdts24JVXjPuDnn1vbga++93S1w/ToriuznCi7bGHvXAkk1fpAuWFOQfILQA6zGReAuBFjBHhzLyO3EKbZaIdJgQ6bgeQXQlYnA4gXY+3C5idACQT4sbG0vKtMHgJQHGUQPp00elHHKFuhhGARPgUvASgMA6guASgOFxVZnI5o9xV0+z3KZVYAgaUOoLSxk8XsEpqA+9WDpuVMUAiQQGIEEJINOLIf0gD61lRJzeGWwi0XV6KG24h0EkKQDU1zkHQbg6gSZPUZRoCEBAss8JMnGUWuRxw/PHqupSBhR3TMjGeNctbaPRCxqFZiDQTxAEE+BeAgk7m83ngj38s/b9VKJNJdFtbqbNFRKEgJWCV6gDavdsYQ3F2ATO3gY9732IWBOrqSgWCOEogfZbr6iJ4htnu775bfNtLRArjAIpr3xSHq8qKfA4n4atSBaCsOICqpQuYWzksHUBVAQUgQggh0Yj7TGW5MTuAZKIW1gEkB9LLlpXmxyQpAAGGAGTOAerqyk4JmGB2Z33ve/6eEzQ/yAtrDlDYMb10qbo8/nhvodELOyeaGZnw+xWAJAjaSwAKMpkPIpQNGGCUtVkn3lEcQHEIQB0dSpgCks8AMr+GU6lNkBIwEUTMZV9JCkCDB5eOjTBZa3b4Kdc1lxIG7f4kApCIZn5LwPyMy7hLwOJwVVnxEoD8ZgCVWwCS8S2ZdVkRgHpDCVhWxgCJBAUgQggh0UjiTGU5kQPqXbvUmbBdu4wDzCACUD4P3HCDuv7yy6X5MUkLQHZB0Bs3qgNQTbOfOIgA9MEHxvIlLQABhjvrxhvjCVMOighAL76otnnYMf3mm+pSSqKiYOdEMxPUATRlilp/69YBS5ao++wEoCCT+SBCWU2Ns2gTJgQ6zomIWZRJ2gEk79W/vyGIWTGXgJlFDrsuYIMHG68joqDsr+LI/zEvj7yfHUGz1pzwKtftFmO0jg57Z6UbIgBJw4IkSsDi+p2LK1jejOwrtmyxd+R6ZQCJ8Fjuyb+Mb/mNowAUL34ygLZvNwLZScVBAYgQQkg0kjhTWU769zcOctasMdw/jY3+J6iSH2N1OpjLYsohAIn7Z+RIe7u6CECrVxtugqSWz464nARB2WsvVf7W2Qncdpt99zQ7zGO6q8twAE2ZEn2Z4i4B699fBTYDattqmrG9rfidzAcVypyCoMOEQIsIsm2bCvCOUmIqEx67rjfm94rTAeRU/gUUOzDME0Y7B1AuZ4wByQFK0gEkwpsdQbLW3HAr1x0wAF1OTjIvJAPosMPUZZZDoOMMlhfkc+i6vYhTCSVghYIhdIrQXgkCULVlAJmzzEjFQQGIEEJINJI4U1luzOU35vIvP2HFfstipMQqaQFo2TJjcuwWAA2o0gjzxHTwYKChIZnlcyIuJ0FQxA1z3XXAD3/o/li7Mb1ihXIk1NcrQSkqcQtAgNEJDFDuELfMCj+T+aDib1wOoHweOPRQ4/YJJ0TrOOg24QGM78TOndHPevsRgMyOG5mU67q9AASUBkGLABSXA8haAuaG36y1sGgaOmTdBSn/27VLudGAZB1AGzbEl3cn+0JrkHfYfWF9vTHu7D57JQhAmzcbv6NS5lwJAlAlOYDcMoAaGozfDeYAVSwUgAghhESjXK6NJDGX3wTN//FbFiOuiKQEoEmT1MFaa6vxGdzyf4BSV0ga5V92xOUk8Es+b+T/eOE0pqX8a//9gdra6MsUtwCUzwNPPWXcXr/eWzTxmswHFX/jcACJu07GshCl46DbhAcoFobsOvoFQSbPHR2luWBCXZ2xTiUIetcuQ3zyEoBkQpxUBlCZ6RGAgjiAJPdq6FDDCRdnCPSwYaoUr6sr3q5Uzc3G9r3++uj7QrccoEoQgGTdDh1aLLqVE3H1VEsItJtIrWnZGAckEhSACCGERKdcro2ksHMA+e0A5rcsRiZ2SQlAtbXAvvuq69IJzMsBBGRDAAKSdxII4tjyS1OT/ZiW8q848n+AeAUgEU2sZ2yjiCZAcPFXxAPzxFvX/YftJtVx0E9bdik7ipIDlM8DX/iCur5yZWkumKBppZ3AZNtpmtFdUHByAFWrACSfP4gAJOVf++xjjLPW1tKgbTNBHEC5nOG4+v3vncW9oGzYYOy3/+3fou8L3QSgSgiBNudbyfoutwAUxAFU6SVgADuBVQEUgAghhMRD2q6NJIniAAqSddTQ4HyQFQfWTmBeDiAgOwJQWng5tgQpn/rqV+3HtDiA4sj/AYwxuGGD/VljvwJQUqKJEET8lYm0uXRn507jvb3EhaQ6DnpNeDQteg6QiHDmdu2Aswhn7QRmbgFvFducHEBphkCnSHsYB5AEQE+erLaliChOZWBmYdKvyCqvdd11zuJeUF59VV3KckfFjwPIKQRaBKDdu8snZDgJQEE7wsVJkAygSnAAeTkisyAEkkhQACKEEBIfabk2ksbc0SWoAORVFgMYE+GBA5PtpGENgpbJs5sAZHY6dXTEl2eRVfw6tg45RF2+8or9/+N2ADU1GZMGu2BZvwJQUqKJGb/ir50DSK7X1TlPPAW/2+qZZ4B77/XvwvCa8Jj/F8YBFEaEM3cCA+w7gAnSCl7EpWp3AEUVgDTNuyX67t1AW5u67uUAEnHPKopEddgBwOLF6nL69PCvYSZKCZjZefbYY+X5bbATgHbvjl6aGYVqywDyckTSAVTxUAAihBBCrJjLbz76SF33KwC5lcUIMnHZsCGes8ROOAlATiVg+Tzwgx8Ytx98MNnlywJ+HVvSOejll0sn8p2dRpldXA4gTXNuLd3WZkx4vASgsC3tg+JH/LVzAJkDoL1C1v1uqx/+ELjwQv8uDD/BzFEcQGFEOKcSMGv+D1DsAOrqMpxA5QiBToHIJWCAtwAkr53LuTtvknbYZUUAyueNdQcAZ57p/d0qFJQIG0SM9cIsbvbvbwil5SwD620CEB1AFQ8FIEIIIcSKTDRXrDAyWPwKQIBzWYwdcZwldsIsAOm6ewmYnMWWyWMay5cF/AYZf/GLqmRvyxbggw+KH/PBB0qU6dfPf1aUH5xygGRyWlPj3pYbCN6pK0lsQqA1mUT4yVnx466z4mf8epWAAcZkKIwAFEaEs5aA+RWAtmwxJtpyf1SqQQAyO4AAQwhxeg1z/o/beEvaYZcFAUh+G6yf0+27lc+rfeHs2cHEWC/MDiBNy0YOkDi/ekMbeIAOoCqAAhAhhBBiRSbDH32kDuAbGoKXU5jLYv70J+ez8XGcJXZi771VGPSOHcqhIuUrVmEq6bPYWcZvkHHfvsDBB6vbL79c/Dgp/zrgACMsOA6cBCDz5NTr/YJ26koSuzbwfgOgAX/uOit+xm/SJWBhRDinEjAvAUgcEkOGuE9Ig5A1AShoCdjWrYZAIC4WGW9eDqByOuy2bjXEZtn3REU+jzWLCrAPgQ7z2xBGMPKLNd8qCwKQuHqqpQsYM4CqHgpAhBBCiBXrhG3ixHATeymLGTvW/QA1jhwWO+rrjQmPtDkfPLi0i1AaOTFZxm+Q8aGHqkurABR3ALTgJQD5CacN2qkrSezawIsY5FdYCOKuE7zGb9IlYGFEuLAlYCIAxVX+BRQLSR9+WHYhOHAItJR/jR5tbGO/JWBewmSSDrvXXlOXe+zh77vuB8mL8hsCHfS3IemTCVYBSE7MZEEA6i0lYHQAVTwUgAghhBArjY3FBz9Byr/sSCuHxQ7pBPbUU+rSbuJczuXLCn6CjJ0EoLgDoIU4BCAgWKeuJLEJgdZEAPLjABKs2+p73/P3PKfxG6QELIwDyCzCWXES4dy6gFkxC0AyEY4rADqfBy6+2Lj99a+XPRcscAmYtfwL8BaA/LaAT9JhF3f5FxC8BCzob0PSJxOsAedZcgBVmwDktD+kA6jioQBECCGE2CGTbyC6AFTOHBbJAZo/X13a5f9kKSemnHgFGYsAtHhxcZZD2g4gKd8I4grw26krSexCoIM6gATztjrhBH/PcRq/fkrAoraBb24Gbrih9H4nES5IFzARgHbsUJNrIB4BSEp5rJPrMueCBS4BCyMA+S0BS9JhlwUBKOhvQ9InE7JcAlYtGUBe+0M6gCoeCkCEEEKIHeYD36gCUDlzWEQAkq5RdgJQlnJisszeeyuhoq0NWLJE3dfebkwws+oAEvx06koSEYBaWowSkDAOICtRx6+fErAoDiBBJqtHHOEtwgUpARs0yNiW0o0uaglYhnPBAgtA1g5gQLAQaC/EYTdqVPH9UR12aQpAum6fAeQneN383UryZEJXlyF+V5oAVCkOIF1nF7BeAAUgQgghxI6RI43ru3ZFm+iUM4dFBCDBrgQsSzkxWUbTSsvA3n1XtYEfONBeXIuC01n1sAJQuTG7fLonD5q5DXxYoo5fPyVgUR1AgCHOHH20twgXpAuYphnZLvIeUR1AGc4Fa5cSMLOTzI0kHUBCc7MS84R8PprDbudO4O231fWkBKCuLuP+9nZD2DNnAPkJXv/619U4uPde5TJ0E4uinEwwL7O43rIgAPnpApYlAahQAObNU9tr3rziY5v2dvV7BtABVMVQACKEEEKs5PPAY48Zt2++OXruRblyWCZPLj4g37nTXszKSk5M1rEKQObyryDtyf0gDqBNm5TrSKhUAaiuzggglwl2HA4gwHn8DhniPX6T7gImiDgjuVxuBOkCBhgT4rfeUpdRHUAZzgXrcQC1thrrxwldtxeAvLqABXEACQ0NhhC3zz7RBPPXX1fLPmZM8cmIqMjn6eoqHssiNAKlbeCdvlsyRv/934127//yL4aQFPfJBHOHOympknEu/ysHfrqAZaUELJ9XxzKyvWbPLj62MQvcdABVLRSACCGEEDOSe2E90x9H7kU5clgef7y4g9kttziLWVnIick6IgD985/qMqkAaEBNdBoa1HXzRLtSBSDAcPrI5CEuAQgoHr8yZo84wnv8Jt0FTAgiAAUpAQMMAUjGRlQHUIZzwTr79oUu+zSvMrD165XQUVMD7LmncX/cDiAhrq5USZR/AWpcydgyf3YRgGpq7IUMu9+G229X/3Nyx1rX3YgR0U4mWPN/zNfL5QAqFIzPXy4HkJujx4wc21idfeZjGxEF+/QBamvtX4cOoIqHAhAhhBAipJF7kWYOixzwWZfXTcwqd05M1pk5U10uW6YOgJMKgAbUGXO7HKBKFoC6hR4p/dLChkA7IeP3Bz9Qt+fM8T5TnXQXMECNFdmG++3n/fggJWCAIQAJUQWgLOeC1dTYdpSzRdw/EycaYioQXxcwK3E5UhYtUpdxC0CA/Wc3B0A7bXPzb8MxxwDf/77ze2iaeq2nnwYOPljdd8UV0U4mZFEAMjt6yiEAeTl6BL/HNrKvdBPD6QCqeCgAEUIIIUKGcy8Ck+EQ14pm1ChgwgS1DhctStYBBFSfAGSduMfpADJz4IHKadPeDjz0kPtj0+gCJnkuo0b5E7usDiC3NvBAqQAUtQQs67lgMl78CkDm8i/A+O60tBiZJ2aq1QEEGGVqEqgM2AdAu+Hnt/KTT9T4+Nd/Vfc9/njwZTUjopqdALRzZ3EZW1qYBZ20BSA/jh7B77HNP/6hbruJ4bIP2r27/CVtJBQUgAghhBAhw7kXgakmMStrSBnY/PnA+++r60k4gIDqE4Bk4m4tAYvLAWTm859Xl3/7m/Nj/HS9Mf8vrAMoSPkXEKwNPBC/AwjIdC6Y7tcBZNcBDCgeb3Zh0vK6YR1AUQSg1lZDWE7bAWQOgHYjyG/lqaeq6y+9VCw6BUXWqXlsDxxolKwFWed+y6a8MAs6fjOA7E7KBCXoCR6/20uOGdz2hWYRmmVgFQkFIEIIIUTIcO5FYKpJzMoaIgD98Y/qYLupKZ4Jtx1VKgBpW7ZA6+yEtnNn0f2xIgLQk086lyuYu94k2QUsrAAUpgTM3BUsKlnNBQtaAmZ1ANXWGuvSWgbW1RXeARRHCdiSJWriPmxY/J0FAe8SMD8E+a2cMAGYOlWt1yee8L+cVuxKwDQtuOvKb9mUH8QBk8u5u+HEAaTr8bhug57g8bu9ZPu7CUC1tYZQSAGoIqEARAghhAhZzr0ISjWJWVnjsMPUpbR9HjeuuKVynFhbwXd0GAfdcU3y00Qm7lu3ok7EH8DIlYiTAw9UeTvt7cDDD9s/xuzokQ5ldkR1AEkJmJ/8H6C4BKyjw5ig+xGAmpriLc3KYi5YVAEIcM4B2r7d+D4HFSbjKAEzl3/F3VkQiEcACvpb+dnPqstHHw2+vIKdAGS+7WOdaw884L9syg9+OoABxeVhcZSBBT3B43d7TZigbrsJQABzgCqcsgpAN998M2bOnInGxkaMGDECZ555Jt55552ix+i6jhtvvBFjxoxB3759cdxxx2Gp2CIJIYSQOMl67kUQqknMyhoff1x8+/XXw59B9sLqADKXqyRRNpU0MqHeuhV14qYZODCZ75SmeZeByTL07eu+DOVyALW2FotOTi4lsxiYlBstQ+h+MoC6uowSTWsJGOAsAMntPn2M7eCXqA6gQgF45BF1vakpmYy2OASgoL+VIgA98YR95pIfZJ1ax7dfAahQQO6aa8Ll4jmVjImY45b/Y/1/HAJQ0BM85u1lxby9JAvKzQ0JsBNYhVNWAWj+/Pm4/PLL8dJLL2HOnDno7OzEySefjJ2mM0I/+clPcOutt+K2227DwoULMWrUKJx00knYHvYMDCGEEOJGhnMvAlFNYlaWyOeBL3yh9P6wZ5C9sApAMmkbPLgyt123aKVt3Yr6JMu/BBGAnnhCuQ+sEzg/HcAA44x4R0fwCVx7O/DBB+p6mBIwmWT16eM80TQ7gKIGQFcCXg6gQgH461+Btjb1PbErpXISgMKWfwHRHEBSmiQC0L33JiMs233uoCHQQLDfysMPV9/zLVuAF18Mt9xeDiAP0a3prbegrVrl/ACnXDy3kjG/ApDZIRRHcLKc4HHC7gSPbC9zNzygeHv5CcQH6ACqcMoqAD3xxBO49NJLceCBB2LatGm4++67sXLlSizqbn2o6zp+8Ytf4Lvf/S6am5sxZcoU/OEPf8CuXbtwzz33lHPRCSGEVDNZzb0ISrWIWVmhHJ3VrAKQhKhWYv4PUOQAqhUBKEkn05Qpah22twOf+1zpBM7vhMf8/6AnId9/X42JxkZje3phLgHz6gAGlIpo1d7dz80BJBP2Cy5QtwsFYK+9SoUU+Q5ZXyNsC3ggvAMoSEenqMQRAi34/a2srQU+8xl1PWwZWMQSsD5e5YKCubzKa7tIZzMvAUjT1DoA4nEA5XLAd77j/F6A/Qme5ubijpX771+8vfwE4gN0AFU4teVeADPbulXEod07puXLl2Pt2rU4+eSTex7T0NCAWbNm4YUXXsBXv/rVktdoa2tDW1tbz+2W7oHZ0dGBjgptVSfLXanLT8oDxw0JA8eNhaOOMq53dSWX85Ikp50GnHoqtAUL1IHt6NHQjz5aHRjGtJ17y7jR5s9HrY/gzc65c6HPmhXPmw4fjjoA2LoVHdu2QVu/HrUAuoYMQaEC17fW2IhaAPrmzajvnmx0DR6c2GfRHngAudWrYS2E1LsncF3XXYccAL1/f3R6LENtnz7QWlvRsWWLuxhjXYYlS9Q223dfFHyWv2i1tWo97d6NwubN6npjo+0yag88gNw3vmF8xvnzoU+ciMKtt0I/6yzfy1kJyD6mc+BA5AB0bdpUNHa0Bx5A7vzzAV0v2uayvQv33dezTmoGD0YOQGHDBnSZX2PDhvDfsSFD1Pd182Z07N5tTPrdKBRQ+/WvlyyzWnAduqYBV12FzlNPjcX1pw0cqD6fad3V7Nih1mdDQ7jvoo/fSu3Tn0btvfdCf+QRdN50U7DX7+pC7caN0AB0DB5c9NtVM3SoWvZ16xyXvaOjA60+Bb3O4cOhd3T42y4//Sk0AHp9vff+o74eWmcnOnbuDP/bWyj0/JbX/PGPqAGgNzRAM8199bFjUbjlFuinnWb7PrWbNvV8Hv2jj9Ryd2+vmpYW9Z3o16/oO2El19iIGgCFzZtdH1fJVNpxTZDlzIwApOs6rrnmGhx99NGY0t1Kde3atQCAkSNHFj125MiRWLFihe3r3HzzzfiP//iPkvufeuop9AuqameMOXPmlHsRSAXCcUPCwHFTpQwcCOzcqboiJUC1j5uxzz2HGT4e99rjj2OVOeA4CrqOzzY0oLatDfPuvRdNb7+N6QA2Fgp48bHH4nmPFGl6+20cDWD36tU9IdDrWlvxchKfpVDAyV/7GuymzJquQwfQ+atfIQdgc2cnFngsw2fq69HQ2ornH3sM2ydO9L0Ykx96CPsD+KSxEa/6/JxNS5fiaAA7Nm7Em888gyMAbNN1zLc8f/SLL2Lmf/1X6QusWoXceedh4be/jTVHHOF7WSuFN1auxEwAm5cvxz9kncj2tpmwy/Zuv/xyzKmtBXI57L9pEyYD+OjVV/Gmab1OfP55fArAuvb24OOyUMDpmgZN1/HMX/6CNh+iQ9OSJTjapTRJ03Xgk0/wz5/9DJumTg22PHbv9957OBrAzpUr8Wz359v71VdxIIBPNm/2PUaDUldTg1M0DdrSpVj2ta+hZeJEbDrgAF+iVn1LC07pFikeX7gQuqmkauLatWp7LV3qvr0OOAC7m5rQxySAmNEB7B42DHNaWoDHHvO3XbqdXjvb2/GMx3o7FUAdgPlPP42dVleuD0a/+CKm/u536Csu0O5lXnLxxQCAg+68E7uHDsVTv/ylWqcOy/PZdet6BABt9248d+ed2NFdTjbtrbewB4B3V6/Guy6f51PbtmEigDV//Ss+2rbN93asRCrluGaXlHH6IDMC0BVXXIE33ngDCxYsKPmfZsku0HW95D7hO9/5Dq655pqe2y0tLRg/fjxOPvlkDAxwtiZLdHR0YM6cOTjppJNQ55UyT0g3HDckDBw3JAy9Zdxo/fsDt97q+bhPnXIKpsXlAAKQGz8eeP99zN5335626cMmT8app54a23ukxvjxwHe/i/7t7T0h0CP32y+Rz6LNn49a02Sp5P8AGrrLq4aMH++5DLVNTUBLC46dPh26dILzQe6++wAAY084AaN9fk6tO0tmQG0tZu67LwBg4LhxxctYKKD28st7PkvR8wHomoaZf/4zOm+8sWomZ7KvmXrsscBPf4omTetZJ362d7+NG/HZgQOhz5qFmrffBu6/H5MGDsQE03qtefNNABHGZVMTsHEjTjjoINX+3APNZxnN4RMnQo/jezJuHHD99RjQ3t7z+Wq64zfG7r237zEaFO2BB1QWTns7Dvrd7wB0u1X8ONW6Q9T1wYNxyhlnFL9ueztwxx0YWVPjuL1k3NT8938DF12k5pKm/+vd88r6X/8ap552mnrdAOVN/QcP9t5/9O8P7NqFWUccoUpTA6A98AByP/mJbfnx1LvuQuFnPwMA9Onq6ll+W3bvRm1rKwBA339/aMuWYdagQT3jKtcdsTJ5+nTs7fB5tAceQO7llwEA4xYswLgFC/xvxwqi0o5rWgKM10wIQFdeeSUeeughPPfccxhnCrQaNWoUAOUEGm1KO1+/fn2JK0hoaGhAgzXcCkBdXV1FbDw3quEzkPThuCFh4LghYaj6cTN7tpo8rVplnwOkacC4caidPTveCfeYMcD776N2/fqe0M2aYcNQU4nrWvI6tm3rEYBqhg5N5rMECOKtaWz0XobuXIza3bu92z6b6W5FnpsyBTm/z+t+L621FbXdZ3ZrBg0qXsZ//EONRQfEOVL30kuqfXsVkeseR9rWrcY+x+f2rt2wQW2/7teo2bq1eL3Kd6ypKdy4HDEC2LgRdVu3+hsn48f7etna8eODjTsnuudQ2ubNqKutVfut7lya3IAB/sdoEPJ5oLs0z4y2ejVqzz/fO5Ouu/uhNnx46W9M9xyxZuNGz+1Vc8450J55BrjzzuLlGDcO+MUvUGteBp/bBQC0hgbv377unKA6XQ+2HQsF4JvftP3NERGrtvvEhLZ1qypBdHr9deu6n1ALbdYsYNky1L75JtDtIpIw8NygQfbjIMx2LBRUsHZ3CTqOOaaiBOlKOa4JsoxlDYHWdR1XXHEF8vk8nn32WUyaNKno/5MmTcKoUaOKrFft7e2YP38+jjzyyLQXlxBCCCG9mXJ1VpOTYGvWGMGtFR4CrXV0GKGsSXUB89sqGfDuAmZ+TJBW8F1dwNtvq+v77ef/eXZdwKxOdnNYrRt+H1dJ2HUBC9oa2ykEOkoXMCB4ELR0dHKobrDt6BQF+VydncZYDtoGPghxhOc7BUADwTqv6TqwcKG6fuih6nLvve2Dq/1sF+m+5xUCbX5M0BDo558vDaE2o+vFQrCLC65nHQ0bBhx8sLr+2mvG/926IobZjm4d1EjZKKsAdPnll+NPf/oT7rnnHjQ2NmLt2rVYu3YtdnfvhDRNw9VXX40f/ehHeOCBB/Dmm2/i0ksvRb9+/XDhhReWc9EJIYQQ0hspR2c1cyewSheA+vfvEcj6d2c9JiYA+ZnAiaji1fXG/JggXcA+/lidVa+rU52o/GLuAuYkAAUVPKoJGTO7dhkT6qBCilcb+LDjMmgreBGWnVyFQLzCct++Ritw+exJCkB+BAy79utmREyTdWtGRKGWFsAUhmyHtngx8MYb6vNLEHVrq/26NQv+JS/UvV0uvVRd+hGAxKERNFTYr4Aroo3buNu4UV0OGwZ86lPqulkAcuuKGHQ7ptnZjgSirALQHXfcgW3btuG4447D6NGje/7+8pe/9DzmW9/6Fq6++mp87Wtfw4wZM7Bq1So89dRTaPRzpoYQQgghJG78tj6Oi2oSgDStZ2LdTyZ1SbWBd3NsCcceqy6DCEDz5qk/P63Wu7NLsM8+/jpCCeIAam/vKUkqOSuftnMkSwwaZHxuEWz8TNjNQooIPFYBKEobeCBcK/jmZuWQsJKEsKxppeJXkgJQHE41NwfQ4MHGd0sEDge0u+5SV84+G5g82XhtO/ENMAR/a7yIbJfp09XtJB1AfgVc2Y+6rQOzADRlClBTo8rCRIx3awMfZDvG4foiiVH2EjC7v0tFTYVyAd14441Ys2YNWltbMX/+/J4uYYQQQgghZSGXU7kqF1ygLpPMNKgmAQjomVgnXgIGODu2AFWOIO2qN2xwn4zk88ATT6jrd9/tv5RByr/23z/YcosABBhCgtUBVK6SxCxQU6NEIKC4hEu2t3VM2QkpZhHEPFGNWgIW1AEkiNPr8suTF5atApB0EEpCAIrDqeYmAJlLsVxEt1xrK2q6A9nxla8Yr9XW5l7W2dysysTM3H+/ul/EHD/5K2EFIL9Cr3Qm9OsA6tcP6A6Y73EBuZWABdmOcbi+SGKUVQAihBBCCCEe2AlATU3lW56oWB0/STmABKtj6xe/UPc/+6zRKvnOO50FHSllsLbZ9VPKIA6gIPk/gD8BCChPSWJWsMsBAtRn/upX1fUTT3QWUkQEKRSKy/rK4QDSdeCll9T1L3wheWHZyQHUr1/87xWHU81NADLf7yJ+jPnHP6Bt365KMWfNUuWo8nm9tpW8ruTVSj6tiDlBSsCCCkB+nW0iPPp1AAGlZWBuJWBBtmNvzierACgAEUIIIYRkmSp1ADneTgKzY8upu4+doBO1lEEEoKAOoNpao6zFTQAC0i9JzAoybqwCEKDWBwB85jPOQkrfvobQZn6NcjiAPvxQTc7r641JeZKkWQIWh1PNLQMIcBeACgVo8+djn/vvV7f/5V+Ug8zreabn9wgnX/yiunz8cXUZRACSxwTNAAIMode6/sxCr4g6fh1AQLEApOvuJWBBtmNvzierACgAEUIIIYRkGTlI3r49+uQ0C6TtADIjgo4ddoJO1FKGsAIQYIgT0rrZSQAC0i1JzApuAtCHH6rLPfd0fw2rENLRYbgg0nQAvfiiupw+vTRvJgnEQZiGAAQ4O9XGjvXnVAvrAOruQlV70kloXL1a3ffrXxsirx8BaNMmVSqqacqdBajttXVrOAEoqANIOP54Yx91112lQq98liAOoGnT1OVrr6kwbCmJdcpE8+s47M35ZBUABSBCCCGEkCzT2Fh6QJ6GayYpyuEAEoIKOlFKGTZuNCZckrURBJmMy2u4CUC9ETcB6IMP1KWXAGQNgt661fhfWGHSj6hgRcq/jjgi3HsGRYQvaRmetAAEGE61Z54xyqGeftqfUy2MAOTUhWrtWsPp52dbiZDX1KTKx/bbTwnEzzyTrgC0fLm6HD5cuZisQm8UB9C77xpCM6DK45yQ7Xj11er2YYeVOg6DBrKTVKEARAghhBCSdaQMDFCCkJ/Q0axiEnz0hoZkJ51Wggo6UUoZJAB6wgT3CZUT4gCSs/LsgFuMkwC0bZshbAR1AMnlwIHBuraZkTKlLVv8l/uIA+jww8O9Z1DSDIE2k8spJ4t04JJSPTe6ugzhwq8A5Ld0049oYi0/+8xn1OXjjxvbN8k28IIIQJJDZMWPmGUVgEaOBEaNUuvkhRfUff36eQszuZwS0QBVOmv3+OZm4G9/K3UBjR5d/flkGYcCECGEEEJI1jELQJVc/gUUOyvSLP8Cggs6YUsZCgXgwQfV9ZEjw7U7NgdBA3QAWXESgMxOCS/RzCqExFFiOXSokTHj0ZYcgBJfXn9dXS+XAJRkCLQde+2lLsWp5caWLcb3x0kAsuYu+XX6tbWp227leuKMkfc45RR1+cQTxvOT7AImyLh2EjVF1AlSAgYYLqAFC9SlU/mXFenK/cknxjiycuihal3X1CihCQD++78p/pQZCkCEEEIIIVmnmgQgc8lX2gJQUEHHLfhUsJYydOeO4JZb1O2FC/21jLdidWNQACpGxpG5bAvwn/8DODuAopQl1tT4c5YIixYpgWPMGOeA8rhJMwTaDhGA3n/f+7GyDgcNcnbaWN0vfp1+8r314wAaOVJdHnusWk+rVgGLF6v70igBk3Ed1gGk6/ZOKqsA5NdpOGiQ2q8BwJIl9o959VV1eeCBwGc/q66/8oq/1yeJQQGIEEIIISTrVJMAZBJ99LQFoDAdiZyCTwHgu98tPpvtlDvip2W8FTqA3HFyAPnN/wGM75K8Rlwh60GCoM3lX04iY9yUWwDae2916ccB5JX/Y/6fPNav008EtyAlYH36ALNnq+vPPKMu08wAchKAzA4gu9K3HTuM97ZzAL35prr06wACgIMOUpdvvGH/f2kvf/DBKisIAP75T/+vTxKBAhAhhBBCSNapJgHI7K4oR5i130421ueYW61//vPq/scfNyZbUVvGWzELQJoWLkeomnESgMQpIS4TN5xKwKKOyyCt4CUAOq3yL6D4c+t6+RxAcQtAItaI088JcfodeWTxe9hh14JecoCkBCyNDCAvZ5uIOh0dQEtL6f/F/dO3b3GpnwhAso9KQgD61KdUORigHJGSa0bKQsh0M0IIIYQQkhqSnwCodr2FQuV2UDG7fgYNKs8yNDcDZ5yhskLWrFGOgWOOcV+n0modAE48EXjsMVW+85//qSa069b57zAmr+OGeTI+cGB67pBKwUsA8uMAsnYBi6MEDPDvANJ1wwGUVgcwoFgAam017i9HBlBXl5GZZIedAGNF1vfWrUoAqatTTr+zzy59rNnpJ06hoAKQ5AAJq1Z575OjOIC6uozAbCcHUL9+6m/XLiX2WPetdvk/gHJjyfOAcAKQVwnYwQerMrB+/YDt21VA/gEH+H8fEit0ABFCCCGEZJl8XjlLhIcfDpcpkxVMpUz6rl3hApLjQASdCy4obansxfDhhgvg+uuBCy8EvvENf8/1m09idgCxA1gpcZaAxRkCDfh3AK1cqdqS19YC06dHe88gNDWpy7Y2o2MakJ4DaOJE9X1rbfX+PvhxANkFb0vJkRWz088s1Nk594DSEGhAOV7M+4u77vLeJ0cRgNauVduqpsY9J8otB8hJAMrlDCEHCLavMQtAVlfP1q2GaDVtmhrjM2ao2y+/7P89SOxQACKEEEIIySqSKWM9oA+TKZMF8nnVBrqbXKWKWfl8+GX2m09iFoCY/1OKnQDU2QmsWKGuhykBS9sBJOVf06al574BVDmhlCStWqUua2vVXxrU1SkRCPAuA/MjANXUGKKWPP4vf1GXRx6Jzjlz8Mo116BzzhyVpSNlnvKara3Azp32r20NgZZ9slW49tony/oOIwCJq23CBPeOY26dwJwEIKBYANq+3b8ov/feaj+1a5exjIKUf02caHyfpAyMOUBlhQIQIYQQQkgWiTtTptzIxGn16uL7K03Mctsubji1jHfCWgJGipFJ5Y4dRq7KJ58oEai+vjg3y4mkQ6C9HEAiAKVZ/gWosSifUcoW03L/CH5zgPyUgAGl6/zPf1aXF10EfdYsrDr2WOizZhU7d/r3N4RWp21lfv8o+2RxAIXJAPIKgBbCOIDyeeCvfzVuP/mkf1E+l1OlXUBpDpA5AFoQVxYdQGWFAhAhhBBCSBZ5/nn/mTJZp5rELK/tYodThzE36AByx5xxIq3gza2y3XJlhKQcQCJWeDmAzB3A0iYrApBXK3g/DiDz/zdsUBkzixcrR9O55zo/R9PcRZOdOw1n0IgR0fbJUUrAggpAfh1AIsrL90cIIso7BUGbA6AFcQC98YYRPE5ShwIQIYQQQkgW8ZsV4/dx5aSaxKww69utw5gTFIDcqa018krEuSNuEj/lX4Ah9OzapcqA0nQAtbUZIbnlFICkBCzNEjTAfyt4vwKQOXfpnnvU9U9/2r7kyel5VkTA69NHhSNH2SdLed3bbwPz5gUTu/0Gm8tn9eMAikuUdxKAzAHQwvjxqqFBZ6cS6EhZoABECCGEEJJF/GbF+H1cOakmMcvv+v75z9VEdO7c4twRv7AEzBtrDlCQDmCAWq/iFNqyJX4HkJMAVCgAv/udcoMMGmTk4aSJVQDKaglYUAfQ+vVG+deFF3ovh1tek7n8S9PC75PzeeC//ktdf+45YPbsYNlnSZSAxSXK2wlAbW3AW2+p62YHkKaxDCwDUAAihBBCCMkixxyjnCNO7b+DZsqUk2oSs/xulyuvDNdhTGAXMG+iCkA1NcWt4ON2AG3dWlryk8+ryf8VV6jb27apiX3aGVhZEYDcSsA6OgwR5v333d0oss4feUSNg379gDPO8F4ON9HEGgAdZp8sZVbbthU/NkiZlV8BKEgIdFyi/NSp6vKDD1QeFwAsXapcPkOGlHYtYxB02aEARAghhBCSRXI54Je/VNetE44wmTLlpJrErLS2C0vAvLEKQEFawAsihKxerZwL5teNslyy/c2TcREDrM6LcgShl1sAkm20davhvDIjQpm0Fz/3XHfXjHQBk+yZ009XIc9e+BGAxNEV9LsfR5lVW5sxXrzGdRAHUFyi/PDhxmOWLlWX5gBo63qiA6jsUAAihBBCCMkqzc0qO2bs2OL7w2TKlJNqErOAdLYLS8C8EaHGGgLtNwMIMIQQcaLkctEdVzU1xkRbRISsBaGLYFKuEOj+/Q3hwFoGFrRjYD4P3Hhj8X1PP+1PUAsiAAHBvvtxlFmtXKke16+fdye0IA6gOEV5axmYXQC0MGOGeu3ly7275AmFgspNuvfe4PlJpAQKQIQQQgghWaa5GfjoI5UlEyVTptxUi5glJL1d6ADyxuwAkj/Au1TG7jVEhBgyxHlSHASrsJC1IHQRvlpb1WXaIdCAfQ5QUKFMxCKri2jTJn+uKre8pnXrih8j+P3ux1FmZS7/8hqXTmJWV5daH4AhAMUpylsFILsAaGHQIGC//dR1P2Vg4gSbPVtlOgXNTyIlUAAihBBCCMk6uZzKkomSKZMFuidOnXPm4JVrrkHnnDmVKWYJSW4XCkDemAUgmSiPHOmv9EewOoCiln8J1lbwWQtCt+Ycpe0AAuxzgIIIZXG4qvyGQFvx892Po8xKXG1+RE0Rd1pairOntm0z1oE4v4D4RHnJAXrjDSU2vf66um3nAAL8l4FlqWSyiqAARAghhBBC0iOXgz5rFlYdeyz0WbMqV8xKGpaAeWMWgIK2gBdECJHnRw2AFqxujKwFoWdBALJrBR9EKPMpFmkLFjg/JkgIdFDiKLPyGwANqO+DdLUzl4HJ9cZGoKGh+DlxOBnNDqAPPwS2b1fvs+++9o+XIOjHH3cu68payWQVQQGIEEIIIYSQrEEHkDdmAShoBzBBhBB5flIOoKwFoWdBALIrAQsilMXhqgqaARSEOMqsRADyM65ragyHj50AJA4hu+WM4mTcbz+gtlZlcT38sLpv6lSgrs7+8Tt3qstXXnEu68payWQVQQGIEEIIIYSQrFFfb1x/+22e6bYjTgFo167i21GxCgtmMcBKOYLQrZ8zKxlAQYSyOFxVsp127TLGgOCUARSEqGVWQUrAAHtBy0sAikpDg5Hr88c/qkun8q98HvjWt0rvt5Z1+RX3nnmG4dABoQBECCGEEEJIlsjngYsvNm5fdhmDT+2wKwELKwBZXzMqduHCzc3ADTeUPrYcQehZcgCtXm2ILyKU2ZX+WIUyn2KRfvTRzstgLosyb6tCwRBOoghAgFFm9eCDxn0LF/rb3kFKwAD7TmBJC0CAUQZmbgFvJUhZl19x74c/ZDh0QCgAEUIIIYQQkhUk+NRaksLg01LsHEBBM4Csgk/cDiBruLA4fGbPLm9Xv4EDi91G5RCAhg4FBg9W12X7AWpdHHBA6eOtQlkcJVaaZr+tNm9WgcZAPMJJLgeccYbhlFm40Ps527YZ3c2y7AACgClTim9LMLSZIGVdXuKeHdxH+oICECGEEEIIIVmAwafBEPFg40Zg5Up1PcsOIAD4xz/U5Vlnlbern6YVf/ZyCECaZl8Gtm4dsGyZun7ffe5CWRydrOxEExGDmpqcs2zCcOSR6vKFF7wfK+6fYcOUU8kP8lnSdADl88Cttxbfd8EFpUJMkMwmt5JJJ8LsIwsFVT7Wi8rIKAARQgghhBCSBRh8GgwRa3buVBO3Pn2AUaOCvYZVAErSAdTVBbz4orp+1FHxvE8Uyi0AAfat4P/3f9VYnzEDOO88b6EsaicrNwEoavmXlTACkF/3D2CIPGk5gMSxaBacAFXWZ3XjBM1sam4GvvrVYMsTZB+Zz6uysdmze1UZWW25F4AQQgghhBCCeLoa9Sasbp099zTaYPslKQeQiAotLUBbm8qZWbpUlfX0729kppQT82cvRwg0YO8Akgn42Wf7fx3pZBUGOwEojgBoO0QAevlloKPD3V0UpAOYkGYJmJdjUdOUG+eMM4ozm1atcs54GjeuuBPe6tXq8ktfAk48EXjrLZX744XXPlKEK+tydJeRaffdZ2RDVRl0ABFCCCGEEJIF4uhq1Juoq1NiihC0/AsoFXziEoAGD1atsQFjMi7lX4cdZvyvnGTBAbT33upSBKAtW1RnJyC9XCS7cr2kHED77qvG2O7dwOuvuz82aAcwIN0Q6KCOxaCZTbt3A08/ra5feaVygp1wgr9lc9tH+ii1zX3zm1VbDkYBiBBCCCGEkCwQpAU2UZgFmzACUF0dMGCAcTuuErCamtJyHBGAslD+BWRDALI6gB55BOjsVKHCkyenswx25XpJCUA1NcARR6jrXmVgYUrA0nQAhXEsOmU2NTWVZjbNm6e6w40bB0ybpu6LYx/pQ7jSPvkETW+95fqxKhUKQIQQQgghhGSBOLoa9TaiCkBAsRASlwMIMMQDERNkwk8ByEAEoI8+UiVR99+vbqfZFc0tA2jkyPjfz28OUJgSsDQdQGEdi+bMps98Rt133HGl2/zhh9Xl5z5n7P/i2Ef6FK76bNni63GVBgUgQgghhBBCskIcXY16E9IJDFBugTBlG0kJQGZhYe1aVdKjacDhh8f3HlHIggA0ZowK7y4UVOevJ59U95dbAEoqAwjwJwDpejQH0MaN6jU6O1VZHRC/ABTFjSOZTf/5n+r2I4+ofCxB19V9gBKAzETdR/oUrlrj3BdkCApAhBBCCCGEZImoXY16C/k8sHChcfu668J18ZGJXl0d8M9/xpf9Yc6WkfKvqVOBQYPief2omMWzt94qT+ZJTY3hcLntNqC1VbmC0gzJTrMLGADMnKkEkI8/Vn92rF2r1kVNDTBhgv/XFpGns1MJKlu2GFk3cZU3CnG4cQ4+GDjgAPVZxf0FAEuWqHXTty9w/PGlz5N95O23q9sDBqgyQj/7SB/ClT5uHDYdcID3a1UgFIAIIYQQQgjJGnKG3KsFdm9Fuvi0thbf393Fx7cIlM8DL72krnd0xNsK2pwtk7X8n3we+I//MG5fdln5WmCLAHTXXeryzDOdJ+dJkGYINKDECsm0cXIBiftn/Hj3TmFW+vQxMq02bDDKv4YMSSZ4PKobR9OAiy9W1//nf4z7xf1z4onO7rRcDvjKV9T/d+wA3nvP3zKLcOXUiQxA4ZZbqnafSwGIEEIIIYQQUjn46OKDq6/2drSIiLR7d/H9QUUkJ+wcQFkQgORzb95cfH9cnzvossybp67L9vqf/0l3GUSo27HDGAtJZgABxjhwEoDCdAATzDlASeX/mInqWLzoInU5bx6wcqW6bs7/caOuDjj0UHVdvmN+l9lu+bqFK/2ss/y/VoVBAYgQQgghhBBSMWgLFgRrP21HXCKSGyIsrFgBLF6srpdbAErjc/tFhKgdO4rv37AhXSFq4EDDZbNhg8qSkmVKwgEEuOcAFQrAs8+q65KPFARzSVsaAhAQzbE4YQIwa5a6fs89Snz75z/V7c9+1vv58p0KIgABxrq59tpeVWpLAYgQQgghhBBSOYRpP23FRytoTxHJC5mIP/ecymQZMwaYODH868VBGp/bD1kSojStWDQR909DA9DYmMx7igD06qvAzp3G/fm8KsW7+251+4kngpfmpe0AioMvfEFd/uY3wPe/r8bApz5VWlpmRxgBqL0dePlldf3LX+5VpbYUgAghhBBCCCGVQ9j202biEJG8EPdIe7u6POqodLNt7Ejjc/shK0KUYCcAjRiR3PYaP16JG4UC8Mor6j5xRFnXS9DSvHI4gKJSX68uV6wAfvtbdf3DD/195iOOUJfvv290b/Ni8WKVH9bUBOy7b/DlrWAoABFCCCGEEEIqBv3oo8O3nxbiEJG8sHZdkolqOUnjc/shK0KUIGLd+vXJBkALmmaMhzvuAJ55Jj5HVKUJQPk8cMklpfe3tPgTvoYMAQ48UF13ylSysmCBusyCKJsyFIAIIYQQQgghlUMc7ad9tIL2FJHcyOdVByMzP/5xebpsmUn6c/slK0KUYOcASioAGlDjYM4cdf0vf1FjJS5HlF0JmHy+rOFWCij4Eb6CloHJ444+2t/jqwgKQIQQQgghhJDKImr76ThEJCeklGf16uL70w43tiPJzx2ErAhRglkAkjKipBxAMj62bQv+XD+OqEpyAMVVChhEANJ1wwFEAYgQQgghhBBCKoCo7aejikh2ZCnc2IkkPndQsiJECU4ZQHHjx/Hihh9HVCWFQMdVCigC0KJFwO7d7o999121XhoagOnT/b1/FVFb7gUghBBCCCGEkFBI++mwNDcDZ5yhHAZr1qgJ9jHHhBcegjgaoix3VOL+3GGX4e9/V4KIeZ2NG6fEnzTbcZsFoNZWdT0JAchrfDihaWq9+HFEmT+LiGlZFYDiKgXcc09VsrdunQrVdltP4hI69FAlAvUyKAARQgghhBBCei9RRSQzWQs3diPOzx2WLAhRQHEItDhIkhCAwmz3oI4oswMo6wKQlAKuWmXvivIrfGmacgHl80rgcXt8Ly7/AlgCRgghhBBCCCHxkLVw40pAhKgLLlCXaYs/gH0GUBIh0GG2e9DSPPks27erTlpAdgWgOEsB/eYAmTuA9UIoABFCCCGEEEJIHGQt3Jj4I60MID/jY9w44Omnw+VaAcCgQcWCSS6n7ssqcWVSiaDzwgtAV5f9Y9avB957T10/8shwy1vhsASMEEIIIYQQQuJAHA3nnKMm8+aylnKEGxN/mF0zO3ao60kIQH7Gxy9/CZxwQvj3qKlRjh9xMjU1qfuyTBylgAcfDPTpA2zeDLzzDrD//qWPEXfQlCnAkCHxLHuFkfGRQAghhBBCCCEVRBa6bJFgDB4M1HZ7I0SUSapsKo3xYV72rJZ/WYlaClhfD8ycqa7feiswb15pt71eXv4F0AFECCGEEEIIIfGSlXBj4g9NUy4gCWkeMkQJCkmR9PgQRxNQOQJQVPJ54LXX1PXf/U79jRunHFUiqokDqJcGQAMUgAghhBBCCCEkfrLQZYv4xywAJREAbSXJ8VGJDqAo5POqrM7aSWzVKnX/X/4CNDYCCxeq+484Iv1lzAgsASOEEEIIIYQQ0rsxu2aSyP9Jk97kACoUgKuusm8jr+vq74ILgFNOMcKhjztOiUa9EApAhBBCCCGEEEJ6N9UkAPUmB9DzzwOffOL+GGsWkDiDeqEIRAGIEEIIIYQQQkjvppoEoKYm4/rWraUCSDUhZXtBELfQ1VdX97qxgQIQIYQQQgghhJDejVn0qWQBKJ8HfvAD4/bttwN77FG9bpfRo8M9T9eBjz9WDqJeBAUgQgghhBBCCCG9G7NrZtu2ynSGSBjy5s3F91dzydMxx6huX5oW7vlhHEQVDAUgQgghhBBCCCG9l3weuP564/bPf155rhmvMGSgOkuecjnV6h0IJwKFdRBVKBSACCGEEEIIIYT0TsQ1s2lT8f2V5prxCkOu5pKn5mbg738Hxo4tvj+Xc36OpgHjxysHUS+CAhAhhBBCCCGEkN5HNblm/JYyVWvJU3Mz8NFHwNy5wD33qMv77lNCj9UZJLd/8Qt3kagKqS33AhBCCCGEEEIIIakTxDVz3HGpLVYo/JYyVXPJUy5Xup3+/ncl8pm387hxSvxpbk5z6TIBBSBCCCGEEEIIIb2PanLNSBjyqlX2jiZNU//vZSVPaG4GzjhDiXhr1igB7Jhjep3zR6AARAghhBBCCCGk91FNrhkJQz7nHCX2mEWgXlzyBMDeGdRLYQYQIYQQQgghhJDeh1cL8UoLCnYKQx43Tt3fC0ueSDF0ABFCCCGEEEII6X1Uo2uGJU/EBQpAhBBCCCGEEEJ6J+KaqaagYJY8EQcoABFCCCGEEEII6b3QNUN6CRSACCGEEEIIIYT0buiaIb0AhkATQgghhBBCCCGEVDkUgAghhBBCCCGEEEKqHApAhBBCCCGEEEIIIVUOBSBCCCGEEEIIIYSQKocCECGEEEIIIYQQQkiVQwGIEEIIIYQQQgghpMqhAEQIIYQQQgghhBBS5VAAIoQQQgghhBBCCKlyKAARQgghhBBCCCGEVDkUgAghhBBCCCGEEEKqHApAhBBCCCGEEEIIIVUOBSBCCCGEEEIIIYSQKocCECGEEEIIIYQQQkiVQwGIEEIIIYQQQgghpMqhAEQIIYQQQgghhBBS5VAAIoQQQgghhBBCCKlyKAARQgghhBBCCCGEVDkUgAghhBBCCCGEEEKqHApAhBBCCCGEEEIIIVUOBSBCCCGEEEIIIYSQKocCECGEEEIIIYQQQkiVQwGIEEIIIYQQQgghpMqhAEQIIYQQQgghhBBS5VAAIoQQQgghhBBCCKlyKAARQgghhBBCCCGEVDkUgAghhBBCCCGEEEKqHApAhBBCCCGEEEIIIVVObbkXIGl0XQcAtLS0lHlJwtPR0YFdu3ahpaUFdXV15V4cUiFw3JAwcNyQMHDckKBwzJAwcNyQMHDckKBU2pgRrUO0DzeqXgDavn07AGD8+PFlXhJCCCGEEEIIIYSQ+Nm+fTsGDRrk+hhN9yMTVTBdXV1YvXo1GhsboWlauRcnFC0tLRg/fjw+/vhjDBw4sNyLQyoEjhsSBo4bEgaOGxIUjhkSBo4bEgaOGxKUShszuq5j+/btGDNmDGpq3FN+qt4BVFNTg3HjxpV7MWJh4MCBFTEASbbguCFh4LghYeC4IUHhmCFh4LghYeC4IUGppDHj5fwRGAJNCCGEEEIIIYQQUuVQACKEEEIIIYQQQgipcigAVQANDQ244YYb0NDQUO5FIRUExw0JA8cNCQPHDQkKxwwJA8cNCQPHDQlKNY+Zqg+BJoQQQgghhBBCCOnt0AFECCGEEEIIIYQQUuVQACKEEEIIIYQQQgipcigAEUIIIYQQQgghhFQ5FIAIIYQQQgghhBBCqhwKQBnh5ptvxsyZM9HY2IgRI0bgzDPPxDvvvFP0mEsvvRSaphX9HX744WVaYpIFbrzxxpIxMWrUqJ7/67qOG2+8EWPGjEHfvn1x3HHHYenSpWVcYpIF9thjj5Jxo2kaLr/8cgDc1xDFc889h9NOOw1jxoyBpml48MEHi/7vZ//S1taGK6+8EsOGDUP//v1x+umn45NPPknxU5A0cRszHR0d+Pa3v42pU6eif//+GDNmDL74xS9i9erVRa9x3HHHlex/zj///JQ/CUkTr32Nn98k7mt6H17jxu44R9M0/PSnP+15DPc3vQs/8+3ecGxDASgjzJ8/H5dffjleeuklzJkzB52dnTj55JOxc+fOosd95jOfwZo1a3r+HnvssTItMckKBx54YNGYWLJkSc//fvKTn+DWW2/FbbfdhoULF2LUqFE46aSTsH379jIuMSk3CxcuLBozc+bMAQB8/vOf73kM9zVk586dmDZtGm677Tbb//vZv1x99dV44IEHcN9992HBggXYsWMHPve5z6FQKKT1MUiKuI2ZXbt2YfHixbj++uuxePFi5PN5vPvuuzj99NNLHnvZZZcV7X9++9vfprH4pEx47WsA798k7mt6H17jxjxe1qxZg7vuuguapuHss88uehz3N70HP/PtXnFso5NMsn79eh2APn/+/J77LrnkEv2MM84o30KRzHHDDTfo06ZNs/1fV1eXPmrUKP3HP/5xz32tra36oEGD9N/85jcpLSGpBK666ip9r7320ru6unRd576GlAJAf+CBB3pu+9m/bN26Va+rq9Pvu+++nsesWrVKr6mp0Z944onUlp2UB+uYsePll1/WAegrVqzouW/WrFn6VVddlezCkcxiN268fpO4ryF+9jdnnHGGfvzxxxfdx/1N78Y63+4txzZ0AGWUbdu2AQCGDh1adP+8efMwYsQITJ48GZdddhnWr19fjsUjGeK9997DmDFjMGnSJJx//vn48MMPAQDLly/H2rVrcfLJJ/c8tqGhAbNmzcILL7xQrsUlGaO9vR1/+tOf8KUvfQmapvXcz30NccPP/mXRokXo6OgoesyYMWMwZcoU7oMIAHWso2kaBg8eXHT/n//8ZwwbNgwHHnggrr32WrpWietvEvc1xIt169bh0UcfxZe//OWS/3F/03uxzrd7y7FNbbkXgJSi6zquueYaHH300ZgyZUrP/aeccgo+//nPY+LEiVi+fDmuv/56HH/88Vi0aBEaGhrKuMSkXBx22GH44x//iMmTJ2PdunX44Q9/iCOPPBJLly7F2rVrAQAjR44ses7IkSOxYsWKciwuySAPPvggtm7diksvvbTnPu5riBd+9i9r165FfX09hgwZUvIYeT7pvbS2tuLf//3fceGFF2LgwIE991900UWYNGkSRo0ahTfffBPf+c538Prrr/eUqpLeh9dvEvc1xIs//OEPaGxsRHNzc9H93N/0Xuzm273l2IYCUAa54oor8MYbb2DBggVF95933nk916dMmYIZM2Zg4sSJePTRR0t2aKR3cMopp/Rcnzp1Ko444gjstdde+MMf/tATkGh2dQBqh2e9j/Re7rzzTpxyyikYM2ZMz33c1xC/hNm/cB9EOjo6cP7556Orqwu333570f8uu+yynutTpkzBPvvsgxkzZmDx4sWYPn162otKMkDY3yTua4hw11134aKLLkKfPn2K7uf+pvfiNN8Gqv/YhiVgGePKK6/EQw89hLlz52LcuHGujx09ejQmTpyI9957L6WlI1mnf//+mDp1Kt57772ebmBWNXr9+vUlyjbpnaxYsQJPP/00vvKVr7g+jvsaYsXP/mXUqFFob2/Hli1bHB9Deh8dHR0499xzsXz5csyZM6fI/WPH9OnTUVdXx/0P6cH6m8R9DXHj+eefxzvvvON5rANwf9NbcJpv95ZjGwpAGUHXdVxxxRXI5/N49tlnMWnSJM/nbNq0CR9//DFGjx6dwhKSSqCtrQ3Lli3D6NGjeyytZhtre3s75s+fjyOPPLKMS0mywt13340RI0bgs5/9rOvjuK8hVvzsXw455BDU1dUVPWbNmjV48803uQ/qpYj489577+Hpp59GU1OT53OWLl2Kjo4O7n9ID9bfJO5riBt33nknDjnkEEybNs3zsdzfVDde8+3ecmzDErCMcPnll+Oee+7B//7v/6KxsbFHeRw0aBD69u2LHTt24MYbb8TZZ5+N0aNH46OPPsJ1112HYcOG4ayzzirz0pNyce211+K0007DhAkTsH79evzwhz9ES0sLLrnkEmiahquvvho/+tGPsM8++2CfffbBj370I/Tr1w8XXnhhuRedlJmuri7cfffduOSSS1Bba/wUcF9DhB07duD999/vub18+XK89tprGDp0KCZMmOC5fxk0aBC+/OUv45vf/CaampowdOhQXHvttZg6dSpOPPHEcn0skiBuY2bMmDE455xzsHjxYjzyyCMoFAo9xzpDhw5FfX09PvjgA/z5z3/GqaeeimHDhuGtt97CN7/5TRx88ME46qijyvWxSMK4jZuhQ4d6/iZxX9M78fqNAoCWlhb87W9/wy233FLyfO5veh9e820/c6eq2N+Uq/0YKQaA7d/dd9+t67qu79q1Sz/55JP14cOH63V1dfqECRP0Sy65RF+5cmV5F5yUlfPOO08fPXq0XldXp48ZM0Zvbm7Wly5d2vP/rq4u/YYbbtBHjRqlNzQ06Mcee6y+ZMmSMi4xyQpPPvmkDkB/5513iu7nvoYIc+fOtf1duuSSS3Rd97d/2b17t37FFVfoQ4cO1fv27at/7nOf41iqYtzGzPLlyx2PdebOnavruq6vXLlSP/bYY/WhQ4fq9fX1+l577aV//etf1zdt2lTeD0YSxW3c+P1N4r6m9+H1G6Xruv7b3/5W79u3r75169aS53N/0/vwmm/reu84ttF0XdcT1JcIIYQQQgghhBBCSJlhBhAhhBBCCCGEEEJIlUMBiBBCCCGEEEIIIaTKoQBECCGEEEIIIYQQUuVQACKEEEIIIYQQQgipcigAEUIIIYQQQgghhFQ5FIAIIYQQQgghhBBCqhwKQIQQQgghhBBCCCFVDgUgQgghhBBCCCGEkCqHAhAhhBBCSJmZN28eNE3D1q1by70ohBBCCKlSKAARQgghhBBCCCGEVDkUgAghhBBCCCGEEEKqHApAhBBCCOn16LqOn/zkJ9hzzz3Rt29fTJs2DX//+98BGOVZjz76KKZNm4Y+ffrgsMMOw5IlS4pe4/7778eBBx6IhoYG7LHHHrjllluK/t/W1oZvfetbGD9+PBoaGrDPPvvgzjvvLHrMokWLMGPGDPTr1w9HHnkk3nnnnWQ/OCGEEEJ6DRSACCGEENLr+d73voe7774bd9xxB5YuXYpvfOMbuPjiizF//vyex/zbv/0bfvazn2HhwoUYMWIETj/9dHR0dABQws25556L888/H0uWLMGNN96I66+/Hr///e97nv/FL34R9913H371q19h2bJl+M1vfoMBAwYULcd3v/td3HLLLXjllVdQW1uLL33pS6l8fkIIIYRUP5qu63q5F4IQQgghpFzs3LkTw4YNw7PPPosjjjii5/6vfOUr2LVrF/71X/8Vs2fPxn333YfzzjsPALB582aMGzcOv//973HuuefioosuwoYNG/DUU0/1PP9b3/oWHn30USxduhTvvvsu9t13X8yZMwcnnnhiyTLMmzcPs2fPxtNPP40TTjgBAPDYY4/hs5/9LHbv3o0+ffokvBYIIYQQUu3QAUQIIYSQXs1bb72F1tZWnHTSSRgwYEDP3x//+Ed88MEHPY8zi0NDhw7Fvvvui2XLlgEAli1bhqOOOqrodY866ii89957KBQKeO2115DL5TBr1izXZTnooIN6ro8ePRoAsH79+sifkRBCCCGkttwLQAghhBBSTrq6ugAAjz76KMaOHVv0v4aGhiIRyIqmaQBUhpBcF8wm6759+/palrq6upLXluUjhBBCCIkCHUCEEEII6dUccMABaGhowMqVK7H33nsX/Y0fP77ncS+99FLP9S1btuDdd9/Ffvvt1/MaCxYsKHrdF154AZMnT0Yul8PUqVPR1dVVlClECCGEEJImdAARQgghpFfT2NiIa6+9Ft/4xjfQ1dWFo48+Gi0tLXjhhRcwYMAATJw4EQDwgx/8AE1NTRg5ciS++93vYtiwYTjzzDMBAN/85jcxc+ZM3HTTTTjvvPPw4osv4rbbbsPtt98OANhjjz1wySWX4Etf+hJ+9atfYdq0aVixYgXWr1+Pc889t1wfnRBCCCG9CApAhBBCCOn13HTTTRgxYgRuvvlmfPjhhxg8eDCmT5+O6667rqcE68c//jGuuuoqvPfee5g2bRoeeugh1NfXAwCmT5+Ov/71r/j+97+Pm266CaNHj8YPfvADXHrppT3vcccdd+C6667D1772NWzatAkTJkzAddddV46PSwghhJBeCLuAEUIIIYS4IB26tmzZgsGDB5d7cQghhBBCQsEMIEIIIYQQQgghhJAqhwIQIYQQQgghhBBCSJXDEjBCCCGEEEIIIYSQKocOIEIIIYQQQgghhJAqhwIQIYQQQgghhBBCSJVDAYgQQgghhBBCCCGkyqEARAghhBBCCCGEEFLlUAAihBBCCCGEEEIIqXIoABFCCCGEEEIIIYRUORSACCGEEEIIIYQQQqocCkCEEEIIIYQQQgghVc7/BwZs7YEgcOJ9AAAAAElFTkSuQmCC",
-      "text/plain": [
-       "<Figure size 1400x1000 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "FIRSTEPOCH=25\n",
     "loss = history.history['loss']\n",
@@ -1541,7 +1529,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 77,
+   "execution_count": 28,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -1553,7 +1541,7 @@
      "output_type": "stream",
      "text": [
       "[INFO] predicting house prices...\n",
-      "3/3 [==============================] - 0s 1ms/step\n"
+      "3/3 [==============================] - 0s 2ms/step\n"
      ]
     }
    ],
@@ -1565,7 +1553,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 78,
+   "execution_count": 29,
    "metadata": {
     "scrolled": true,
     "slideshow": {
@@ -1578,16 +1566,26 @@
      "output_type": "stream",
      "text": [
       "True \t \t  Predicted\n",
-      "  62500.00 \t   91602.59\n",
-      " 129000.00 \t  175620.03\n",
-      " 585000.00 \t  604572.64\n",
-      " 625000.00 \t  487662.05\n",
-      " 750000.00 \t  864853.76\n",
-      " 454999.00 \t  445260.49\n",
-      " 669000.00 \t  765313.21\n",
-      " 570000.00 \t  600197.18\n",
-      " 380000.00 \t  367856.68\n",
-      "  87500.00 \t   24435.35\n"
+      "  62500.00 \t  118267.09\n",
+      " 129000.00 \t  182509.16\n",
+      " 585000.00 \t  489385.13\n",
+      " 625000.00 \t  439696.30\n",
+      " 750000.00 \t  814101.03\n",
+      " 454999.00 \t  333713.15\n",
+      " 669000.00 \t  845040.62\n",
+      " 570000.00 \t  584275.86\n",
+      " 380000.00 \t  364128.92\n",
+      "  87500.00 \t   79811.56\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_3900348/3927113488.py:3: DeprecationWarning:\n",
+      "\n",
+      "Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)\n",
+      "\n"
      ]
     }
    ],
@@ -1606,7 +1604,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 79,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1621,7 +1619,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 31,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -1639,7 +1637,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 32,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -1649,21 +1647,21 @@
     {
      "data": {
       "text/plain": [
-       "410    46.564142\n",
-       "392    36.139555\n",
-       "497     3.345750\n",
-       "474   -21.974072\n",
-       "144    15.313835\n",
+       "410    89.227340\n",
+       "392    41.479971\n",
+       "497   -16.344422\n",
+       "474   -29.648592\n",
+       "144     8.546804\n",
        "         ...    \n",
-       "93    -25.021701\n",
-       "176   -20.927975\n",
-       "443    12.628008\n",
-       "84      1.527449\n",
-       "96    -13.468930\n",
+       "93    -22.322733\n",
+       "176   -17.543243\n",
+       "443     9.551273\n",
+       "84      8.921155\n",
+       "96     -1.275839\n",
        "Name: price, Length: 96, dtype: float64"
       ]
      },
-     "execution_count": 81,
+     "execution_count": 32,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1674,7 +1672,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
+   "execution_count": 33,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -1685,8 +1683,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Mean absolute difference percentage on test data: 22.45\n",
-      "Standard deviation of absolute difference percentage on test data: 20.69\n"
+      "Mean absolute difference percentage on test data: 23.18\n",
+      "Standard deviation of absolute difference percentage on test data: 28.67\n"
      ]
     }
    ],
@@ -1709,7 +1707,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 83,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1718,7 +1716,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 84,
+   "execution_count": 35,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -1734,7 +1732,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
+   "execution_count": 36,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -1747,7 +1745,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 86,
+   "execution_count": 37,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -1777,32 +1775,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 87,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "VBox(children=(Label(value='1.534 MB of 1.534 MB uploaded\\r'), FloatProgress(value=1.0, max=1.0)))"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "data": {
       "text/html": [
-       "<style>\n",
-       "    table.wandb td:nth-child(1) { padding: 0 10px; text-align: left ; width: auto;} td:nth-child(2) {text-align: left ; width: 100%}\n",
-       "    .wandb-row { display: flex; flex-direction: row; flex-wrap: wrap; justify-content: flex-start; width: 100% }\n",
-       "    .wandb-col { display: flex; flex-direction: column; flex-basis: 100%; flex: 1; padding: 10px; }\n",
+       "\n",
+       "    <style>\n",
+       "        .wandb-row {\n",
+       "            display: flex;\n",
+       "            flex-direction: row;\n",
+       "            flex-wrap: wrap;\n",
+       "            justify-content: flex-start;\n",
+       "            width: 100%;\n",
+       "        }\n",
+       "        .wandb-col {\n",
+       "            display: flex;\n",
+       "            flex-direction: column;\n",
+       "            flex-basis: 100%;\n",
+       "            flex: 1;\n",
+       "            padding: 10px;\n",
+       "        }\n",
        "    </style>\n",
-       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>MAD_test_percentage</td><td>▁</td></tr><tr><td>epoch/epoch</td><td>▁▁▁▁▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███</td></tr><tr><td>epoch/learning_rate</td><td>▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>epoch/loss</td><td>█▃▃▂▂▂▂▂▂▂▁▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>epoch/val_loss</td><td>█▅▄▄▃▃▂▃▂▂▂▃▂▂▁▁▁▁▁▁▁▁▂▁▁▁▁▁▁▁▁▂▁▁▁▁▁▂▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>MAD_test_percentage</td><td>22.45322</td></tr><tr><td>epoch/epoch</td><td>199</td></tr><tr><td>epoch/learning_rate</td><td>0.001</td></tr><tr><td>epoch/loss</td><td>19.44193</td></tr><tr><td>epoch/val_loss</td><td>22.45322</td></tr></table><br/></div></div>"
+       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>MAD_test_percentage</td><td>▁</td></tr><tr><td>epoch/epoch</td><td>▁▁▁▁▁▂▂▂▂▂▂▂▃▃▃▃▄▄▄▄▅▅▅▅▅▅▅▆▆▆▆▆▆▇▇▇▇▇██</td></tr><tr><td>epoch/learning_rate</td><td>▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>epoch/loss</td><td>█▃▂▂▂▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁</td></tr><tr><td>epoch/val_loss</td><td>▇█▆▅▅▃▅▃▃▃▂▂▂▂▁▁▁▁▂▁▃▁▂▁▁▁▂▁▁▁▁▁▂▁▂▂▁▂▁▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>MAD_test_percentage</td><td>23.18426</td></tr><tr><td>epoch/epoch</td><td>199</td></tr><tr><td>epoch/learning_rate</td><td>0.001</td></tr><tr><td>epoch/loss</td><td>19.51833</td></tr><tr><td>epoch/val_loss</td><td>23.18426</td></tr></table><br/></div></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1814,7 +1810,7 @@
     {
      "data": {
       "text/html": [
-       " View run <strong style=\"color:#cdcd00\">comfy-shadow-29</strong> at: <a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/hq3dbraz' target=\"_blank\">https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/hq3dbraz</a><br/> View job at <a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjEyMTY0OTE0Mw==/version_details/v6' target=\"_blank\">https://wandb.ai/iaai-hdm/dsm%20ml%20demo/jobs/QXJ0aWZhY3RDb2xsZWN0aW9uOjEyMTY0OTE0Mw==/version_details/v6</a><br/>Synced 6 W&B file(s), 2 media file(s), 49 artifact file(s) and 0 other file(s)"
+       " View run <strong style=\"color:#cdcd00\">decent-valley-35</strong> at: <a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/lj6fvssk' target=\"_blank\">https://wandb.ai/iaai-hdm/dsm%20ml%20demo/runs/lj6fvssk</a><br/> View project at: <a href='https://wandb.ai/iaai-hdm/dsm%20ml%20demo' target=\"_blank\">https://wandb.ai/iaai-hdm/dsm%20ml%20demo</a><br/>Synced 5 W&B file(s), 0 media file(s), 92 artifact file(s) and 2 other file(s)"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1826,7 +1822,7 @@
     {
      "data": {
       "text/html": [
-       "Find logs at: <code>./wandb/run-20231214_162115-hq3dbraz/logs</code>"
+       "Find logs at: <code>./wandb/run-20241211_152029-lj6fvssk/logs</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1849,7 +1845,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 88,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1858,7 +1854,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 89,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [
     {
@@ -1867,7 +1863,7 @@
        "'models/bestmodel.hdf5'"
       ]
      },
-     "execution_count": 89,
+     "execution_count": 40,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1878,7 +1874,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 90,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1887,22 +1883,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 91,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Model: \"sequential_3\"\n",
+      "Model: \"sequential\"\n",
       "_________________________________________________________________\n",
       " Layer (type)                Output Shape              Param #   \n",
       "=================================================================\n",
-      " dense_9 (Dense)             (None, 5)                 60        \n",
+      " dense (Dense)               (None, 5)                 60        \n",
       "                                                                 \n",
-      " dense_10 (Dense)            (None, 5)                 30        \n",
+      " dense_1 (Dense)             (None, 5)                 30        \n",
       "                                                                 \n",
-      " dense_11 (Dense)            (None, 1)                 6         \n",
+      " dense_2 (Dense)             (None, 1)                 6         \n",
       "                                                                 \n",
       "=================================================================\n",
       "Total params: 96 (384.00 Byte)\n",
@@ -1918,7 +1914,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 92,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [
     {
@@ -1935,7 +1931,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 93,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [
     {
@@ -1943,16 +1939,26 @@
      "output_type": "stream",
      "text": [
       "True \t \t  Predicted\n",
-      "  62500.00 \t  111086.62\n",
-      " 129000.00 \t  192715.03\n",
-      " 585000.00 \t  566607.73\n",
-      " 625000.00 \t  460268.00\n",
-      " 750000.00 \t  832999.79\n",
-      " 454999.00 \t  454685.30\n",
-      " 669000.00 \t  765562.95\n",
-      " 570000.00 \t  598022.10\n",
-      " 380000.00 \t  375363.09\n",
-      "  87500.00 \t   45008.03\n"
+      "  62500.00 \t  113191.13\n",
+      " 129000.00 \t  173295.87\n",
+      " 585000.00 \t  471911.66\n",
+      " 625000.00 \t  420648.97\n",
+      " 750000.00 \t  782619.35\n",
+      " 454999.00 \t  327963.99\n",
+      " 669000.00 \t  818770.22\n",
+      " 570000.00 \t  564198.76\n",
+      " 380000.00 \t  357770.73\n",
+      "  87500.00 \t   79152.96\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_3900348/3927113488.py:3: DeprecationWarning:\n",
+      "\n",
+      "Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)\n",
+      "\n"
      ]
     }
    ],
@@ -1964,7 +1970,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 94,
+   "execution_count": 45,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1978,15 +1984,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 95,
+   "execution_count": 46,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Mean absolute difference percentage on test data: 20.96\n",
-      "Standard deviation of absolute difference percentage on test data: 20.04\n"
+      "Mean absolute difference percentage on test data: 22.69\n",
+      "Standard deviation of absolute difference percentage on test data: 27.63\n"
      ]
     }
    ],
@@ -2018,26 +2024,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 97,
+   "execution_count": 49,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/html": [
-       "wandb version 0.16.1 is available!  To upgrade, please run:\n",
-       " $ pip install wandb --upgrade"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning:\n",
+      "\n",
+      "Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "\n",
+      "/opt/miniconda3/envs/python3/lib/python3.9/site-packages/pydantic/main.py:314: UserWarning:\n",
+      "\n",
+      "Pydantic serializer warnings:\n",
+      "  Expected `list[str]` but got `tuple` - serialized value may not be as expected\n",
+      "\n"
+     ]
     },
     {
      "data": {
       "text/html": [
-       "Tracking run with wandb version 0.16.0"
+       "Tracking run with wandb version 0.19.0"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2049,7 +2058,7 @@
     {
      "data": {
       "text/html": [
-       "Run data is saved locally in <code>/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20231214_163340-9i8kvi9p</code>"
+       "Run data is saved locally in <code>/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/wandb/run-20241211_153550-pi6qcyz7</code>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2061,7 +2070,7 @@
     {
      "data": {
       "text/html": [
-       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments_gitprojects_dsmmachinelearning_WandBexperiments/runs/9i8kvi9p' target=\"_blank\">flowing-bee-1</a></strong> to <a href='https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments_gitprojects_dsmmachinelearning_WandBexperiments' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
+       "Syncing run <strong><a href='https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments/runs/pi6qcyz7' target=\"_blank\">misunderstood-haze-1</a></strong> to <a href='https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br/>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2073,7 +2082,7 @@
     {
      "data": {
       "text/html": [
-       " View project at <a href='https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments_gitprojects_dsmmachinelearning_WandBexperiments' target=\"_blank\">https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments_gitprojects_dsmmachinelearning_WandBexperiments</a>"
+       " View project at <a href='https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments' target=\"_blank\">https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2085,7 +2094,7 @@
     {
      "data": {
       "text/html": [
-       " View run at <a href='https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments_gitprojects_dsmmachinelearning_WandBexperiments/runs/9i8kvi9p' target=\"_blank\">https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments_gitprojects_dsmmachinelearning_WandBexperiments/runs/9i8kvi9p</a>"
+       " View run at <a href='https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments/runs/pi6qcyz7' target=\"_blank\">https://wandb.ai/iaai-hdm/dsmmachinelearning-WandBexperiments/runs/pi6qcyz7</a>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2104,22 +2113,22 @@
    ],
    "source": [
     "run = wandb.init()\n",
-    "artifact = run.use_artifact('iaai-hdm/dsm ml demo/run_hq3dbraz_model:v48', type='model')\n",
+    "artifact = run.use_artifact('iaai-hdm/dsm ml demo/run_lj6fvssk_model:v15',type='model')\n",
     "artifact_dir = artifact.download()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 98,
+   "execution_count": 50,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'/Users/johannes/gitprojects/dsmmachinelearning/WandBexperiments/artifacts/run_hq3dbraz_model:v48'"
+       "'/home/fb1/maucher/mounted_home/share/gitprojects/dsmmachinelearning/WandBexperiments/artifacts/run_lj6fvssk_model:v15'"
       ]
      },
-     "execution_count": 98,
+     "execution_count": 50,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2130,7 +2139,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 99,
+   "execution_count": 51,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2139,7 +2148,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 100,
+   "execution_count": 52,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2148,22 +2157,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 101,
+   "execution_count": 53,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Model: \"sequential_3\"\n",
+      "Model: \"sequential\"\n",
       "_________________________________________________________________\n",
       " Layer (type)                Output Shape              Param #   \n",
       "=================================================================\n",
-      " dense_9 (Dense)             (None, 5)                 60        \n",
+      " dense (Dense)               (None, 5)                 60        \n",
       "                                                                 \n",
-      " dense_10 (Dense)            (None, 5)                 30        \n",
+      " dense_1 (Dense)             (None, 5)                 30        \n",
       "                                                                 \n",
-      " dense_11 (Dense)            (None, 1)                 6         \n",
+      " dense_2 (Dense)             (None, 1)                 6         \n",
       "                                                                 \n",
       "=================================================================\n",
       "Total params: 96 (384.00 Byte)\n",
@@ -2179,7 +2188,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 102,
+   "execution_count": 54,
    "metadata": {},
    "outputs": [
     {
@@ -2196,7 +2205,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 103,
+   "execution_count": 55,
    "metadata": {},
    "outputs": [
     {
@@ -2204,16 +2213,26 @@
      "output_type": "stream",
      "text": [
       "True \t \t  Predicted\n",
-      "  62500.00 \t  111086.62\n",
-      " 129000.00 \t  192715.03\n",
-      " 585000.00 \t  566607.73\n",
-      " 625000.00 \t  460268.00\n",
-      " 750000.00 \t  832999.79\n",
-      " 454999.00 \t  454685.30\n",
-      " 669000.00 \t  765562.95\n",
-      " 570000.00 \t  598022.10\n",
-      " 380000.00 \t  375363.09\n",
-      "  87500.00 \t   45008.03\n"
+      "  62500.00 \t   86201.17\n",
+      " 129000.00 \t   64973.66\n",
+      " 585000.00 \t  509218.26\n",
+      " 625000.00 \t  384596.30\n",
+      " 750000.00 \t  636850.27\n",
+      " 454999.00 \t  311054.24\n",
+      " 669000.00 \t  828080.42\n",
+      " 570000.00 \t  551502.89\n",
+      " 380000.00 \t  391991.51\n",
+      "  87500.00 \t  161363.00\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_3900348/3927113488.py:3: DeprecationWarning:\n",
+      "\n",
+      "Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)\n",
+      "\n"
      ]
     }
    ],
@@ -2225,7 +2244,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 104,
+   "execution_count": 56,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2239,7 +2258,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 105,
+   "execution_count": 57,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2253,15 +2272,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 106,
+   "execution_count": 58,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Mean absolute difference percentage on test data: 20.96\n",
-      "Standard deviation of absolute difference percentage on test data: 20.04\n"
+      "Mean absolute difference percentage on test data: 35.00\n",
+      "Standard deviation of absolute difference percentage on test data: 41.90\n"
      ]
     }
    ],
@@ -2286,7 +2305,7 @@
  "metadata": {
   "celltoolbar": "Slideshow",
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "python3",
    "language": "python",
    "name": "python3"
   },
@@ -2300,7 +2319,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.9.20"
   },
   "toc": {
    "base_numbering": 1,
diff --git a/WandBexperiments/models/bestmodel.hdf5 b/WandBexperiments/models/bestmodel.hdf5
index 10388a361d10e1ba5500b039229841acc0235015..efeeeac897c4c6d63771d61031c54aab2ddb0d33 100644
Binary files a/WandBexperiments/models/bestmodel.hdf5 and b/WandBexperiments/models/bestmodel.hdf5 differ