diff --git a/models/internal_priming.pth b/models/internal_priming.pth
index 7eb6ff99f2a924ff4bc1a60a12fc26199d0b0e09..c5463d1389d0544340d95c8bcbf263b0e9d8cf42 100644
Binary files a/models/internal_priming.pth and b/models/internal_priming.pth differ
diff --git a/notebooks/internal_priming.ipynb b/notebooks/internal_priming.ipynb
index 12a06a03f42df7d35f09e7446db3233fbf5d0049..b114148887e4eef46568ceb5004a50f8fea93643 100644
--- a/notebooks/internal_priming.ipynb
+++ b/notebooks/internal_priming.ipynb
@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 80,
    "outputs": [],
    "source": [
     "# importing the libraries\n",
@@ -127,13 +127,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 81,
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 20000/20000 [00:00<00:00, 78749.71it/s]\n"
+      "100%|██████████| 20000/20000 [00:00<00:00, 97752.58it/s]\n"
      ]
     }
    ],
@@ -184,7 +184,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 82,
    "outputs": [],
    "source": [
     "# TODO: reshape shape from [n, l] to [n, 1, l]\n",
@@ -228,37 +228,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 83,
    "outputs": [
     {
-     "ename": "RuntimeError",
-     "evalue": "Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
-      "\u001B[1;31mRuntimeError\u001B[0m                              Traceback (most recent call last)",
-      "\u001B[1;32m~\\AppData\\Local\\Temp/ipykernel_13904/3792042515.py\u001B[0m in \u001B[0;36m<module>\u001B[1;34m\u001B[0m\n\u001B[0;32m     29\u001B[0m \u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m     30\u001B[0m \u001B[1;31m# plotting the training and validation loss\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[1;32m---> 31\u001B[1;33m \u001B[0mplt\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mplot\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mtrain_losses\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mlabel\u001B[0m\u001B[1;33m=\u001B[0m\u001B[1;34m'Training loss'\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0m\u001B[0;32m     32\u001B[0m \u001B[0mplt\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mplot\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mval_losses\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mlabel\u001B[0m\u001B[1;33m=\u001B[0m\u001B[1;34m'Validation loss'\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m     33\u001B[0m \u001B[0mplt\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mlegend\u001B[0m\u001B[1;33m(\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n",
-      "\u001B[1;32mc:\\users\\gzaug\\onedrive\\dokumente\\uni\\programming in life sciences\\scrna-seq-simulation\\venv\\lib\\site-packages\\matplotlib\\pyplot.py\u001B[0m in \u001B[0;36mplot\u001B[1;34m(scalex, scaley, data, *args, **kwargs)\u001B[0m\n\u001B[0;32m   2755\u001B[0m \u001B[1;33m@\u001B[0m\u001B[0m_copy_docstring_and_deprecators\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mAxes\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mplot\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m   2756\u001B[0m \u001B[1;32mdef\u001B[0m \u001B[0mplot\u001B[0m\u001B[1;33m(\u001B[0m\u001B[1;33m*\u001B[0m\u001B[0margs\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mscalex\u001B[0m\u001B[1;33m=\u001B[0m\u001B[1;32mTrue\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mscaley\u001B[0m\u001B[1;33m=\u001B[0m\u001B[1;32mTrue\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mdata\u001B[0m\u001B[1;33m=\u001B[0m\u001B[1;32mNone\u001B[0m\u001B[1;33m,\u001B[0m \u001B[1;33m**\u001B[0m\u001B[0mkwargs\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[1;32m-> 2757\u001B[1;33m     return gca().plot(\n\u001B[0m\u001B[0;32m   2758\u001B[0m         \u001B[1;33m*\u001B[0m\u001B[0margs\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mscalex\u001B[0m\u001B[1;33m=\u001B[0m\u001B[0mscalex\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mscaley\u001B[0m\u001B[1;33m=\u001B[0m\u001B[0mscaley\u001B[0m\u001B[1;33m,\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m   2759\u001B[0m         **({\"data\": data} if data is not None else {}), **kwargs)\n",
-      "\u001B[1;32mc:\\users\\gzaug\\onedrive\\dokumente\\uni\\programming in life sciences\\scrna-seq-simulation\\venv\\lib\\site-packages\\matplotlib\\axes\\_axes.py\u001B[0m in \u001B[0;36mplot\u001B[1;34m(self, scalex, scaley, data, *args, **kwargs)\u001B[0m\n\u001B[0;32m   1630\u001B[0m         \"\"\"\n\u001B[0;32m   1631\u001B[0m         \u001B[0mkwargs\u001B[0m \u001B[1;33m=\u001B[0m \u001B[0mcbook\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mnormalize_kwargs\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mkwargs\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mmlines\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mLine2D\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[1;32m-> 1632\u001B[1;33m         \u001B[0mlines\u001B[0m \u001B[1;33m=\u001B[0m \u001B[1;33m[\u001B[0m\u001B[1;33m*\u001B[0m\u001B[0mself\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0m_get_lines\u001B[0m\u001B[1;33m(\u001B[0m\u001B[1;33m*\u001B[0m\u001B[0margs\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mdata\u001B[0m\u001B[1;33m=\u001B[0m\u001B[0mdata\u001B[0m\u001B[1;33m,\u001B[0m \u001B[1;33m**\u001B[0m\u001B[0mkwargs\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m]\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0m\u001B[0;32m   1633\u001B[0m         \u001B[1;32mfor\u001B[0m \u001B[0mline\u001B[0m \u001B[1;32min\u001B[0m \u001B[0mlines\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m   1634\u001B[0m             \u001B[0mself\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0madd_line\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mline\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n",
-      "\u001B[1;32mc:\\users\\gzaug\\onedrive\\dokumente\\uni\\programming in life sciences\\scrna-seq-simulation\\venv\\lib\\site-packages\\matplotlib\\axes\\_base.py\u001B[0m in \u001B[0;36m__call__\u001B[1;34m(self, data, *args, **kwargs)\u001B[0m\n\u001B[0;32m    310\u001B[0m                 \u001B[0mthis\u001B[0m \u001B[1;33m+=\u001B[0m \u001B[0margs\u001B[0m\u001B[1;33m[\u001B[0m\u001B[1;36m0\u001B[0m\u001B[1;33m]\u001B[0m\u001B[1;33m,\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m    311\u001B[0m                 \u001B[0margs\u001B[0m \u001B[1;33m=\u001B[0m \u001B[0margs\u001B[0m\u001B[1;33m[\u001B[0m\u001B[1;36m1\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m]\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[1;32m--> 312\u001B[1;33m             \u001B[1;32myield\u001B[0m \u001B[1;32mfrom\u001B[0m \u001B[0mself\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0m_plot_args\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mthis\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mkwargs\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0m\u001B[0;32m    313\u001B[0m \u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m    314\u001B[0m     \u001B[1;32mdef\u001B[0m \u001B[0mget_next_color\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mself\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n",
-      "\u001B[1;32mc:\\users\\gzaug\\onedrive\\dokumente\\uni\\programming in life sciences\\scrna-seq-simulation\\venv\\lib\\site-packages\\matplotlib\\axes\\_base.py\u001B[0m in \u001B[0;36m_plot_args\u001B[1;34m(self, tup, kwargs, return_kwargs)\u001B[0m\n\u001B[0;32m    488\u001B[0m             \u001B[0my\u001B[0m \u001B[1;33m=\u001B[0m \u001B[0m_check_1d\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mxy\u001B[0m\u001B[1;33m[\u001B[0m\u001B[1;36m1\u001B[0m\u001B[1;33m]\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m    489\u001B[0m         \u001B[1;32melse\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[1;32m--> 490\u001B[1;33m             \u001B[0mx\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0my\u001B[0m \u001B[1;33m=\u001B[0m \u001B[0mindex_of\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mxy\u001B[0m\u001B[1;33m[\u001B[0m\u001B[1;33m-\u001B[0m\u001B[1;36m1\u001B[0m\u001B[1;33m]\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0m\u001B[0;32m    491\u001B[0m \u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m    492\u001B[0m         \u001B[1;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0maxes\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mxaxis\u001B[0m \u001B[1;32mis\u001B[0m \u001B[1;32mnot\u001B[0m \u001B[1;32mNone\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n",
-      "\u001B[1;32mc:\\users\\gzaug\\onedrive\\dokumente\\uni\\programming in life sciences\\scrna-seq-simulation\\venv\\lib\\site-packages\\matplotlib\\cbook\\__init__.py\u001B[0m in \u001B[0;36mindex_of\u001B[1;34m(y)\u001B[0m\n\u001B[0;32m   1650\u001B[0m         \u001B[1;32mpass\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m   1651\u001B[0m     \u001B[1;32mtry\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[1;32m-> 1652\u001B[1;33m         \u001B[0my\u001B[0m \u001B[1;33m=\u001B[0m \u001B[0m_check_1d\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0my\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0m\u001B[0;32m   1653\u001B[0m     \u001B[1;32mexcept\u001B[0m \u001B[1;33m(\u001B[0m\u001B[0mnp\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mVisibleDeprecationWarning\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mValueError\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m   1654\u001B[0m         \u001B[1;31m# NumPy 1.19 will warn on ragged input, and we can't actually use it.\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n",
-      "\u001B[1;32mc:\\users\\gzaug\\onedrive\\dokumente\\uni\\programming in life sciences\\scrna-seq-simulation\\venv\\lib\\site-packages\\matplotlib\\cbook\\__init__.py\u001B[0m in \u001B[0;36m_check_1d\u001B[1;34m(x)\u001B[0m\n\u001B[0;32m   1302\u001B[0m     \u001B[1;34m\"\"\"Convert scalars to 1D arrays; pass-through arrays as is.\"\"\"\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m   1303\u001B[0m     \u001B[1;32mif\u001B[0m \u001B[1;32mnot\u001B[0m \u001B[0mhasattr\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mx\u001B[0m\u001B[1;33m,\u001B[0m \u001B[1;34m'shape'\u001B[0m\u001B[1;33m)\u001B[0m \u001B[1;32mor\u001B[0m \u001B[0mlen\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mx\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mshape\u001B[0m\u001B[1;33m)\u001B[0m \u001B[1;33m<\u001B[0m \u001B[1;36m1\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[1;32m-> 1304\u001B[1;33m         \u001B[1;32mreturn\u001B[0m \u001B[0mnp\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0matleast_1d\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mx\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0m\u001B[0;32m   1305\u001B[0m     \u001B[1;32melse\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m   1306\u001B[0m         \u001B[1;32mtry\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n",
-      "\u001B[1;32m<__array_function__ internals>\u001B[0m in \u001B[0;36matleast_1d\u001B[1;34m(*args, **kwargs)\u001B[0m\n",
-      "\u001B[1;32mc:\\users\\gzaug\\onedrive\\dokumente\\uni\\programming in life sciences\\scrna-seq-simulation\\venv\\lib\\site-packages\\numpy\\core\\shape_base.py\u001B[0m in \u001B[0;36matleast_1d\u001B[1;34m(*arys)\u001B[0m\n\u001B[0;32m     63\u001B[0m     \u001B[0mres\u001B[0m \u001B[1;33m=\u001B[0m \u001B[1;33m[\u001B[0m\u001B[1;33m]\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m     64\u001B[0m     \u001B[1;32mfor\u001B[0m \u001B[0mary\u001B[0m \u001B[1;32min\u001B[0m \u001B[0marys\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[1;32m---> 65\u001B[1;33m         \u001B[0mary\u001B[0m \u001B[1;33m=\u001B[0m \u001B[0masanyarray\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mary\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0m\u001B[0;32m     66\u001B[0m         \u001B[1;32mif\u001B[0m \u001B[0mary\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mndim\u001B[0m \u001B[1;33m==\u001B[0m \u001B[1;36m0\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m     67\u001B[0m             \u001B[0mresult\u001B[0m \u001B[1;33m=\u001B[0m \u001B[0mary\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mreshape\u001B[0m\u001B[1;33m(\u001B[0m\u001B[1;36m1\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n",
-      "\u001B[1;32mc:\\users\\gzaug\\onedrive\\dokumente\\uni\\programming in life sciences\\scrna-seq-simulation\\venv\\lib\\site-packages\\torch\\_tensor.py\u001B[0m in \u001B[0;36m__array__\u001B[1;34m(self, dtype)\u001B[0m\n\u001B[0;32m    676\u001B[0m             \u001B[1;32mreturn\u001B[0m \u001B[0mhandle_torch_function\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mTensor\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0m__array__\u001B[0m\u001B[1;33m,\u001B[0m \u001B[1;33m(\u001B[0m\u001B[0mself\u001B[0m\u001B[1;33m,\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mself\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mdtype\u001B[0m\u001B[1;33m=\u001B[0m\u001B[0mdtype\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m    677\u001B[0m         \u001B[1;32mif\u001B[0m \u001B[0mdtype\u001B[0m \u001B[1;32mis\u001B[0m \u001B[1;32mNone\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[1;32m--> 678\u001B[1;33m             \u001B[1;32mreturn\u001B[0m \u001B[0mself\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mnumpy\u001B[0m\u001B[1;33m(\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0m\u001B[0;32m    679\u001B[0m         \u001B[1;32melse\u001B[0m\u001B[1;33m:\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n\u001B[0;32m    680\u001B[0m             \u001B[1;32mreturn\u001B[0m \u001B[0mself\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mnumpy\u001B[0m\u001B[1;33m(\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m.\u001B[0m\u001B[0mastype\u001B[0m\u001B[1;33m(\u001B[0m\u001B[0mdtype\u001B[0m\u001B[1;33m,\u001B[0m \u001B[0mcopy\u001B[0m\u001B[1;33m=\u001B[0m\u001B[1;32mFalse\u001B[0m\u001B[1;33m)\u001B[0m\u001B[1;33m\u001B[0m\u001B[1;33m\u001B[0m\u001B[0m\n",
-      "\u001B[1;31mRuntimeError\u001B[0m: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead."
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 25/25 [00:18<00:00,  1.34it/s]\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": "<Figure size 432x288 with 1 Axes>",
-      "image/png": "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\n"
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
     }
    ],
    "source": [
@@ -312,12 +289,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 84,
    "outputs": [
     {
      "data": {
       "text/plain": "<Figure size 432x288 with 1 Axes>",
-      "image/png": "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\n"
+      "image/png": "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\n"
      },
      "metadata": {
       "needs_background": "light"
@@ -344,15 +321,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 76,
+   "execution_count": 85,
    "outputs": [
     {
-     "data": {
-      "text/plain": "0.997"
-     },
-     "execution_count": 76,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.9995\n",
+      "0.9995\n"
+     ]
     }
    ],
    "source": [
@@ -398,7 +375,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 79,
+   "execution_count": 86,
    "outputs": [],
    "source": [
     "torch.save(model.state_dict(), '../models/internal_priming.pth')"