diff --git a/Makefile b/Makefile
index eff618a9c8..af9812364b 100644
--- a/Makefile
+++ b/Makefile
@@ -32,7 +32,7 @@ sweeper_test:
 
 # Here you define a list of notebooks we want to execute and convert to markdown files
 # NOTEBOOKS = hellomake.ipynb hellofunc.ipynb helloclass.ipynb
-NOTEBOOKS = src/super_gradients/examples/model_export/models_export.ipynb
+NOTEBOOKS = src/super_gradients/examples/model_export/models_export.ipynb notebooks/what_are_recipes_and_how_to_use.ipynb
 
 # This Makefile target runs notebooks listed below and converts them to markdown files in documentation/source/
 run_and_convert_notebooks_to_docs: $(NOTEBOOKS)
diff --git a/notebooks/what_are_recipes_and_how_to_use.ipynb b/notebooks/what_are_recipes_and_how_to_use.ipynb
index 3cc2d7f431..9efc19b78c 100644
--- a/notebooks/what_are_recipes_and_how_to_use.ipynb
+++ b/notebooks/what_are_recipes_and_how_to_use.ipynb
@@ -1,1322 +1,955 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "name": "python3",
+   "language": "python",
+   "display_name": "Python 3 (ipykernel)"
+  },
+  "language_info": {
+   "name": "python"
+  },
+  "accelerator": "GPU",
+  "gpuClass": "standard"
+ },
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "![SG - Horizontal.png](data:image/png;base64,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)"
+   ],
+   "metadata": {
+    "id": "sh6t_y7KzqBH"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "#  Using SuperGradients (**recipes**)\n",
+    "\n",
+    "This tutorial will explain what **recipes** are, when and how can recipes help you scallable training and reproducing results, and how to use them.\n",
+    "\n"
+   ],
+   "metadata": {
+    "id": "5aISf1B-AGDQ"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "!pip install -q super_gradients==3.3.1"
+   ],
+   "metadata": {
+    "id": "8uZM-4va5Rpu",
     "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
+     "base_uri": "https://localhost:8080/",
+     "height": 1000
     },
-    "language_info": {
-      "name": "python"
-    },
-    "accelerator": "GPU",
-    "gpuClass": "standard"
+    "outputId": "a93c1b2d-3b81-4cd7-aeaa-f62f6d6bf81d",
+    "ExecuteTime": {
+     "end_time": "2023-10-30T10:27:01.325915300Z",
+     "start_time": "2023-10-30T10:26:46.000330100Z"
+    }
+   },
+   "execution_count": 1,
+   "outputs": []
   },
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "source": [
-        "![SG - Horizontal.png](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAABGcAAAD5CAYAAACK9FhIAAAACXBIWXMAAAsSAAALEgHS3X78AAAgAElEQVR4nOydCZgcV3W2z62ZkUbryPIu20gywWhFEsZJzGLJkBCWEMsYsFk1hjiGgLEclgQIWCIsgQQ8Zov/sFgibGazxB8ghhiPCJD8EViSZUuyvEnYlm3ZljQaLaNZqv7ndp/quX373urqrrrV1d3f+zw13VNVXcut6uq6X33nHBEEAQHQZMwgoqW8yXN4MLGViA7x+H4c5DLUNlTf6+zhgbT2BAAAAAAAAACQEp1oSJBzpGiw4ukDY2+Y1O2dN3my6JGbe/x4EEyaJES1TR8bIxoZCfzubuGNjdHo0WP+U8PDwZZTTu74Lgs2e3K+/2kg23Dp0wfG/rqrU8ydPt07RS5zaKjYLnGWf/SYPzZlstch3x87FgwcH/J3T+gSP502zbuVRRsAAAAAAAAAAHUC5wzIIysHBvzVU6aKF1FAorOzughTL1JoGBkJftbT432ixUSGQhtOnCgu7OoSEzo63KxkdDQIhBD+oYGxO0+e2SHbcIObNQEAAAAAAABA6wJxBuSFOQMD/qenTBGXCSE8V2KCDd8vOEkOnBgOPnHSDO+rTRq+M+fAgbGPTJ7svdGlIGNDtmEQ0Njx4/7Ppk71/rpNXEkAAAAAAAAAkBiIM6DRzHnqqbFvnnJKx/PzcCRkGJQ0hAyd8L8wZbJ3XcM3KB5zjhzxvzR1qvfyvGyQ71Nw8NDYb0+e2fE6iDQAAAAAAAAAEA3EGdAwDhwY+9r06V6vy7ClepEizehYMDRxgnh9nkN1jh7zb5g4QVybxzYMGRjwv9fT4/0VkgkDAAAAAAAAgBmIM6ARLD182P/11KneZC9WOtrGIUN1jh7zfzttqvenORMXmqYNJSeGC0LXy1E1CwAAAAAAAAAqaYJuHWglDh7y3zM6GmyZPr05RAW5jdOmes87MRw8GlFuOlNkGxJR07ShZOIE0e37dId0S+VgcwAAAAAAAAAgV8A5AzLj0X2jPz7zjM5XNIugoDM2Rn5HB72kke6PJ54Y+59TT+34o2ZtQ+lEGhz0N/X0eCsR5gQAAAAAAAAAReCcAZlw3/0ju5pZmJF0dBS+L3ewcyVzdu4afqCZhRkKnUjTvOXHjgUPENGMHGwSAAAAAAAAADQcOGeAc7bddeLRxYsmzmpmUcHAxVk6aO7ceuKJpc+ZeForteHx48H+SZPE6TnYFAAAAAAAAABoKHDOAKf8y5cPbW9BYUaGON2eVQ6a7/1w8NFWE2YkEyeK0wYGfCQIBgAAAAAAALQ9EGeAM6665vH/eMdVMxa1mqhAHOJ07FjQ7zo050Nrn9p12cppLSduEYc4TZ3qLR8c9NfmYHMAAAAAAAAAoGEgrAk44cV/8fC3N37rrCumTW1t/e+pp8d+esrJHa9wseyLXv7w/97+o7Mv6OoSLhafN5YR0dZ22FEAAAAAAAAA0IFzBqTOc16455/efdVJLS/MSGae1PFyIlqR9nKf84I9v7zxH09rF2GG2IUEAAAAAAAAAG0JxBmQKs950Z4Pzpsz8b2vesXUtmhYGZpzYjj4cZrLfM6L9tx+wXMmvWjJcyamudhc090teo4e829omx0GAAAAAAAAAAWENYHUWLz8oevECfHZH37zLPqDZ3a1TcOOjUnnh//RadO865Mua/Hyh24TJ8RLf/WzZ9D06e2lnY6Nkd/RQScT0aEcbA4AAAAAAAAAZAacMyAVFl/80HViRHz2gqWT6Nxz20eYoWJyYJo82ftg0uUsfvFD3xEj4qWXv3o6TZvWfl9NmWT5wIGxz+ZgUwAAAAAAAAAgUyDOgMQsfnFRmKExog+8byZ57ZEmRafz4CH/PfV+ePFLHvq6GBaX05iga94+g0R7tiH19HSscl0BCwAAAAAAAADyBsQZkIjFf/LQdWJUfJZ8olmnd9HcOe3lmgkpumfER+v57OI/feifxbB4sxS3XnzRZJoypa2/lt7goH9dDrYDAAAAAAAAADID4gyom8UvfejqgjAzRiTFmbdf1VMQKdqVzg4xmYiW1rL7i1/60HU0It4j2498QW/rnd7WbSj3fcJE8d4cbAoAAAAAAAAAZAbEGVAXi1/24NU0SjcVhJmgKCy85OLJbd2YUlgYGPD74s6/+GUPXkej9FnB4pYsPb54YftUaLLR1Vm7yAUAAAAAAAAAzQzEGVAzi18hhRlxkxgTVHR8EM171gTqntiYRCmyWpIcqo3LgqlTvRfGWc3iVzwoHTOfLbVhUAxpGh1tXPW04eHydcv208dlgSxPPjDgJ06wDAAAAAAAAADNQieOFKiFxa988M00Im6iUSqJChQIesMV06irKztxRlaAP3LUp9vvOEb9vzxO+/aN0q7dw6Xp886bQLPO7KSX/slketELJ9HUKV4mSXaDIPCIhHR9bLXNs/jPH7xaCjOhsBU6j173mqnU2ZldG0rxxfcD+s1/D9F/3nGM9j02Spt/N1SaLtvvrFmd9IILJ9ErXjaZTju1syCcZEH3JPHKzBoCAAAAAAAAABqMCILGPakHzcXiVz34ZhoWX5fCjBgVVAhpKgyC/vPHZ9Npp2aTLGVkJKBP33CQbvn+YPSMyql9+Wum0fv/5qRMBKQDB8Zunjmz462maYv/4sGraVjcRMNEBdeM0oa/+/UzMhO4RkYD+pf/M0BfWT8Q7wMB0QXP7aYPvH8mnTu3y7lI4/sUeB6dS0R73K4JAAAAAAAAABoPwppALBZf8uCbaVR8PUz+W3R7FF9lrpSshJnHnxilFS9/hG754WEiL7APgs9u1jqkkLPizx4pfN41nV3i5aZVLF4pHTNUdB0F5a4ZKXxkhWyDV122j77yb4eqt2GoFQmizVuG6NVX7KMf/fiIFE+c4nmFNa/IrFEAAAAAAAAAoIFAnAFVWXzpg6+mUfp6mPxX+JwnhYohTTKESLpZXDN4xKfL3rSPBo+NFc/cyEFuaCg0FMWFwUGfLnv9Y87zqEyf5p2hj1t86QNvLggznGOm0IbBuLtnyeKJmbhmwjbc9+TIePt18FDRnkobKiLNRz76dCYCzdMHxv7a7RoAAAAAAAAAIB9AnAGRLL7sASnM/ICU5L8FgvFB5iRxLSz4AdHqv9tPg8f8cVeMOgiqcHqMjx93gUiB5h3X7C8szxUjI4VYwVK1ocWXPcCuI1Hefko7yrw4rpFiSqENj/vmttPHeYY2pHGBZv+Tbl1Ik7q985w3CgAAAAAAAADkAIgzwMri10phRvxADWUSgSgTZiTLlrov//z734/Q5m1DES4PTVRQRRpNXNh851Bhea7o6iqkHi6IM4tf98DVpXCwYDyMSW/DZ5ztPjf3trtPFNvQJG55BnFLaMKNJtB86CNPOxW5Jk8WPe6WDgAAAAAAAAD5AeIMMLL48gdeSiOhMCOUykzliXbl+9NPc5tvRjo+vvrtgUqHTIV4QHYXjSbQfHXdYadhOQcOjF206PIHri5UttLaUKjtGBQ36OST3bahrMz0ha8epKCDioNXPhidM2Rq03KRa/9+d+4ZmRRYdSABAAAAAAAAQKsCcQZUsPj1D7yURsVtZaWeyfRa7KXLkssukZWBbv/1UQq8wDhYBRtdoFFef7HpmNOKQ0dPBH8qRummsgTKJnFLlv1+1oSCeOKSY8d9+t/tx63Jf0vtqoc4GZ00QWncd79/xNlWB0FhbTPctgwAAAAAAAAANB6IM6CMxW+Qjhm6rVBRyGcBJiKkKQse+v1IMdeMJRSnKCpoIo3VQROUcs/s2esutImC4GwaDfP0iAqnTHEernY1zf3X8K4dJ6qLV4LGhZqoeWj89Ve/Oe5MWOoomolQsQkAAAAAAADQ8kCcASUWv+mB59Mo3VZIXBtYHB9aSNMF53fTseNulZqd90UIC4oIUybSUHX3zP33uxNnZkzvKG8v23t2HnU4rkT+698di65uZRCxAps4o7hndu0edrrtjz8xutDd0gEAAAAAAAAgH0CcAQUWveV+Kcz8uqwqU+iUoUpRRmXiBLeVmu6W4owpCbAlL0qFi4YMr0R03wPuxJlpU73K5L+k5Juh8VfXYWFSPNv10LA5mXJFVSb+kE2gIe09ET38iLu8M11dYrazhQMAAAAAAABAToA4A2jRqvtni1Hx64r8KGQIXzKMd+36KAgLtqpMtrwoFDGO+e3vhtxueFSuGeX9WbPcijOTJwl6VCbureI8soaBkVncCuc9dsxdZuXuiWKms4UDAAAAAAAAQE6AONPmLHrr/TPEmNhTqihkCmMK880YePZ5E5w24OARv7xKUJSoQAb3DBmEGWVZTkOybCFNDWDfkyPF5L9CSQSsO48sDhpreBNz7253DqQxn6Y0psUAAAAAAAAAIDsgzrQ7o3RwPPmv6vYwJP81CAuF8B3XKMlqSwIDRTg+SBFoqHycLtSMjbpRS2SS3FmndWluGW3l/P8557h1zhQw5pgxiDRGwUtzz2RLd0PWCgAAAAAAAAAZAnGmjVm06v5AjIry3ChkEWNi5J5xhsnVIYJKN02EUJO1sCBLV591OosuVdpMhh05R3cc6SJNVGiYQVcCAAAAAAAAAJAeGTyyB3lk0VvvD4SvJP8lQ46UPKGLLaVtDMonBtp8ooH7EtWOWW+Tp2yPUWjhCep0oU0GAAAAAAAAAOAEiDNtyKK33R8UQpnGIhLWksEt04AO+uRJXnXnS6CIMPprHlArNTUKoYlaRpEmKFpkbG3YAAcSAAAAAAAAALQDCGtqMxZddX8gRRlRlvxXC2myldBWySjORVaCKuS1MZZ6Dt8bctDkhbwIRFUSKEeVHC/+b8jfAwAAAAAAAAAgFSDOtBGLrr4vqCiXnQN3TDWec97E2oQFGv8/aGwy23EakatHJcwro+fvIV20UTYOThkAAAAAAAAAyASENbUJi95xX0CjxRwzQq/EZMuNEiUiiGLcy727h5034LzZE80iQVl+FCUkJy8hTXkSvArtFKj/jLedOjowjAcAAAAAAAAA4BQ4Z9qARe+UjpmwKpOlZDbZRRphC2ESRIODvnlaisw7d4K5MhMld3ZMm+bmK5BJifFa0MPA4oYzAQAAAAAAAABwDpwzLc6id903nvzXt4Qy6e9N/9tggcaVyCHpmeYVxI7BwaDc1aE6Pepwy2z+3RA954K96W9wB1HQ4160qglT5SVVkDElAAYAAAAAAAAAkAlwzrQwi969m3PMjIcxCRJ2IaaOjrkUOFwKM5LOTkEv/sMplflQkqC7cNIaJhIFM8fyFxpUsX+B2S2j5p1BzhkAAAAAAAAAyASIMy3Kout2F0OZ9OS/1fLMUD7dE5f/SU+5qKALB7rgEEU4r5fyMDGg4KSx7BsnBoGxzTSBBkIMAAAAAAAAADQEiDMtyKK/2R3QSCjMRAg0lI4Qs++xUeeNuPi8ieY8LvWICnrVojSGTqLgJD+/YUFCE2h0YQsAAAAAAAAAQMOAONNiLHrv7srkv2QJaQoT/ZrGxYFn3bNnJJNG/OvLZsZzekSNT1uU8TiU6WRDjpm8CTW2MCYAAAAAAAAAAA0F4kwLsej9u8uT/1KMEKYYBKYcJEqn/rd3nsikES+5eBqvu86dcSLMBBTM8PMvcoQ6HKoyAQAAAAAAAEDugDjTIiz8u3uLwoyS/LesTDZZwpmiKjbFZNv2EzQy4t4mMrnboyv+bHp9H3aR/FdWZWoGYYYikvyqOXwAAAAAAAAAADQEiDMtwMIP3huI0RqS/6alo3DHXlZs6upy37vv6CB631tOoWlTajhtpT7lBekPEzj5b96qMkVRkUA5f5sIAAAAAAAAAO0IxJkmZ+GHVGFGVOSZMb4mxdCx37M3m7wzEyYI+uvXziz+U01cCLcz7VCmCUQkc8x0ZLHHKaG0VS1phQAAAAAAAAAAuAfiTBOz8MP3BiIsl62LMlpIkyglHUmwvya3Bf9/28+PZdaQr395D82bOyF6Jj1xcNqhTM3glNGpN1dPFQ4PGpIhp0SHR087WzgAAAAAAAAA5AQRBM3YywQL19wb0DCRkCWzwwTAoYNmjHPPhKKNjL4JlGlB+KoJO4XpSqWnsM8t06r42vgwVIrXM++8CfTNdWdkEt4k2f/0KL3kqt+P709puzT3UJrIctnT/YKkKcbUdhOV26G2P88n9HHcpt/7xpn07POqiE0JWfSW+8vWKXxt+8u2S8ldpJwzpe3XzxV3l5CL79o8u99pwwAAAAAAAABADoBzpglZuHaXTyNSIFDcMKZYFb3THKcTrSaIjVuqWhDt2j1Mx49nJ/SdPKOTPvXu08wTvaLDJdVhAlEwc6z4HnpmOS6SLQu6DsIMAAAAAAAAoF2AONNkLPyHXT6NCjHuXLEk/nWZb0Z9r4TKfPu7g5k1pkwO/LKLptIVL9OqNxXEpZSHDlkue8wuVjUD1QS3epBt46U+DJMXXH/X/87ua+LWBgAAAAAAAICagDjTRCz8OAszapiRKxFGRa5KzVeidvKV97f+6AiNjWXXnp5H9P6rTqZ5505wk/jX41CmmU2W/LcaaQg0woE7qYOGyaO33PU/cz7qtgEAAAAAAAAAIF9AnGkSFn5yZ0mYqSyTrQs1Wu+7nvAmsnTiI0Kd9j02SrvvH860Qbs6BX3tY7No2lTPjTBzql/+LUFIUxE3oUwfv+s3c27Jw+4BAAAAAAAAQJZAnGkCFn5KEWZ8SzhTSBwHTRznhKkqk8Eto4c2/fNnD2bqnpFIYeaHN55dFGjSrMo0010VoqbFlUPJo0/d9Ss4ZgAAAAAAAADtCcSZnLPw0yzMKJVxROiMMYkycbG5YqJEGdP8VC5qbL5ziAaPZC9qnHFaJ33vhrNp2rQUHDSdSP5romDQ8pwMF9/1yzl/l789BgAAAAAAAIBsgDiTYxb+886xslCmUPOwhSmZXDPVxIW4VZnUvDNGEWd8RV+86RA1okL7mad20idkBaekwswpY62VYyYNCo4ZJwmAP7W9fw6qMgEAAAAAAADaGogzOWXhDTvHaEx4xVAmYcgz49DVEZbTNk5TXoVhHBHd8v1BGjicvXtGJgi+6HmT6fN/e0Z9QkFnUHTMhPsD10wRN/ll5PCp7b+YC8cMAAAAAAAAoO2BOJNDFvTtGKMR4dFYpRgjqiX/TYLuiLHlmbFOHxd13vP+JzPPPUOqQPP+M1GVKQ3cVGWSbX7F9tshzAAAAAAAAAAAQZzJHws+t2NMjIaOGYNLptbkv3GICm2i8mlloU0RrzL3zEN7RhrSvgWB5vzJ9LUPz4qXJNjjHDP4NpTjMPnv9p/PRVUmAAAAAAAAAGDQHc0RC74QCjOi3BkTtypTLSKN5nQpH294T9UFGX2Z77puf8MaVwo05y+YRLd8/OzoMtu2HDPtHtLkMpTpP+CYAQAAAAAAAAAViDM5YcGXFMeMXipbpZ6qTKbBNF/Z/0HlNGFJDGwUaYj2PTZK3/j2YEPCm4gFmnPO6KIffvIcs0DTSeSXqjKlGB7W7LhL/vvF7T+FMAMAAAAAAAAAOhBncsCCm9RQJlEZzhRVQjsNbHlmyCK8VHtV3DOf/uwBevpAg9QZ5oxTO+mHHz+Hpk4RBWGpMHQE48IMGMdlKNOPz30XWhoAAAAAAAAAKulEmzSWBf96z6gY8YrJf3W3jEmMsQkz9Qg2Qvuc+n/4XsSYT61upL8PiN517X767rfObGg7S4Hmjs/PpTd97BHa9cgJCk7ialLZF5XKL4ooN22KR/POnZjKpp59eue3P/ruU/+DiFbU8fFDRLQ15y0HAAAAAAAAAImAONNAFnz5nlEaER3jooylZLaJNJIA6wJLhTATFLfJkDBYuk8EiXJBpkzQGZ+w675h+twXD9E73z6DOhroVOmeIOjbHzmbrvjcXtr12PC4MNPu+WWo0gklhZkvf/RMOnY8mXolpFlJ0OuOHvNfV+tnOzwhhkeC/dOneY1V9gAAAAAAAADAMRBnGsSCr90zSqOiQ0SEMZVIuypTmQsmGHfomAQaivG/sLhmwjcB0VfWDdCFf9xNF5zf3dB27+oU9J13z6arvvIobb7vWEO3JTfo4ptPJA6LgpBWyNWTjLAYd10MjwSNPWEAAAAAAAAAIAOQc6YBLLj5npFyx0wVUUbHNN6WzzZM4qt/KCq3TKy8MpwYWP9cxHJWv+9JevyJ0Ya3vxRo1r39bLrij2c0fFtyQeE48jBGJB7vIBpBgmQAAAAAAAAAyAqIMxmzYP09wzQqOgvuhNA1Q4ZqQXq+mTiuGVsJbH0ekyhjel8KTzKIL2Sp3FSxHUFp2uCgT+/+mydpZDQfcUQfuuw0uuLCNhZoDMl/xZNeQaABAAAAAAAAAJAdEGcyZMG/3X2CRkVXRfLfODlmkmISbEoiSmAWVmyvttLc1nHjAs2u3cP09nfuz8XxkKW2P/Sa0+iK57ehQGMUZjogzAAAAAAAAABAA4A4kxELvnn3EI2ICYXOb1gW2ybM6AJNGrlmbP/HKpttcMco02OFNykCzeY7h+jjnzpAfg4qJUmB5oOvPY0+/ZYzGr8xGRJ4yiBdXI91EJ1om90HAAAAAAAAgFwBcSYDFnz77uM0IiaSKfkvaSFNaSX/pUoxpZB3plpuGZsTRv/flH+myjyqQ+eW7w/SJ/8pPwLNy543jb5w1azGb4xrFJEsTOTsPQXHDAAAAAAAAAA0EogzjlnwnbuP0ojoLokyFBHCZBJmahVpNBFkfJz2v/5eFVeMr0H5Z2IINnEEmtv7j1GQgxQ0niBavmQKfeGvWligCUOZOoLiIMuhH/CIRnKwbQAAAAAAoAzP616hDmgdAFobiDMOWfDduw/TqJhcFGbGXTNCd8rUI8CY/q9WYCfKLWNbvjAIKybhJSq8KWLce/72Sfrlfx3PhYNGhALN1S0q0KhtL6sy7ZehTNVOGgAAAAAAkBWe1z3D87r7PK/7EBHdoQ6e1x14Xvc6z+uegwMCQOsBccYR83+w/UkaFdMKgowfIwGwSaCJEm2qCTKx3DLavFHii+3zpvCmGhIES655z376r1/lSKBZOoW+8I4WE2j05L9PdxA1vqo5AAAAAABg2B2zh4iuJaIeS7usIqKHPK97NdoNgNYC4owD5v9w+8NiWJwyXpVJVIowSUKXojC5YBRhJCAtfEmdL+JzZQJOxbjyITCJPOryPLtAk4cQJynQXLRsCn34jac2fmPSQq/KhFAmAAAAAIDcwMLMHRGijM4Nnte9BkcQgNYB4kzKzN+w/WExKs4mSzUmoQo1OkmEiTjhSfp8RgdNYJ7H9FmTo0Z10OjzxXDQyBCnvOSgee3yHrpiRdzfx5zjFYXCYihTa+wSAAAAAEArIEOZiGhDHbtyPXLRANA6dOJYpsf8H23fI0bE2eOOGUsIE1kqNdVDQeDQBB/BK5DLFsq6+L10zwghysaVRBN1XmvIlLJs0j6rizX6uAqUGYKiQPOpj51Cf/anUwpVlBpJocz2m04tbNd3fjHQ2I1JShCQeKqTaLi5dwMkw/O6lxKRvImTr3P4tZoCuYlf+4loqxx8f2gPDgUAAACQGqtrcMzo9PHvOQCgyYE4kxLz/337g2JEzNaT/1aIL2m5ZgSVCy/qeE2MqRBPqr2SJr6oyyPDPOouqlqLrAZEomaB5m///im67/4Retc7ZuRCoPn7VafS1vuHaNee5rWcoCpT++J53SuJKBzqufFbrr3KZW5jsWad7w9tbfc2BgAAABKSJH/MEvnwBb/HADQ/EGdSYP5P7npQjHhzy5L/kiG/TFTeGRNRYURxRBnb+6hXUpZvcsao/+sijv5ZznFTj0DzlXUDNHjEpw+8b2bDBRrJtz9yNv35+39Pjz7RpFl0UZWprWB7dC/f7M12sO9LeLiWhZo+3x9a1+7tDkA7wdVi5rAbj5RXG7LjeIhf96AjCZoJz+vur3NzV1c71zksKWkc/Ur+bgEAmhiIMwmZ/9O7HqQRMbci+a8tnKkeTA4ZFatbRgttUsSdIODQJlNIUqCELlENoopldCyBRo73ywWaW74/WHj7ob+dmdbhqpuuLkHrP3gWXfqBh2nwaA7KSgFgwfO6pSizxpEoY0KKNDdzUsI1EGkAaE1YjFnBncB6OpPL1X88r5s4bFJ2ejdArAE5Z3mdmzcDBxYAEBeIMwmY/7O77qdRMVf4FkHGVKWJLP/Xih7WJAyOGKrBLWMQcIxqiklgqeqKiSHQBJy0NgiK77lNpUDz4IMjdNMXT6Ouzsa6P844tZM++fbT6V2feayh2wGACSWZYJwbyDAs6RC/2pij5KZZWkXwmc0ijXTr9KKjBUDzo7jwelmITZvlPMikpnv5GtaHvFYAAADaEYgzdTL/P+/aTSPimcbkv2RO/iuSJv8lg4tGdcjY5jN+RnHPmPLSkPZ5sog6ZEgQbCGWQFMqtx2UxK3Ndw7RG9/yOH3z62c0XKC56PzJdMWfTKdbfna4odsBgAon+u2v8iR7I3d85BPqQ/U0IHfUVipPz03rkx24LZ7Xvdb3h1DiE4AmhF0y8vu7KsOtlwLvtRwuuYmdePWGkgAAAIgBh9XN8P2heqqFgZRBKe06mH/7XbtoWDxLCjNCT/5rc8iYKjXVSKk8dUhUmevSOKVctaGcdUCBcfz4YCmJHXc+bQjC7bHNS9oy+f2u+4bpjasepxMnGltnW5bY/rtVp9CsU6FrgnxQRZiRZcbWEtFc3x9aKUOO6hVmJPKzvIxedtRcSUR7LbPLJ+H9LOgAAJoAKcp4XrcMTXwoY2FGR7pp7uBrCMoEg1YnDacp3KqgKnyNX+l53X18fZUdqzsSJqQGKQJxpkbm9991N42IZ1uT/5LmoEmKXg2JIspcmwQaivhfF0OoRuEl7nxpCTS7h+nFL3+EHm9wUt7OTkFf+/BZDd0GAKi6MCOdMrJ6wxoXIQKKUBMl0sgOFgQaAJoAzhvVaFFGJxRpNrCbB4CWgx+abEywXwNwPQAT8j5RhptL0d3zuvfwNf5WdinWm0cJOEXrj7cAACAASURBVATiTA3M37TtbhqmhaEoUwrRsSUANgk0NtHGJpbY5qn4jCKMqNP1aSaxRHfP2ISXqkKKe4FmcNCny17/WMMFmjNP7aS/XIn+JmgcSo4ZkzBzHTtlMsnboIg0aw2TDyVx6wAA3MI37/JacX2Om/oS6QzgnFYAtCJJwoD7cEYAGr+er1FcMVuI6AYW3bMqFAESAHEmJvP/a9udNCIWFhLVhmFMZblmtJCmNPLLqNgWV9X1YpjPNK/+uWrLiRyyEWge3TdKfoMKJ8ny3u+8fCbNOg3hTaBh2CoyXen7Qw25UeMcM8sUF80AJxIFAOQQFju2NMlNuxSib2AXDZ6OgJaCk+ibHnBUYxPyuwGFlSy0wxXTpKBnGYP5v962mUbEslIYUxyHDMWYFodQnODlSEGjLImvvnx9XPi/4A+EooeWlLeUHLjic+qy4iX+La0gal5RbMuakgQr/0iB5nVveoy+dfMZdM45XQWxJGtkeNM/vut0esvf78t+5Y6RIWRvu/qJWCt5W+90ev6Fk5p4b5sPtvdfa9jwKxtdylreYCrhVutQdQWAfMK5ZfIUwhSXSzhcElXhQEshRRYWHk2/7yY2cWccANAiQJypwvzfFISZ5xWrMo2HMYlAlAs0FFOsiUvBKaK4cVTRRWjiiSpehIKIqUw2kVmc4fdVqzcJsosuRnElQqAplc4urrfQpn7EvBaB5lWv2Uef/8xp9KIXTmqIQLNkXjddsGgSbd52PPuVO2TwiE+btwzFWsElr5rapHvZ1Jis/RsbLcyEcBjT0jxsCwCgHO789TsqjZ0VyD8DWhLfH5L5Qfo5VMnmaBvgamYIZwKgxUBYUwTz/2fbb0rCjB7GpGITY+oRaUz5ZkzhSFHTbblp9Lwx+vy15J/Rx3nm5UWGOGnjAy8oX16MECfJNe/ZT//1q+MNCXGSgtCHrzol+xW7RB6HOEPKkXugJkyhQsjFAACIpEWEGQlcM6Blkcl9OY/bMg51upGI1vP7S31/aAaEGQBaEzhnLMz/322/oFG6cLwqU8zkv/UKMuGrKSSJFGEisIQ2qeFLNmcLGabbwol0KuYzrMfjtqrVQaOGV6lhTp7Sxr7dQSPfSoHmO18/k+Y9e0LmDppnzOoqume2N7l7RtQo14453BZghUOG9CTA6xE+BACIooWEmStRmQa0AyxAQoQEoI2Ac8bAvN9u/QWN0MU0JirdMgXDgCX5bxxhxuYsMc1neq8vhyyvUW6aetwzxsGRg8aUKNgzLbvcQXPVO5+g/U9mX8Wpo4Pow29vAfeM2s7VBtBIVhjWjY4KAKAa61pEmMlF+CYAAACQNuhmacy7c+ttYkRcXFaVKTC4ZlxRJqoYRAqyvJZND8yfEdpyE4c3RQg0ccWcWgQao/iTjzLbBffM4iZNihtLiDOIfqBRmKqU9ONoAABsyNKqnEg3CwY4UWk4bEtpnTdCmAEAANDKIKxJYd7WrT8SI+KlxeS/ESFMlFI4k44exmRaphrapCf/1V/VbRXacqOqN4VGoDgVnMIPp1HFKSrESZ2/InyqPEmwFGj6bzuburqyUxKke+Ztl85ozsTAtYguDSpdDsqocM5wAl4AAKjA87pXcGlVV2xkgbg/Kg8Mh1Ut5WvYyhpdPDJ0E3m1AAAAZAo/3KiFdfw7V0hcX63UPacrCKuu9UOcYeZt37pejIhXFZP/GsKZQuKW0I6LMIgyqgiivyeLgKNPD8UXveS2aRlkH1cm0Him3C/Kh6uVzg5zx2Qg0Lxx1eP0ra+fUSh3nRUveN4kmjbFK6y/aRBBKSqvGoVqWgCAXMM/8mXuKt8fajlnVbvsJ42Xzg+rE22tRYxlQcRF2ONeWS1GLjvu9vB8/Tys4f3q5WTmeh4tFSnMmJKgNyXa8dzjOl+YIoqV0arfFxWtrUMOIZl0utjOsVqvV82M5Vxri+9ZFvBDBhPOr6F1PNzo59+25cTfD9vDBSUXXOk3EOKMFGbu3vplGqa3lBwzYd/ahTuGDIKMOj7CLaM7VwrChSj9Y3bHiKgOdbxswKkINOH8pSS/Ae+rYeYUBJpd9w3Tpz5zkD7wvpmZJgi+/OXT6SvfbYLfIT1ELgrXoXwAWDDd8DXyRiet7TEsp67OAgsUK3hYaiu76nnd4dtNnFxyay2d6kajPFUK99PYkef9HOD96+d9zKwTZhCMar5pVPZ1qeWYXlxjGGNfFeGjVmT7rk4jvIjbRoo0fSzQmG6At7kUZiJu+KsRq9PJ33X13NXdQmtZ5EoNz+tW17c8Ytuo1u9LRCe8Gs4FkRhtrc5LLDCq+97wpPquz8c0YBFiRZx2pvG23qYIs/1ZbKtNLIlB1XO1jnMttd+lGN/BevZZMiMv51/ca5gyPyltHA79OSqUca3ndW+w3C+u03+jhex4tzPz7tnyQRoWHxcjgmiUO/uj7JwZ4ypNimgjfGVaoFRy8hXRwjQuUD4fkGGaKJuvJBCZKkUpnxOBsjwiQziWtlwiw/8RlaiUoSSQqNtApnmFZXyV+fVt1+Yt7au+DxXzitK+ff4zp9Hyi7LLBfP4/lH6097flx9/3kahj+Pj+r1vnEnPPm+C0+1a/MoHqZDgup68SWPa9oftzsv72EdOob/48ylOtvvwoH9o+jTvJCcLb1LYXql3Yk5qxadTfKNwhzrO94caZuFKa3sMy9nk+0Oxbor4xmw1P5UxijE1IMNR1uWx8k2K+7mXb376XH9HPK+7X7uRXFvNzkzjnYjemPt6cVxB0HS+JmQjl7B20o4sTKlJi2WHboXL4+Z53fXeBEceB257eTxXVVlOrHOkGnwOreEOYxIxbi8LeutM7Z7gnIp9jauVGtq66jbyfhuFR1fnStbrqAdFjFidUlLx9dzWLrfZdK8UB+u5muK5VnAe1iNyO7iup0Hi809p26TXMJW97By1CSO1bJuKeg5s4++FylZer3o/IMWjOep11fO65edu0D67tq0TAs/bseU6GhEfF2qn1VQyO6TWS2a1XB5R0/VkuKZxYeJcy7Ti/0Hk58vmsSTnLa2LlPm8qHkD6zIi51crBNn21bYM0pbH4z645ik6fDi7MKNTZnbQrNNzbEhTjx+qMjUrpo6Kk5tekB/kzTE7DA7yDWdSYYY4Qeytnte9x/O6cxE2wvu5LsX9nM3LOSjbjzsZuUDZ14dSPKYqaToyrvP9oZUuhRL5NNn3h5Zyx825MOMCKZKwSHdHCh24qvD6wnNoVQqdmtncWdhTR56FTJFiXsptLTtSN/P1cGWM+VsevkbJ80A6EG5OsdqbPF53yOOXwK2RGfw925DiuTZbOdfa+v5N7r/2PU7T6Snb+Vo+12Rbr67nHkAKO+rA34eQQ/p0y+9WDz98KKAI6hW0bfdr3q4tr6Yx8Vnd3WAMYTLlnUmCLsqYBAYVW9Wmap+PK77EmScrgabKsmMJNMo0mf/luvc9SWNjCY9ZTGSOm4ueNzmbldVKxHG1HieQR0zqf8vkYwCV8NOVPXyT4YLwRnEruxcagrKfcW5+NxmGalzLnc6Gd7xq3Nd6lr8ijh08JrJ8dZ+L7TTBYUxOhSAX8DF9KMV2j4TXt9XROSQ7Etdzh6Zh1wQTilC9xVFbz2bRekOexNysUUSZ61PuMKss547zBu6s5rEdevl75qLa3Wze/7ZLds7f41DwyuKaWSY8N+i7fYnyIGyDNUQ7223KB/Pu3fJ8GhU/kGFMQnXKUIQQYxNkahFq4jhp9PmiXnXBIparxIFAk0Lp7NQFGmVfNt85RLf9/GgNByoZf/GSaZmtqyZkm3gxB5BbOFZ5r7Z9l7T705dWhG9e+vmGwnZzLM+FG4noUiKaK8Os9IGIlvH0Gw3njop8Krol6yfmMfdThtRcqezjCsMg93Uuz7fRspwe7nita8TNmXJDGrWvxBbojZyT5ErONXMxdxLikNYxvLIR5atzlCsgFuxe0e3prtYV9xxKg9l8TciLs24OP6BwJVSryM54QwXrRsCOpK2ORRmdsK1z5Vji7/XNGbTDDbyutoC/U3scCV7V6OFzO0uRRr0f6eNjHbrQBtgpWqLtxJl5926ZTWP067KcMbZcKSbq6bfGcrsE0dP1V6HNa1xmjcJLOJ9XZT5doNGHMrHGsUATOYy36cc/fYBGRrMRHeY9023+mLpQhTSEMrUCph/xXIVsgGTwzcvWiCdKMvRjme8PyRhmmaDVmtCSw0U28HxzWKxZzzcFJq7PSryosp8DLE6cxCE166p12uV0nm8lCzVrLfsp3Qb9WX5nlKoMthvSUGiTx3UG7/Ma3p8ou7S+nlhJFGOwthHCTLPBN9rOQ5go3jnkipsbLdAo14q0QmviMJuvE20h0PAx3pJxG4eEwnlmLr0osvxeM6vyIoK6hPexP0Phz0Yo0mTh2OpTBJge7bxaracraL+uWED3FxKZViTONSWjjRHbUc0Jo00PTCKM/t4oxkS7ReK5ZzISaEjv8CcUaCzzBqb59LbnQYY33fK9IxEHK0VEDgUaCDOtRp+hw7kk684mcAN3BPotOUjWs3ukt96KDyzW9PJNyXrLbM7Fiyr7uZaT562pN7yFhZo1Efu5JKsn40qn2tTp2csOlVBoS1rVJg2L/KY0EtW2Og0SZhrRcSZ2EDSk86hcKxrRoeupsUJaU6K4RBrNtY12kbBAlKUwE3JzKwuB7PDOwokUl00ZVnRcabhv32h6ANJW3bF59275DY2JzlL1H19xypAlz0zchMA2gUGfR59fnxZXoNGXETu8KYh0pNQk5FQTaNT/vaBymXEFmmpCkW2cuh9E9C9fPpSJe6arU9Czz21CcQY0DdxZNXWcQoEml7HboDoRnZABrojQm1bIhzyPWKS52BLutMRVpyRiP7exc6RuUUZH2c9LDTdHUhjKwiVk61RLEWppyg6VpKEBA8hjVR1+AtwuwkxI5h3WBgszIXnpTDqhAS6RaqxqoECzNKOwORu5cA6lDd+X5q0yZGbnGN+3qfft1t/ZHJeVSZd5u7e8iHy6sKxMtamcswuEJuyo/4fvS4KEKJ9GyvRAEx705enzBAaxIlDWo89H2nxSUFHKUpvm++6ac6jDE5WfjSKGPjI2FtD1Nz5Jux4YsewDvxXBeIlvfT5t/tA986bXu88Jc8GiSbTxtoycOnGoJr5kV9AKpIRM0Mk3rfoNVegGWJNlEk+QHO6AmZLEOa1cI8NllDLGerjEEnmTzOJGmvtpE2Zc7ucG3s8NWic3FKGcPLHkp7B6p3qA9zXVp3acsyFpR7Kv2XK+NIAZGXeiTOdQyxNxTQQpkUNhJkQKNJTmb09MGn2uLZcOE5dlxhvEupx9j/dmHbbL9+0r+D7LmvS+bcQZCujnapnsikTAZHDLpGGy0IUYmzBjE2AqxgfjQpJBjCmJFfrnSV+mbISY83kWgWbAowXnTkzUPDaOHQ9o2tQOIjFc3F/TttG4e6dMoCG9zcdFr298+zC9/nXTqKPDyWaXeM58N+1SN1FJfn2TogWahNXcodRv2ns4wZy8qZEiTd6eVgAz6wwhPjKRXK/ryjW8/JWWG3V5k7w1RbHPJMysz+ImXIoOfHOkuxCkCCVFiVSrZvC69KewLkWopInBB1r1yW3KrM6qo5GlQyeHmK6JICU4+Xuez620f3uahTUpXMtzQ8rVA9OiUeeUvJ6vjhLf2iKYYd7uLTeQTxMrymWHRFVrqgeTg0PVQfRcKWXzVUkMHCfUqFp4U63hQWEOGiUUShwT5D3iTuGQzpmyECfTPuj7HLVP/LrvsVF6+JERZ9sdcspMx+pPrdjaDjQ13LlbEZE3ZAkn2JMd0l7ko8kv3AHTXSvbOClsZiWFWSAxnU9r0giX486ALiZuSylPSiyU740e4nStg6pn+pM5p+6gFG7o+5qthHWDyKpcdtYOndzALrBGVHNpC/had30T7OsN7VYxi90zrRSenrf8ZQNZhjSpcJh1ZHu0R6YJn66xumLSTEFiCzkShnl0McQ0zjSNyJ4cWFlHLIHGJHpY1z+eq0YcFyQeysB0VYuYRJVtUL6s8QP9o393X1Z72tScfbWQY6ZlUfJprI3Yx9mchO2gLMEKoSZ3mDpgexv15IzPp23a6J6kNzN8s6l3BgYcixVGFIFGJ80btl7tqf9AlJU5KfydThr6gupM+aKvHUN62lmUygIlXCxN5PVtEw/670dS2vG6lKuy4vXCv/u5c83k+SFEy4c1zdu95b1E1KGGNFVUZQqpu0y2litGHa+HIOnvSREYbKFLRocDhyUFBnGitDkBiTB0yZavxjQhIsRJHPVIPJSRK0QXhwJDnhwl10xhf9V5TO6lgOgntx2ld/xVD3V1ubOOjI0VBZrBw/lI5hJoYoxAjpmWQyrxUnjhG9qoH8JLeJBVATZyeIe1DDPIBFOHOlPHjGn9XLZW7RjKp3krE4TJmW6wG7afMt+L53Wv1QSj2ZyvKY0nfXo4xkrH37OkT5e34TqQH7hT067hTKsRzuSUtES/TXxd7zddO9jx0su/J0mO55IUr8vNwkqLQLmnysO4ekOI9iYQwaJ+N9IQmTaymLgnDAfic2sGD0uVIc55llTsW6cUS7Ddv6zmbSO+l4pCnXdP6+ecCehjuiAj1OS/tQgyJreG6fMm8cWUGyYUEkz5ZnQRgjRxxzSPqjVEjasgpkBzyCPxcMbhOmX7qgg0tv2KFMGKgpYMbXLNseN+oZz25i1DGTRSDFRxxn3BKtAgOLnoCraD98X4kQqFGmkb3ss/fv18o4XQhsaxNsPyjkY4N8tqQ2nVvnqeuFpiztc3Oukhi5orNYFsNeefSfM7cGMG+5rUaeU0NxWfA67dYHuyTvLokLQ7ouE1PuzkFDpULAIt5WPT22inDrs60g5zDB9EyOvq1vC7zefkHO5AtkUIFe9zUtFvW7W8GTR+T7Kar6mr+Zyu9/xycV2ul23K9bKfzyH1e5TGd8gosBiq/pTBocP1iDN7HIlfSR4abOOcexX3Q9q40m8XX89W8rXM9OBrfdKHEPz5yGXUcg+nz9vS4sy83VveSIHMNaO4R0KiXDP1dl5FhDigvyeLIFOaR3HjmMQYdR6yiClSy/CC8ZLhtvlsE7Tkv96jHY3p2JeJMUFlgmBF3IoUvZRt3/v7UfqDZ3Y52+T8hTXxziP5b1vAzoYN3OlcHfOHejYnLi0kL/W87k2Kq6ahQkGbsTcvTwdlJ5dz4ajnz+w6K0no+zSQozh0+R25Q/m/h2/s0gqryGpfk4YqZiEeuc5xsakVQiBSds1EdqSVjsaGlDrRSUmj4ljIek6Kb+xIKW2yjts87wly0yDptaiu5O1cqWaDoVpeXHr4Wt3I343I8ymEfzcTu5NapGpTvblzBupxm/L8su37+Dvdq4UY5z5cstUzT1xjHJt2vhlbrhky5IdRXsuS2OqvtjwqcfLGaHlZAn2eWpYlOdIgYca2vaZpUfMYctHs2DmcxR7kB+SYaUukSOP7Q7JDNFc+uecnp3FZzh2pLZ7XfUhW8UGumkzIm23btD01PdW2xJznJpSOb343aaPTfHKf1dPeRGFNLVi6NU+E+Thu5JAEOVwcISSllW9CuvCW1nJsuTLOHAd5Q+KSxndPtvfFUkSIe52R87HocKkhWXhLkELVnCuTVNXjY7Eiwbm1ukH3IHJ7l8U9n9i9t7TGey4T7ZYIWWVrGg4X+bDL94fk9exKFhZz/7CxZbts83ZvmUEB/VFkjpkQNcypVkx5TaLeR71WCAsRwkvZZ4LydRqGmgQaT5lXVmV6OAeOGX0b9XE0/lohehFV/P/oPvehTQDkBf6BWs0/UMu4g1DLzVEPP01EUmG37M1bSAZ36vRz5ZIaj72ps5U3EUpv99kpVghphsSmLdkZbTDye3OdFMd9f2iGFMr5OryGB2OeDiaNsvJX1uvC40TzSyMqATqBv3NJk1rLdq9JkFJh56mpmlsrkOS8Wp/G75OSjL0egaanAYlywwp7NXXq+buddFvb+R4r1WpV8txNIixmSSs/T19hFGaclco2VFAii7ig/G90z+gCjWm9NoHFNE5dV5x5icNgZFWmPR1EjUoeaxFfKgSaaq8G7e23v3OfC2bW6a2f0gk0H/IGgzsIS9lRcyXH49dyI3oJCzV72FHTzk930iSv4RgmcaGWm0593k15SzzLnQ79O5DGjdz6JsnfhNDF9NjErg0pEPTVeq6z0yypQHFlSkLv6owdNEk7s3WFQuiE+dsSbkuuYEG93pCtbWl2bPmaWO/y0s5HFMXeJNUE+TxKInC21DlYI/IBSVtWD2xlcebdhb+m5L/V8suYjDShwKF/wBI2U/a+ViGhFuGFFLEixnyxBZqjIruqTNUwbStp/9um6+jt5JDBIyiJBPINO2rk0wR5MzuDXTXXsVgTh9BRI0Of+tkyDeonrzcipkSxsY41dzT1xNROE88mQN+uNM7nLPc1b+VK2w0pDFzKDpkkIWJJBYqNaTnwuFO6MkMXSdLvXGoV0bhjHVUVp9lIcl6lLogkEC6W8O9KFvSmIK6jJHz9rPK87q2cP7FtaF1xJqALErtkojrxcUQZ/b1pmu6esblEkgo03vi4qgLNEY/E3py4PiKFJLvoFdhCvTJk8CjEGdBcsKumj8UawTkR1sZ8cio7hndApKmbvXktY8w3p3pOlrjH2DRfXsUZvUO9JIXQPeRxaQ8G+Al7Gud2kuvnQEqOrxJKgs0sSCIwbkw7bxKHhSXNG5IX6u3gbnKYj6re8NYs7jFSqSbIIlS94mYrhDUldWVKF+GtSu7Dla0eUt+S4sy83Vukojq18I/mlhFJ8suEVBNcSBcRyJ5stx5nTOSQUKA5zOWyG6wrTJ7k2duMLO4ZnQYIMvVw7DhqW4N8wjkR1hhCoKIIRZp1yElTE3kVLEL0m9TZMY+vHvKWWxHKIqQkKgOKkvRtwUA9OSkiSHLOuUo+3efaPZOCqO8q3CVv+bHqpd72dSbM8W9BXKeuShbiTJrHvd5rQ9LwxjyQlrAXOrVv5dyHYVj96lYLrW9V58zSWHlmau0TVxUIqieiNX5OrahEBjFCd4ro80QJQfq8nubY0R0zjSqXrdGhRlRZBS+qTA6sf6YJePjh5k5OPHmSu8b2BB12tnBQE2oIFBGdxOFPUY4a+SO6FfloYpP3nB+m7YtzbPV58irMhB0FvQOa5PzNel91dxPIht6UK4DoYYC14CQ0kgUf1wJyku/aRleiryUfVVPBv8P1lHUeSMkNFkU9nXfX9xXbUj6f2tZByeePi+/PbL7PvIFD60OxpulDoFo1Y2m6imrY9wzCl4CEEOMihuBpguzj1Fd9mUJZrnT26CJDlc+VKBtXtmCrWFFYp5w4Ikg84uVCmAmZN3cCbb7neDFvkHYMCgiDwGaaz8DzntvtdNuHh/PlhjnrlC56dP+Ik2Wfc467y4gQ5GajQSL4Rl0+Tevjp51rLHb02fyjmVZyylYmt6IFY9q+OHH/+k103m9St2rnchL3VzMl2YWIWh+b0uy8JnSPpN2h1NmQIKFsHJJ811wLCK733TX15miRoSSunUP1bJtrR0nenazNhrxfvN7xNodijcxTM8DHsK8ZSmfrtL44E9VHjnrgL/jDqghDBgGmQnxRlJAKYSUYT1BsElmixJzwvYgQXaQrxq9doKFjROKB+kKZpAgxYYIb58SsU7rs7UGG8SaxxsIpJ7tNdjw6Fn9e12W95TGadUqnM3Fm8mR3BrwjR4NHp0xxtniQAhyTvYI7FX2Wm6abPa+bINDYcRjTnwryBkceQ404N9X1PK3NE+0iWvTIMDWEYdVMlpVjquG0QylFKMM1IE2SCFOur5/9TS7O1Hsdm51Bp7ouZFJgh2IkcoWlSx9fK7O6H+hRhBrpKF2T93ssldYUZwI6I/a8qgijulNsVZziuGX0+cuEBU1h0MSFkpMl0hkTIbpUiBhVBJphWZWp/tPgqafHaNaZbk6jhc+cWHwTilq6K0YVxPRcQhy2ZcwxFBAtWzrRyTaHyFCfzdvileve95hbcUaKZ/NmT6TNO46nt1DlPD/nbHeXkSAI9jtbOEgV/uFbyk/ZTDdz0mWztRmfYoBU6c15wmi9E9NMeZP6EyZUXeq4U1LrsnPZKVTY5OB6lqQKTRadj205zIMxkEEeq7w7G6vRivnf5jg8Ls1+vHOFFP053OiOBmxXmAdRijSrm+EetFWdM6cX/prKaNeK7sgwumWUdVQLZzKJO6RrKCzQRGIRXUL3TByBZliQ92Adp4DSBoODPtGZdbZtFRb+wcTqbWs7NlWY/YwGnvpafhwpzrh0IEleuGAy/dtP038gOu9ZE2hkJKCuLjfbfsbpnb92smDgDJlAWFZs4qe46lOSHs6HgPCJ9mZ2wpwawE7Si/wKlx18FnBjL9/zuvMuzrhwAmZVIrhe8uisyqKz1ewPFfC7WwMOxL62fyglr/8yxF06qRu0Ccs5zH4tV2HLLa1cSjsZel9TS7AblMo/Geaxlca2TTfMU1Fe2zifJfGvF2Pewx5593cS1RB+Y8JlMtvODkHz5k6sbDP1VX9fjUDQvPMmONvmkKcPxGhY3icpcHV0uBNmJH+4cFJ6C1MSbb/w+ZOcCTNjxSZs+x+0ZoQ7YaakbLI0caplXgEAJZJeL5s+kWLG5Momn5Ftvy3D3hDuBxKC82c8ufaVDU6wfb18gJjnaqIt55yZt3tLcru0LTzJ9j7uKylCQrVwJFuelbh5ZaIcNCOCvEfSqcp03wMj9CcvSb4cE55H9IY/66GP3LQ/2i0Tdz94vqve1uNMUAg5eDh+Ap9du4fLq1M5wPMEveT8KXT75mOpLrz3zdOdbbMQhSOGH7QmhZ+SrDWEJqxxVVEENAV7m8wy3jQCMX/nkixiieM8Dq1EnkvCuwTnBgCgbqRAI0Pc+T6wUSGS0kUjfy9X5FF4bdWwptoxhcSE+V0M+UyqqRQSfgAAIABJREFUCzJanhQdfXrxdSsFtIEE7ZFDQMEcQWIOBbSShGJJjJtXxuP/VTFnhMh7MIYwE1P0+O2dQzQ8PN1ZSM6fXzSV/ukbTxXDp/SEynWIS9OmerTiohRdJBa23B0v30zI00+P0ckOkxRL8Wf1a06h2zf/PtmCFNfMBed305Qp7sx3nlc4ynDONDEc4tSrhbHMlmU9kXumbVmXd0txk5M0J0gvC6ggmtyJFBkJawiPAQAkgu//whyFWSYKVlnC4fe5y4HXmmFNtXTareKJ9l4PpwlDmyJCkyo+S/r40ob2k6A5O65esGzH2xes3fH2Bet3/PWCTTveuWD9Pe+av/aea+YvK8QhC1pXc4iTGuY0wjlm0ohE4vVJ14fLXCldnYI+8Y7T6w9jCgmKQ9+nTy0s0zXb7o0pzvAxunf3sPNtesaZXfTKC6cmX1AgRa4O6vunU506fg4f9p9yt3SQIaaOHsInNHKeJLfQ8TOMjvPEqZH25XYkaWjL6jzbvXNEHit/5D1fjSuc77d8oNCwvUsHuJBB7uAHNfL7u5ZdtVmzPINS8TXTujlndEJjSShikKWTbxJibOOjXmPmliER9O74ywUX77hqQeRJec818/fec838K0nQSvLoUM0CjRRmHqhRmDHtvyY2SUfL4JE6anDXwEXnT6YrXjq98ngJw76rk0OXDR+Gy189nc5/rtMykAVkrpTNdw1Fi0haO/72zhPOt0sKKR97+2mFyk11obhmPnH9KQUXkkuODwU7nDcKyAJTJybXQkSDyHuH2NQBiuN+0ufBsXdL0pDBnpyVh243kog+WQgIeRQpskgw3uzCF5yqIJfIsCIp0vj+0BzOR7Mx4+283vLwqWG0ojhT342f3rkX2rSKccWXssTAJrHGlti3OPTueOvC9bVs5j3XzN9IglbUJNCEjpl6kv/qzh8D27e7FRZk7pkPvPVUWv2Gk2NvUwl2zLz/3TPpA++dSZ570wz5fkD7nmAVTDneQcR2/+o3xwtVj1wjXUPf/oez6IIFMUO7SoJMccOnTfFo/U1n0ote4D407PTTOhqV0R2kCNvs4Z6oTt5FC9P2xQmh0OdBWIRD2C6e9Ank6rzdrOaQPDoRnH63+JxwGX5Qt4CQgfMQ162ckVECbJAhMh+N7w9JZ/VJGQs1uXoggZwzUQlmbbll1M+q2OYzl9Lu3bGqNmEm5J5r5m9b+Pmda8ijPgpNK7YcNCdEMcdMwqpMFSht89OfHaPnX+i2sy4FmisvmUGvfOFU+uTXnqZf/M/RypmCyveXvHwqvfOtM+i0UzsLy8iCXQ/UEKLEeXR2ZRDWFCIFmq98eBb999bj1Petp2nXg9XXLV0yf3lFD73pde7yCxnAD2/rsJUTsIU0642uS3dL3sUZ/ZgNxMxvIY/9KuX/HuQcco6Mo782wUrCsvdwOdlxdf4mWa7rcFHXy08ieK10fM/Q7KG4/Ybk/HG5OPvNBe0MJ+ldFzpBPa97Jf8erXCURLg3TwJN+4ozulhCESKNabryv3TPCBLlyyx7ryT/LY7v3fHm+oSZkHuumX/jws/vlCFOK6wCzYhHoiDMpNiZNrTL5t/Vlvy2XqS4csapnfTZ955ecKfcvfsE3blziB56ZIT2PT5aSHw867TOQvntJfMn0rxnTShUKXJdCUnnlp8erj6TQRSUAs3ihXWGHNWIbMsXPHcSXbj0bDpy1Kftu0/QXbuHCsJSIUzNJ5p37gSae9YEet6Sbpr7jK5CuFZWbXnkqD84dYqHqhCtSyOSv6WBS1Ep75Vy9I563I6QLawN4ow7+hKKMxTG4iN5c7bITonndQ/UeY2UwudK3x/a4Gijex0tNyTJNcFZ54odQ42qKpMWSX5XZjg8pwCoCp9/hXOQc6KFYs3KlO4ne7hyUy4eCrefOKN3iqmKW0YYBBabQ0ZfntDEkuLne3e8KZkwo7COQ5zGqzKF6x0RLMyktCYytVtQqHe877FR2v/kGJ12ajY9dykQdHQIWrawuzDkjV/8xuDqKbWZ/fz77veP0ML5EzNz+BCLNNOnefSC8ycVhiiyFLnGRuk/slsbyAA9RGJTkza6a8fPSu5Y5wp+aqXfAMW6WZcOGc/r3qvlhejN4362ClLg87xuaQe/JOEuyVj8PdJqnnXTtEAC1iToTsNaWB33u1kLHDbkWqBIIs7IzlWvo3O16QVKvibo1+G4rHRxTgFQDwZXzQq+p1iVsEFX5MWx34o5Zyov7oZEtmXTSu8NOT9sCXa1aaXKTdGf6d3xxtSEGbnMDWXr8HiQVadTq8rESZS1cXpbfue7gymsrPnZed8JGjxqSZBcpR1/selYpsJMXvF9op4e7xPt3g4tRhYJG7MgaWe3GnlNxGp6Yl7LTYx+Y7+kzTvfWZCW+HUzl8PPDD432jmsNcm+L3d0vJwLFOwaTJIvqS/tSmN8Libt9OWFes+rVchBBfKKdLv4/lAvh9+1RH7DVuwKjifKNVTwKWGqRGR6X/YaVI5XE75Gl9bu3fGGFIUZGdr0rvkDJFiMCtcjHTMP1SHM2NrANJ/hMz+5LcIt0iZIUeGbP1ZCmqJEwbI2LZ5XsvLVb/77eLs3Ix077h9CyEPrYEnUmCTxY0NuEtk94prZWXeEq8HtrYtSm2oMvzIJBagI5BC2Z6flUJMCTSbHi8///iYOfUyDpMJUX5rXST729Tp5aiXJvvekUK1MJ3PXmEOSuF9aqR1Ag3B5f8O/eUnu03KTY60tn9OXOUFsbhqrQGPocNucMuPjendcvihVYSYkEMGh0nrCUKYTDhK2Wp1HRUFKhjZtv8d9Oeg8MzYW0MbbByMFmcAmgvH7r647XMjt0r5tSDQyQh/LwabkkiZ9emX6sYwrzpgEgEa1QVZiQt4s9KbtqelGnYUcXShYBfeMc9K8Eb7B87o3pO1MCJHL9bxueV7d3ObCTNjJSPIEWLZfKseKxfUbki6nBpIKU5fweZQYXk6z55opwXk76j2vCjmoHGwWyA9O761YmLnZ5e9Iq1Twah9xJo6gQlXcMfp0w2AIb+rd8Vo3wky4joLYVMoxk7IwU63dFPo+d6ithYVbfhKRCNjUjob3m+8cKibkbVOCIPBPmuF9tW0bIALuyG5N68YzC/gHuO6QGIs7I/OnG9xByerJ8eysXArVsFj699aZ18F0Y4+8Mw7h78+NKa5BOqj2pP30k5e3p4XCR9IgaY4PKSr0JxH02S2Yda6RJAJCyKqkv5P8+VY8H5O0y/VZODszcqmCSma7Ek2Y8B4g/B1J/T4n4fYnqRaXKi0nzuw6b1n5TX+1PDOm8XFeTZ3ryvCm3h2vcSjMhOscFST2eunkmFGXG6XzGMQrKSw8/MhIihvRPIyMBvSl7xys3o56qJ1B9PtM38G2FbkOH/bX5+kCmRf4B2cdPxFNfOOZIasNT8FrDYnRHReNuHHL+onhmpy4pEznWV1tYQmzWZ4XIaqFWZMwj4dODz/9LIg09d4Ms1NmtVwO3DJG0rjGL2FBv6bvGB8bKZzemvVx4WSfaQhC8ndya63uPDm//FwLC4VJBfGbXTlopCjD14NbkeOmYTi5v2JRT8092MNuzLTF/iTnd27SKbS2c0YXF9QEvsKSwDfGZ0sd7KhwJinMvNqxMEOFUKYVnkz+O5ySY8aUp0dNCmxsq/EwsX/4xAHyDXmVWx3pmilLBGxKLq21aUV78uvGfz9CTz6VptLWHIyOBv7MmR1/03Y7Ho8+zV6de4GGb4qvN0yqdbv1H8wlWd648VO8LFwzqnDR0+jqGNw50y392xJWQzF1EtcgvMkd3Nl1ccM9m0WVg2xTX23JL1VCTuf55Ll9kMNl0k4WntdS9DXBYmYaopraCVodde2U07jjvSeFUuxJSMtRJ69fW/j8jPwOsDAgr21bWimUSYcfjCTtm0gHTX8a120WAntZELtVuR4ghKp+koT2rKkmuPN1YkONoq9t3tmK2N9X7znFvy39CUVVOGecImhb2eLjJLgtE1YCk9hSPr++3PL5enesdC/MLPjSjku8WqoyRbVBXIGKLO2huGfuu2845ga1BsPDAX3ploOVbaO3L4VCl6U9FQHsQx95upBguF0IAqLjx4OPwTVjpc9g9V7FN0gubah1wdtkEhfq6dybbjQyuXHjjoy6vS4rAehPj5Y0SoDjJ1mmzlmiJ1yyrDYRrdVGp5YfA0S2+3UOm+cSFlru8LzugId+ZSiMk9N5PldVz/a2WKLpNK9zs7ntH+KOkDwu63joZ8fCQyyoN9TFxOdrWsmsic+3W7Xzsk89P1kYaJewutUp/JYtZ+Grv9YwJEWQWcdC4M0GQWxVNbEXWElyHz3bFg6pCJgP8Xcq1rU2Zhn+2XzPIc+pPXxdWs2iS4VgwwKRnLaGhb07UniIlpt8NZ052AYX7C8tU3Z4w95w2AkOtPeleSP+r+h0B+MjRNm/vTsvWezeMSNPzoc7V9ddlUnwBuv7rM6n77veVmX7Pd7O1773Sfr3H86izs6U89/kEBl+9JEvPkmDx3xzG5HWjqb3pLVlUBS5frdliC44v7vl21AyeMQ/OH2aZ3JZAL5Z5RugO7T2WM629d68JELjTna/5Yl4zZ17mcTQ87oHtA6DvHFbU2N4VE0oApO63j6LGygxcl88r3uttny5n8RlIjMhTNpnWNda7jQlwveH1vC5rN6shTeEK9jpkSnsElrq+0Mt2xnw/aG+jMsCZ5WjSWVlI84fV0ghm50sabuLZvPQiGMUlzWG37s0CPc5z/vuFPkd4fMqjUTPyzk8lVhQ28riwB4e5DUnFN5XcNLZuOfzmjxV0GkW+H4xydYuYRF3Lx/DGRZxReaoWRrjvqBWkXk2/06VfqsS7k8c9qZxf5MWrRrW9Js4bpmK0Kay14jQJbLOs27nn2cjzCx67+5L6JhI/6IV4ZYJTMmS9Veu3PSl/zPQFnlT7to1RD/+1ZHKCTaHFZE56XRpvvFpq9/3ZMGV0+qMjgY0fZr34pbf0YSw+HKp4YnXbH5i3ddo9wE/Idlj+SFP0rk32dydhf0oApO6HwOuE9hK4cJS1WhdFseWbcomYWYTb1tarDCcx2EC08xCnJQKQde2Q/4bFvkyuUdpAFfm6eY6RXJVWj8r+PduY3vsbfZIsTZldxKxUHMtP2C4WXHKXc/D8hqFxuVwz9RNGsc2FHCjXC+Rv5kZF1NIQq7SBLSqODP+BDlKXLFNjxO6VDnPup2vXHylk73RWPS+3Uto1MGJFCUo6ONswgL//5V1A3Tn1qHUNzFPyKpK7/z0Y5VbFCOELtDPI8O5JZf/jmv2t7TIJUO3Bo8E781TIq48w6UwTR1b4pui1CupxEFJIHmHxRK/PmHn3hTW5STsh+28ujAj6c3oqbx0lWzTxq1KWnklCj5+GyxPUrelnbOE2zFKoHGe9JlvGvXEnze0Qf6b1Ybzq9m5MmEupNzS5iJFr+NQ0nZnZcrJwl2A3DP1kVXOupVVHhw1g7g8AHEmGyo7etXypZjmMTlrSO9IB0Vh5uUZCTPX37uExgodh3SeohqFJkPyX9VtRJVCgmle6fx4/InWTGwrqzO99aP7xpMA19iO1pLtVH7eyfCmf/znAy2Zf0bu02OPj/7upBneZ3KwOU0DPx1eaulgqZVUVrt2W3CnvloCyfVJw3K4M29yraSad4dFga0GYeZGFsacw/tq6pSElVdSvVlVyhib8oDIc8xJqBGfxyaBpofzQ2xwIUZxrPo6FhL1p7h576gkRh5L3x9a2kIOmpYVZhR62+Hc1FGuhcBd+67MuQAG90x9ZCXO9Nge3vDvdzPkcepzGSJfDy0pzuw6b9khErS78I/aSQ4RFrGBTJ1sS3JgNZTpzzISZj6wu4eOiuTCjC3kK4bjo+K1QqAZb6/BQZ8ue/1jNHSi9UJz3nvjE7Rrzwn7+aW/N7R5tHtm/Ly85fuD9F+/Ot5SAo3cl533Du85a1bn83KwOU2H/CHhDtaNlm0Pkz8e5JCYak83YqMk8wsrrkQlkFybVr4US8gPsWV2DyeGq7esb5jp31Q6VopLmYa7RAhwPVwpI5H4phzDqDLGzoSZEEWgMQmNl3Dc+7o0RBo+xmEyQ9MN4ybOO9MWLj7+XtquH82A7FBe2gbCTLN0op3Aongzn6e5JkIkzxNwz9QIiw1ph63ZsN3jNcNx25ZyyHYqtHIp7Z9aO8n6q81NYxVsFGHmpc/JRpj5yL09NJrAMWMTZPRpMcLAIgUtg0Dzlrc+3lICzce++iTd/tuj1cO+bNMNAkxUeJN8veY9+wsCTdACzSiFmTu3Dj29cP6EuTnYnKaGRYOLq4QprGLR4aBSpaI3ztMo7sSv4Pn7OCv+Qe7QR1VckU95L3bwo2cK+aFQtGCRZh1vb2SHXoavsMARlek/seunXvjmaoUlpEEV3zbUsL96hQxb/L/c76VZhHEpnQNb6MYqFmn6q5UCVuFzdyWft3v4GNue4kkRsSHJiBsJXz+ubMJOfygcNrTcfJbw9yQPOZEyP1f4PM2D06slxbEmEGiWZxHq2oJkJTost/wu5z1EeCDtkO20EEEr9PYMzNu9ZSkFtKVQAUcOvqDS+8L/VPa/0Ker8xHbHNTPSGHm4myEmYUf29UjBr1+8mlpaZt83qYxZTt9ZTv98vHCND4wzK9PM7RVaXnWttI+HxBNm+bRD759Jp1xevMWCJOhTH/18X20+d4hPmditqPPKove9lScJmzt5yttyONXv+sk6n3zdPKaVFaV+XM2/25o8I//sHt6DjanpeDwlCSVPbZxlYVaqinoDLBF1NlNgSVZbxTbtNKStsoDKnI/VpueynPZ1RK+P2STvaP2YYVeiSRqOZyodk3MErf6/tZyPAc4t05DOr18A74uxn4OKFVBVKfLHGWIs8+beH9TsTSz+0oV+dbm8amcjlIyvhkSN0oXxZq0hDT9+1wDFzeiQl5ENbUsCEuV31rHujYlrYbGwnKjwiQG2CFQz77HPlcaeT7W8duaJbKaTk0OSg4Brqu6Yj2/61W2peI3P4ttYYdz1IO0tLhRdxgrFS/z+LsywAJ/Lp2yLeuc2XXesq0k6FjhnzihJ1Xyp2jhTdkJMx/d1UPHCqFM6SqQZieQ3fGh/W/MPVPh/qgMcdr8u6GmS3Art1fmznn93z9Cm+87Xj4xTjtGurKCUqV3a3iTMr7vCwfpk/90oCAUNRuyHb+y7tBBCDNukEIC37xcWWfCzyV1VFMIkTftsgz0HNedUSVnxtqYHwn3a3mMygOkhLfkJlyCK2vMifn0WN/fOMdzQDl+DXMj8Lrn8LZEPcXt4X27RKkEcj133OLs8ybuzKzIW6x5I+AwSdl5uC7HT8+38TFb3W4OJxW+Lpmq9rkmTAzesLZvYLWxbewsaenzro7f1qzYlFeHQxPQm1EC+Irjw+dTHn9XtvG9Tm5DmFs5rEnyZWu4iCYoBKr4Ypp/fNy6nSsyEmY+vquHTqQszFQLb9LnqdZ+pmll48oFmre9/Qn64k2HmkZckCE4t/38KF36t7+nXftOjE+oCHULyqeR1gYU1U6Wsu2eWaCROWhe9ep9dP8DI00R5iRFmcOHfXrzVY89cfXbZszMwSa1NCzSyGvGMn7K7CqR5ADfKMu8DwVRJstOE4tAc1O8Wc91h51vdHp5n29M6WanTFTLQ6eX93MNizTXpXj+hufrMj7Gmbse8o4iAuapc7aXk/4uxTErolTty6rq1qa8PGXma2CWoXgb8/yE3QV8/V2WYc4SG+F3v63aP00iCgykzWxbpUP+XclLEvq1WYVsJ6Flw5rIFNpkCm9SwkmsoU3j86zb+cIl2Qgzn97VQ4OiFMokxkRFqFJNYU1kCbtRQ24M4UtqaFJ5OA6Hg6lhN/rnyRziJJl1Zid98h9OoSWLJ+YyREd+LZ7YP0ofWvM0/b8Dg0TdleeQiBMiZmpHPVSMtPAmY/tp7cjT/rK3h97xVz3U1ZWqAzM1pAh3y/eO0E3rDh781W3PgDDTIDhsYSX/QC6t07a8jUNI5NCfp5slts+uVPYxrvtnE9tuN8QVZPRcPfV0GGsNa4pYjrrPcY/pJraub2iWG16+6VvJHdKlMcO7iPd1K++r8449b6eaF25Pszpz+JrRy2Escds7TbZxiKRTB1uzhTXpcOiGq2M0wCFkpUp5CcIzEoc1qWQQilcR2ppg35sirMkE7/OajENTUvnuI6ypbP1z+F7HRcjaJv6uVL2f4O1Y04DwxPV8LWuK3+OWFmeoKNDsIJ/mF/6p1klWxYbK/B/rdr4gI2HmH3f10HEWZkIRpB5xhhRxplpuGXXZpEwLxRtT7hm9zSiGQEPl0y54bjd9+IMz6Zyzu6ijI4vWjUa6PI4d9+lzXzpEt/zwMPlzRzVhplzgq8g7ox4LvT2qtmV9Ao3M5/OOq2bQ5a+dSp4QuWhHyc9/cYw+87mD9OhTw0e2/2rutBxsElDgH0k1hju8cdbzeGxtxjACRUSZobgPwzwlhxopTKQlzliWS0reFfVYNq1QoKOdu6Eg0pL7mgc4z8nKDHIXDHAHoi+r72ezizM0Lk6vTlGkKeQO4+NQdu3PizijbU+a4sFeFn3S3PemFWdCWHhezdcBV0Jgqt99iDPG7UhTzN3Ix6ueB1QzWPzvdZjjaED5LjfV/UA7iDO9FNDNcd0zpCcHJhZmLsxImPnMzh6SyX8DFmaqiTOmJL9+5bzCJhz4ZE/8a3N9RAk0piHEIi4UjtN5E+idV8+g5z+/mzo80RA3zZ69I9T3hUP0i18eI+oIyJ89QjQloo0Djlgqa1N7EmVrO5YJgTUINFQ+XYo0l182rZAweOpUL/M2DIWtjf/3KH3jO4dp3xMjFEyg49t/OWdytlsCQL5xJc4A4BLFobYigQNPp6FOLk7iXA+xnhRnieYgrFVICzvH/VGOBe6k99mmR7BVTxiaJizYruZzs9bzcq9yDlpzbiXY99jnSjOcj+zYXFFnW6uE3/1+R66f3ogyz5GkLSQmOHdcbEsSYaRmt3GM7ZnD51KtzmcT25TvctOGwba8OENFgeYI+TSl8I+tk6yE7GjhTet2/lFGwsxnd/bQUdFPY0KrypRQnAk094y+z6ZqQqQLDJbwJpuDxibSlL2vFGmkwPDi5ZPpda+ZWhBsJC5CdkZGgsJypSDzo38/Sj+57Sjte2KUyAsKuV78OSNEkw1trLpnKCK0SRdddHeN5dyLJdCUta8m0vB72XZvuGIaPf+PJ9Fpp3YUhBMXjhq53KNHffrVb47Tz24/Rr/YdKzYhh1EQWcwtH3T3EnprxWA5gbiDGgF+CZ/qVYlK6qiSnizvJXdTcgj4RC+zoTHZIaWvzA8FntYOGmZY6Gcl2GnVg03VB12/XDZJUc7z0hrb1Icq8Rt3lDnKhiHhZGlyrVBFYL28HCIrxGZiB2G3xUy/Lao3+OtfE61TE6ydhFn1lBA1xvdM2R2jLDQsG7nBRkJM307e+iIKDpmxjSXSxJxRnXP2PLOqKJBlHuG9M/Q+LhaBBrSP1/pAgmRIsPzzu+mF17YTeec00XnnF0sxX3seECdHUQTJtj7MwUnxzG/IPhInn56jH7/yCht2XqCfv3fxwuVo0pJeD1OuttJRcfMZIOrSA9RCvfZ19qpom0t551pvtJ4i0Cjt6syv9524f9y/2X42AsunETLlk6k00/voGlTvUL7nBgOaPKk6D6hbOuJE4rhUsPDAe17bJR27Bym//5/Q7T5zqHC/6XExV4xkXHQFZzYfsfc7sgFA9CmQJwBAAAAAAA67SLOSBXukZJ7RutcVwgRxXnW7Tp/aTbCzOd3liX/TSzOWMYLk6tDD22qbIfy5ZJBdKDy/40CDRk+Q9o0ihZqVC44v7s0XYoPz2aXjUSKBfv2jZYqHO3aPVyoFFXAViXJY2HmnBGiqZa2LGszRZypEGKEWZjRBRzSx5sFl6oiTcV7i1CjtblMynzWrM7S/89+9oSCaBPy21C8omKlLdmOlaXDtTYMhZnbIcwAYAPiDAAAAAAA0GkLcYaKAs1qCuiG8s6y0PJ9lDrJ/bueu/TiLLZr4RfYMaMk/61bnAkM40lbjkk4iOOeCbR5TIKBTaAhy7zqq3WcqJyuoo8zdW9Kgkww/r86SEGhI6DgnFGiaZY21tulWmiT3rZkmUdvG4srRlSMi2g3m+Bla8M4VGtDuTsybKozGNn+n3Mn1LkWANoCiDMAAAAAAEAnh0WM3bDrvGV9JOjR8g5loDkpCsNWEoWkRM5Z+CXOMVMeB2wm6rZdVBElot6bpkUOgXm69tnACwpD2TR2VpTeq6/q58vmCzjkKBh/rw4d2mCaFr4Pl9uhDJ0FpwcFMpTJmLs8sLdtaFCp2H9DG1W0r/Hcs7RpUNRyPK2NTO1mfLW0XdxBb8Ow/ZT3sg1pgg9hBgAAAAAAAADqoLPNGu1NpaeVgl0EYQe3aAiQwsyKXUuXDrjekIU37eiho148YSZE74wXhANhcI9o4/V9NY0LlydVAHU+/XP2kZXLLrwURYiSk0Zo6w7K5y97tYlLtWIRPgrikQxlOnuExHTFaWTYD/N2K+1Vfh6VT7PCC4tqzlKbBcXDQ4LbU9kOU5vp2xPjsFUQJe6VxCIWbLqCke3/cS6EGQAAAAAAAACog7ZxzlDRPdNPgn5iyTtSFGaWuBdmChyL6ZipBZNLQ3sfkBaWok6vEH/MrpiydvM0p4vFzREIg5PG5vYwDVUdPYbPd2iDp4QwSadHF+eYUXPK29omql1C90yEk6hqO5qmeQaHDLuICs6kUCDRB9v6bG1brc21Ng2KlZiKThop704MRiHMAAAAAAAAAED9tJtzRvJGEvQIEScHLhBsJRIrdi3KRphZeMPOm1MVZoQhl4jJGWRzrJTNY3CDUISDpqo7pHx7AnaACDVprcntUXXdlnVY3geqmCSKIoN0zNB0ze1TvLj7AAAgAElEQVSiO46iXD6628jUlupG6fPoO6g7i9Rjqo4rtVdQWn24DULfBn01dbRhoK5PF2w6g7HtPz63K8aSAQAAAAAAAABYaCvnDBXdM4c4vKlI6JhZmJEwc2NBmOlNbYF6R7+Kc8boqND/tyV9NY3T59VdF7pzg1/DnDRluWniuGHiOj3CvDcdxaHMRdMVFIWZGYb2MbZXUDnO4KIxu2eCyv23taPNWaS7ikzHg/PHlNqUXTXqUK39Co6YcP6OoNR+4/l7qJSnpzBMKAgz7SjwAgAAAAAAAECqtGXHatd5yzbM273lRiJaTgGt2DV/WTbCzOdTEmZUd4U6jlRnhcHREYoIQUBCCIPTQ12Jxa5idX5Q5QR9G3WXjOJECUKRx7B8ERi2g5TP6G1gei2JEAH5s0aIThKVThh9m03vje0+3talzbc5aDzNFaM6YgKlAaJyBEVVZ1JFIb29bM4ZmyvJJpYVwpkCf/vGZ0KYAQAAAAAAAIAUaJtS2ibm7d4yddd5y45ksa6FX9h5MwXUW1b62lgem0s0+1RRJlv4hvlJmV8v3xxZNltJ0hsoyyqbV1SO0xPQVkxXevr6dH2ciWrjo4QE/X/VrSKKzo+iMEPl5cZ534WvtCWRVkK7SplxfzwcSpjmIYpdhnz8f6X9TW1qa8+or3RUO1ZzV3nsnpHCzK3P7IhYCwAgApTSBgAAAAAAOm395DsrYWbBl3bcLEjU7pgxOWT06ZEuD0sOFTI4VIRhnOyM+zFzypSWE4wLC7pLhqqICpHLjTHeGH41Xv7ZP4tDmSKrMiltVuZW4fFq+5HW1ux4Mabh0R00FdM0Fw0pbVmyPFmcR1SDOGMjynUklDLkXYG//QcQZgBIiAyv3YRGBAAAAAAAIW3tnMmCBTftuJl86hW+4ryI65zRxgvd1aE7ZHTHh809ozhABBmmk8kdUsVFQ5bPk+amIcNnTO/jYBUUtDwvqmPGNzhhwrZQXTI2J5LBgVTRToGyvDgOGr29TG1JyvKrtVct7Whz0OgJlGUemq7Av/t7EGYAAAAAAAAAIG2QM8IhC/51R/rJf6PcMlF5USqcHsV/S/lnVIwGD4slRHV7mLYhdIwE+ocq3yZy0QhLUuFOIv+MUaKZehsoOxnRPuXvNVeNPl1rJ1szlhw0ulOmbB5DW5a2W98uUfnZWtsxqqR3oXS279/93T+AMAMAAAAAAAAADoA444gFX0lRmDGFruihOGryX/UzpAgBVEPnvZpAUxGCo4k0+jaqr2ryX+OORqAmurXmRlGS/54+RnRKUHS6mMQtRfgY102CccFDb7dQoFG3QW8rJRzM3tzagdLbz9aWRvEoqFxsZBsa3pvaktsw6AyCu78DYQYAAAAAAAAAXAFxxgELvpqCMGMSOPT/be6KEP1zZBZdjO4Zy7ylhdpyyuiCTFSOFH3ZUSF2JseOLjKoYTgdAfkn+0Sn+bwuEd2OJueMVQwxbFeUQCMMYU6kCCuCysUgXaAxtSUp4yni/2ptqLdfqR2L2xV0BcHd3/qDtiu5DwAAAAAAAABZAnEmZRbcfM/NFDf5rylhbzjeUD5alo4Wtk48ae/V5ak9e5OII2IINKpYEBBVbLTJ+aFvT9m+G8aZ5rWZaWwhOFxRyD/JJ5o1Vhk2VOaeqUz+W9CcogQv1T1jEsN0gSYYn69CjyprM0WkMbWf/mpaX1R7xW0/JddMwTHzTQgzAAAAAAAAAOAaiDMpsuDr99TnmNHDbaKmWd0ylpwwaugTWcKbvGKCW6NAYwqxUcfrThp1+fqrPs20r1HYQnCIhRAOZ/JPGiM6yy+vylTNgaS3pzAoKmXvtfAmMsyjjlBeCofBGhIWKOM0oUZvuzghTDrGNlTWKUUZr1AuO7j73yDMAAAAAAAAAEAWQJxJiQX/VqcwUwvV3DJ6B94klticHh7rOxxaJIRSUUif3xR6oyb91UOeKKGoYAojIhov8Rxuk3TMzBgjOjtCmNG3nwxtWlqP5pCJ60qxCTSmMZFhTIpoQlq7GkPOqqA6s9T95CEIc/VIYWY9hBkAAAAAAAAAyAqIMymw4JspCzMRbpnI0CYRVOnAG3r0lk5+hYtGD2syuWiEQaghqnT01CoqkCZUqAOx20PmmOnxSZyjCDMmYarifWWIkmpGihRDbO4Zff4wFCq0zYQuGqXdRKBtn9F5pIkq9WAIZwpCGaajEBIW3L0OwgwAAAAAAAAAZAnEmYQs+FaKwozRvWFwmpjcH/r/ZPu/DoHGJGqYtoliiApxXTMmMUcY3hfCcIrCDJ0zVllNqjRvYE+6a3AYlXLPWBPGhOFgEQKNcb9YpNFyClmFGts5UG87hgJUmchVzNNTEGa+BmEGAAAAAAAAALIG4kwCFnzn7mtjJf+N6rubQpXIICaYBAXjqyYmGAWcmAINJwoumkssIo3u9ogKZzL9X62tTOJCyfFRDGvyp/lEs8dKYVnC1uBR228LdQr/MSUAJoNAozuM1GWVrV9x0mjrC7S2Mx2uWtox0I9J+N4bT/5bCGX6yrMgzAAAAAAAAABAA4A4UycLvnv3KiLqi/vpUjiSSWhRieGWKVuWTXxR3Rwmd0iUQKO7YxSRpuDsEAbxJ8rlYdq/auiCgirKCCX571SfaO5YMZRJdx3pzhhTOBYp4Umay6gUjVUtvMkjpQy4YQfV9qw4/qFVJ1x+hFijYmtjW/uGDhlN4GJhhu7+VwgzAAAAAAAAANAoIM7UwYLvF4SZdaku1BiKE+Hu0MWCqvlRxqsyjc+jzKg7PnTBR3kf8IiCQ0UXZKptB1GliGJqC+21sM5QTAiFmSljRHP96FCwCreKKJ83qv0CQ3hT1H6RlofGIHJZ21cV1irC06ooWsY21PLTCG2dniLM3PSsuJIZAAAAAAAAAAAHQJypkQU/TFmYEUrITNQ0oYsGFvcMVXHGeHrYDYsecQQAbTsC1fUhNLGGyLxPVdsj/Ggw/r/q8hBclWnyGNG5WvJfm7hl2f5yQUYTVdR9EIZ/qgo02oL09cYNBSsdyxrQl2dqRxnS1El095cgzAAAAAAAAABAo4E4UwMLNqQozJg64ia3jP4ZXXwgg1CgujBsoUsV4wwuGtM2RwgcJbHGtp4oTEICGUQFWZVpsk90rgxlMq9ACjtC35fSMg35Y8pCjESVJqsi0JQ5kMIwIksYGFle9baoB1P7CRovP95FdPcXIMwAAAAAAAAAQB6AOBOT+Ru3rxIkkgszuqODIv4Xls4/Ke4ZsuSeoToFGtVFY3J72FweJvdOLW1iey0JM5z8NxRmSturuI50cStKTDLti41ArwZuEGh0R4zafqqTpqqDJ2Eb6u2oilJqKNPnz4MwAwAAAAAAAAA5AeJMDOb/3+3xHTOmLq/QOvD6NFsoDpE9TwpZOva6oBNHoClze2giTTW3h03giCMsVGsroWyLDGWaEjpmDOuwtYtNCNPnL223oTQ2h4KVtaJaEtuWR6YijEldiEFUq0fgMol3pXFKnh5+DToDuudGCDMAAAAAAAAAkCcgzlRh/o+3v6XmUKZQDLEJMhTDLRPH6aG6Z2h8nNUVEydGpmy7lLwvJqHG5PaIg80NpAoyNC4olJL/PlPJMUPaZ7S2K4U2Gd1HlrZQw5t0gUbdVaGmgYlo10hhy9Bo+jqrtWvZ7EH5OKG0nyrM3ABhBgAAAAAAAADyBsSZCOb/tAbHTC1UuGUM7pgyAcQQvqNQlmPFhu6IUUNw/n975x9i2XnW8efcmdlNQTSgIv6hzaZ1Z2aT3Z2dapUutClBIyFiIGirtOmCRdKCNIb+UVBpK1hDqdr+UygIjRaKItQItmorZfsrRdTZTUJ2ZlLspFqKRQqJQv9odueVc+455z7neZ/3PefeuTOZH58PHO6955577jnP7P5xP3yf5+2TQsEIE5Hu9XoSISWkvNfeykJKKlRipmplKuLPTzMbp/O9odu+Za8vI2jcNqdC/KHKOdEWCa6BlqtXbql99fDfsCDy3J8iZgAAAAAAAA4jyJkEq/80ZzFTqBWWJJ346P0Rr1GyxhU0Wq7YtiUp/GNsa46b+nCEyh7q0qmHljOjevjva25lVmUyA36nqZ9tJ4oSR/2Cpk3RNHLFSppUTcW4mGnTR2Kut3BqWUqZ0bgl7LmPIGYAAAAAAAAOK8gZh9XPP/MOmcfwX0mkO6ZNfPQlPUJC0OSkTmr4b2qezLykghUK9nGkhv++alfktbWY8b7bJpCMZClXjyqKIv5soWrQHpyqVULQqHpFkqaZRyMqpZSrxcCOM/ez+nUx+buGJnlUtjJ9eBkxAwAAAAAAcIhBzhhW//mZ+S6XbWVCKi1TtIalm4JIzJqJkh7TCBotYrzhv15ixpMqMqWcybXjjKQ7/Pe2XZGfuRVfS66O9v6sVHJlyAAzogWNlVjqNB1JUyREjSeZpsGVW6GtQ3MNzapMzz2OmAEAAAAAADjsIGcUq1+cQsxYOZKTBZLYZz+Xe5QBSY8+QWPFgpU07T71HWKu2z4f8tM/lZYpxB/+e9uuhLO3pLDDf8XM3mnPaVqb1GNVC/2eS8+NFKIG+BZmv/m76fFBnqjx6ubNqnGvw2klK7rf1y6XvRDkuT9GzAAAAAAAABwFkDM1q1efedtMiRmdeHHf7wqDdu6Mm/gwrUvuT+sekeAJGisRxHx3lJIxoibVfjMk/ZFKeuh7VFLh1m23RM6WrUxFfB59vZ7MSiRl2vYme92drzA3p2vWEVJNSqWI62fllxE17a1HUq2nkPrSvfRRoQcoh/GMmT9CzAAAAAAAABwVkDOlmPnyM28SkU/N9aQ5aWOFgn1PEiLEtuJkZ8qMRVAVNkklM7zkR5TwcdIa7Vu5tElCOBT+FhaChNtCLWac4z2RNCR1JE4tU/v1jlRt25oZSePVz0keuVUZqlEK57ERMzKWMuX/6Of+EDEDAAAAAABwlDjxcmb1q09fFCmenNsJPZmQa3ny0jNWvHjCoXwxKvxz6U2naOx3WUHkSQX7XudeQ7w/JZtsO5NMxEIlZk4HCWdvduoWCuV4eusYunNzjIzppGeS0kvSgsamYqykEfPd7t8sUce+Gnr1K+oPNs8X6lamD64gZgAAAAAAAI4YJ1rOrH6tFDNyVURu3/PJPGFg3/damzKzY9x0jZegyWFSNJVDCCbtYU81VCoMqYmY89T3E0ZhImdKMbN8s7tcdlJghYkIGZI60q7Frt4kzvH+jvhaojamoD6WGPw74M/lfl/nuRIyup2pHP77fsQMAAAAAADAUeTEypnVr89BzKSEzJC0jNd6077X016TEjRe+45J0YwPCxNJ47XjpO51FkziIxQTKVOJmaVdCauZVZn65sx4qaOU2PLmz7g1Vamg0FNbK7hEzZCJPjNtEcPku3QNrJwpxcwfIGYAAAAAAACOKidSzqz+y9MXphIzjVjQyYvcLJn2tRnwq37MJ9Mz7fOemEWfoLFiI8TXHPTqQaJm0+wlNWPbiQojGEZWzNwc1yiSV4na9bUOpZ53bsesZuXdg07qFBJfo72u1LWIfj6wkFFaxrYzNTWsh//+PmIGAAAAAADgKHPi5Mzqvz59XkS+NJdWJk0q5SE9P+I9EWKlS8rT2GO1RMhJGpv2aJyMkTUNyYHC+lK8ZZ7FSIVmK2fMLIWxmLHLZZvrDdFy1M2cl6IrLtr77UkdtbetltjWm/1cocRKU19JHCd+XTv7+0iJGV3LUsqMxnNmwkK4Y+CZAQAAAAAA4JByouTMyr9fv1BIMV8xk0p5iJUG9T71uhIEoYh/kEfSZYCg0RJBt/YMSZz0zEUJqZWXUvUQ9Z027VGKmcUg4dzNYasyDZVcnWt32pu80qVanFL3FaQ7BFknjcR8lz1tXwm9y+jUUrWDFeP/uWExXLjx3tVvDbsBAAAAAAAAOKycGDmzsnF9fsN/JdG64ooEZxUhL5mRa88Z1efYdT7nzJSZCIREC1Zv+40h1cKV2lc4z+u0R5uY6dRJXUynhum2sFZa5VJHjXiZRtDounr3F+zftnmdGALch70u/TfU9WvrWEmZ8n/uhRuPrT47xTcBAAAAAADAIeVEyJmV63MUMzbhIVYoJFqKRLo/3uv3qtkzkkjGWNlgl87uu87gyIOcaMlIjM79pT6vX+u0R1G34OhWJi8pk6hjp7Updb0p8SXOsfbW6uWw2zYnfR/6vCmpJjIZAiwZOdOKpsQBObnV1LCUXEty+cajiBkAAAAAAIDjwrGXMyvPTCFmUmKicOSBfq9JUUgRSwLdZiO+RMgOqPVm0Nj9XtojamfaY8ojV5vOo1nquZEKi7vjViZPEqUkTe5R1OwZe33e/JmolnHtooHPqfavWQVXqthJuTXZQj38Vxbl8o33rD6V+gYAAAAAAAA4ehxrObPy7PXpVmUSI1RSKzOlUh72eeq1xD/i3fkz4h2b+fXvSQU3cRL8Uw0Y/Dv5LnVTkaBRs1GaVZnO3YwFUiYtY1ubovRMe5zT3tS8X17DbkLQeEKrXpFr/KdPtKKlWtBmxaudljLFZPivLIbLN37nHGIGAAAAAADgmHFs5czKjWvnZR+G/1bpiuaXtNdSI6kf8UYS2B/4qX0N3kyZ1NLXubRHtu1noGXwkh6ipEIrZsbDf3fvuimFHf4bCaz6wlJ16b125zobQRNUvYKSMl7NpCtpxpeUmRkUCa4B9bPXb+oXRA3/bbZT4b4b70bMAAAAAAAAHEeOpZxZ2SrFjHx57qsy9c6ZUb/UU+mKKMUyeZ6dP+Nils/2rneeaY+MUOg8b4b/1mKmuypT6CZ0UrIjxJ9p0zP2WnR7kyWXOrIpGns9TcBIz+4R6Q4QtnXsq2tCbLVCxgqu8fDfh26869zne84MAAAAAAAAR5RjJ2dWtq/Nf1WmXFtSXztTR8aY1YfEnKsUGrtG0Oj2G5t+ab9TSZpsO5P5Tsm8tjXwXketOKGVCuXw391zk1WZOmIlWUezbLhzD6630u1NHp6gsXUtzHdm5s2E9qbii8ktzR10kXvamao6LlZzZh668ci5zyRPCgAAAAAAAEee45ic2buY8X6U5xIWkkin2OM7Bxq0oGnmnoREisYKGJ3caa9D2Qzva1NtQPZ7cjVqhIyWCgsiuwu7EqrETOHXLZdUsUkcPXtGCqee+m8wQNA0IieoD1qxlrouWyNHaIVgdnqX0ytmmuG/4eEbv30XYgYAAAAAAOCYcxzlzDAxkxIeuR/q9fN27ownX4pEOkYzZK5MnbRIpmjEvLZCowhGKmRacVI18d5r4i9WotSzUXbLVZnubpbLTrQwpZ6nhIi+8KKIOsi6KaSEoHFrpWbR2O9OJY+859PgXXPTwtQd/vvwjXfe9akZvgEAAAAAAACOGMd+Ke0sOSEjTSqkiIVCKi2TS1oU5ryDVmaS7jLbroRJtDyJvc50K86gOkX30G3BKZd6LluZgmplio7VKRi7nHf7vll9KZJf5pYaMaTn2tgltoP5+0YpImeZcV1P9zNDi+fQScqY5FH5P3IhPHzjtxAzAAAAAAAAJ4WTLWdSpFpvUs+tkNHywUtaFDKZP9MnaPTyzvZgTy7tl1RIteCU17cwXpUpRMN/u1IkGuibEC9JwSTdyEwkaPQMmWBPbr432cbkiBpxjk+ljzyiNiYlZEStyFTVUR7ZvIKYAQAAAAAAOEkgZzTeD3FPzDStTTbh0ZE0jnyxM1VSgiaR5AmFkTS5JM1epIInc2xyZTRZ7rlKzGgx48mtaVJHYgYDx5XwBY17qErieC1h2TamRNooJdWiOqpie3Us9HLZZfJIHt58GDEDAAAAAABw0jjecibVrhQdZ9qX7GetXBjSziSJFqJg23BMyibVgmPEUPO80IN/cwkUfb6+mmWet1KmI2Ze9of/NrXVM3i81qaUGLGzYzr3M1DQFDIZAGwlTV/yyF5T+9U9RUyJG5s6GtUXvlAtO/7w5tvvRswAAAAAAACcQOYiZ5Z3Nh4UkbV6awbylqsmXS8ft8+sv3goS+vJBOmRCOr9ah6Ml54R57OaYNtwzGBaex1esqMJdeh0hyhZk7vnobVp0jpaKMgk7REW61WZgvjDf72aFUqkJFNHCbEUCbAeQRP9bR1J0yfZZmlfsq9tWqaQzvDfsBQe2fxNxAwAAAAAAMBJpYiW/h3I8s5GKWEerbcfyXzqJRF5sjzuICTNyva1UP2gLpMpu3UaZrfeSs9Q7quf6/2dY4OY50V3v3qvXe5aHy/O58V8Xh/X2dQvfO84cYSBtz/zZ20ETiicg6zccNtwQqX1du9+Oa6hV7/dbo2KTh0Lpwa6lk59o9oVnf1Fqmbec90i5tUuVcdOOsgrsvcYJiszVUOUReRUeGTzrXd/IvEtAAAAAAAAcAKYSc4s72ys1cLl1VN8rJQ0V7bPrD+5n2WdWc40AqZpN9LHBEfcaEEjjrwRe/xAQSPmeElIhZSosZ+ZBi/5EbXi1GLmvBIzuRo6gqvQEkv/jSSu7WBBI11J0/FOubpFdXRaqWauYehKmtGkjuUAZSmH/74FMQMAAAAAAHDSGU17/7WYuTqlmJE6XfO3yzsbVw5NzYuepEi7Lzj71A9tCbHEiI4L7mfbfaPuj/dKgtjP6GNGZvNEytDNO++C2uqVhGQplEkP2b3wcn8dU8+L2ju19x7iWtg6SYhrMDJ1KbrnKlMpQZ9rNOCxmQHTbBK6r/u25m82qremhov1Vl5T2cZ0qqrjY4gZAAAAAAAAkGnljBIzuTamPj65vLNxz56ueq+4CREjYLznKZkzeHMEzcgREp6k0Z/NSZrcfm9bMEKmsy+Mpcw45VHJmVtazET1CH79Uo/2vYT8igRNToQ1YsRImlA49bW1mqZuI1M3Wzu1LzTbYiu4Htv8tfN/tq//xgEAAAAAAODIMFjOzEnMNDxRz6w5cKI5K32JD53wkLQccNMz7hYmEiOXeLHCICVqvETJtEJBLec8SX2ENu0RiRlvVo1XU5uQUfuS6ZncNlTQWEkz6hE1e9k8uaWFTJWcqQXXkoicDo9tPoSYAQAAAAAAgAmDVmuas5iRuiWqbG/66IH8LZof4t4QV+sZ9LHeo/6METjl/J7CLv+sz9uZLTP9EtrdawjdY6MvS9UiIafcFEr9uBjk1t0vT96zdSx6rlfXTe0PzeUU0r25kLkFb4ltW1ub5mm/d7JKUzD34S7FnSljdFmRIDKtWAuV4PqTzV9FzAAAAAAAAECXXjmzD2Km4dF9kTOFfE+C/KgrZCbHdAVLKwzMstmRWKh3WtmgfsQnBY0rHOqL8CSNd+32e1Pn9YY8e6IhSgc56ZNFkVvN8N+c3LI1tcfa+kbvqZuxIsrSCBortTzJFX2/vvbJF7hzsVP/dtwamjST6ERN2cokf7n5wPn3Ju4IAAAAAAAATjDZtqZ9FDMlr67PP2++nTxfkZEUnqjwHsUIDPs6NSDYS6V0BtmamTLeo7flWpbsUN/cbJrO3JS6DeeUyK2LP4jKFbxatK/zw5PtvhDtV8tNe5/Xg3vtoGD73Ktb596dIb62tctu9v320dS2GQJc1vF0+OvNB86/Yx/+rQMAAAAAAMAxIJmc2Wcx03CHiFzf9zKaFE05d6ZKt3itS+I87widXKRDHZVrcbLXFkyyQ6dLbELFa6+ahqR8Ch15UQ6v3S1bmVIplNR9WNkStYDF6aS4s6mUHcWwVIw+wEseeX/fqPVphjrqz+r71cJt3Mr02c37L7x1D98AAAAAAAAAxxw3OXNAYqZkP5IzT7bPUqsHifOjWtSP6lwyRgYc4yVo7PLP9jOdJEtID/+ddXitTdDo5MhC6KRswpJZLjtKx4jfxqPrE9U189lUgqavxp1kjErSpJJHqdqkUknelkonLUo3SbMkEk6HL27ef+GB/n+yAAAAAAAAcJKJkjMHKGb2Dy9ZkkrGeO+LOYd93p1kO/6xvuskMIpxgmb8tOieOzsbxfuuKQf/dg7Tk28T0kQlZjZ/5Xyx/M2NMLiORaZ+XqKmPWn3+t0EjT7Gfpd3HcFcRC555F+Gjyf5mmu0wmhUCa6vbN134d4BZwYAAAAAAIATTic58wqImRf34ZxXO68SaZmgUzVRMiP3XiJBY2eemERGsKkOL9khzjm8+TDe0te5mSk26WETNYtjKRNOjcVMfR3/EdVRXWNn7oxXn1SypicNk03Q2Dq5y43rx6ASNWEyz2ZPS46bGTU6OVMvOR5OV2LmjQP/vQIAAAAAAMAJp03OvEKJmf2YN/NC+2xIWqZw0jHS/LB3Uhsam6DJHdukaJoFiXIzb7yUh5fuSM2cSSVBrPgY1dKoFgyb95/Xn/ymiLymrYW1MYW482OSs3rcmjirN3nBGT2LxzswmTjy/rZTDOpJpmUc0VSLm7AUvr5170XEDAAAAAAAAAxGJ2eeOGAx89L2mfWrA46biq2zl16QQr7ffsamYLwf2eL82Pb2eZv+Du/zNkUzmiRp2vTOkBkpQ67FO9aZkRIWQruVs1HKzYiZkqciOWFqFqdc7HFDZvPE82eaBE2IEkVNYsXUyd6vrV1fMsZLyiw4x9jHNnkUxsmj0+Ha1r0X3zDvf9MAAAAAAABwvKnkzPLOxhURuXjAd/rkgGNm5WvV57wESaHlQuiKA5lFLiSOTbUqGYlSXkMkaga1NPUsl73QlQmhTHXU22SA7bgNZ/OXIzEjnfawbIJkyuG/th4jc8zI1ichdEYJsZUSVkNal7wlx6Mhyl0pU7aNhbKWp8MzW2++uD7ff8YAAAAAAABwEmiSM4++Avf6gX089+cGp2Xs40zpD3WsTnakZEFCGlSiRsmaZpt2TkolYYoQCxm7lWLmly54YkaqVJNXB02qfrmaevv1LBfnM2GUkDR6/ktCfvX+3XJ/J32+tnaTWT6hWtmqFjNvunjQchMAAAAAAACOCYvLOxt3vAKpmQ9un1l/YcBxsxK3SxX+PJJSYlQrKXnvi6yBXg4AAAlSSURBVJkrM6pXZUrMlGlXEGqO7+wzz1PXJGYsSqjnwgwhlXDRzxsRUs6YudcXM4oviMgvds4Z1a98ambH6LNOM5enveGi+13NYlXqu4uolmZFKzvLZopRM7lUUCuJmjqekme2LiNmAAAAAAAAYHbKn5hrB1y/v9g+s76fqZly7sx1KeR/qhdNG4wVF32pj1SCxpsh46Y0QvczNjljv6uvhWma2Smp9py6DaeaMdMvZiRKIKXqpN/36qf/BkPSLDZFY2vTpGlGai5NVM+elayyq1t10zjV9yyMt8nqTKFMzGwjZgAAAAAAAGCvHLScKcXMlQP6rk9nW2zU/uCJg5ygyQkGLRLaz6h2p9RMmb72mr7NOzZqxamH/755kJiRai6QvX+nniElX6Ia9dQvqocjaZzHpu0pkjVDN/O9ISVkRnUtl2ox84a1len+SQIAAAAAAADEjA6wJgcpZqRefWpCofpaHDkQDQeeRdDkEjUiXVFjJUNKsAyVNnolIZ0AWVADgMsZM/cMFjNSt559IZmKUftaQZOtXY/ESUkubx5NbnbP0K2WL0kZ0yaQ6jou1qtbnQ7f2PoFxAwAAAAAAADMh/Kn54sHUMuDFjNNa9Nm9aIv7SJ7EDRRUiYjXVKiZpRJ1th2JXdlJuc8ekWm8vFUkM03XhwsZhSf7tZigICx79v62CRRn+QqlCRpRI23OlauLWyhr4aOEGqljKpjKWZev3Z2hjoCAAAAAAAAuJQ/Ra/vc2kOXMwoPtxNeCTSM7MKmpEjCHKtOrlUTHNOb4ukhBU7CfGgEzOXZxIzZXrmCSnku52dTnJGbHuTrZ2bBOqpX6KNKRIoRULYeGkcd7+p54KzutW4lWln62cRMwAAAAAAADBf9lvOvJJipkzPTMSCJ1js/tRxKckgSjB4aQ8rGnLJjmk3LWBs8mPUpGbq+ShLcsceS/l4VqqoGmUFjfsZZ/lxT6J4gsat5ywDgJ1lxheU3FoMEk6Fna3Xrd25xzoCAAAAAAAARIy2z6yXbU1/tw+leUXFjOJ9UXoml64oBwSPQrVFaY/kDJgQS4ZkO5MjeqbZbEuOPo8dAHxKJCyFOzZ/7uK39ljDbnrGuxf1erCgsTXsq58nyGwSaUgtbboo1Tq2OJ4zE06H/9y+dAkxAwAAAAAAAPvCqD7pR+d88sMiZpr0zKab/JB8qiNaxUkSgqDzfmbgb6qlacjmiaIFI2T0jJSlSsxc2Hrd2l7FjNQC733RfWaue6oWp877ifpl5diUsstL40QrW43rGE6Fb29fvPTqvdYQAAAAAAAAIEUlZ7bPrF8VkY/NqUqHRswo3t0+3aug6UtxuGma4B87bcrDSoROi07TglNJmXK7vHVp7dl5FbCePfM1V3IlkkGuoLGCJSWr9BwYr16pfUPFTWp1q2ZfKbdOh29vX7j0U/OqIQAAAAAAAIDHSO37gIg8vccqHUYxU6ZnrkohH0vKGG+fJ2j6WpSyKQ9vkG9mpaaOMDBDge0Q4MXJ81LMyCm5b2tt7al9KOXbpJDvt6+soBnp/XXtRlK3iDkyLJVi8USNHdqbElm9cit0N6+WVSvT7n9v34WYAQAAAAAAgP2nCGGygtHyzsbtIlKmaC7O8M2HUsxoVp6/9qwEuVuaW96VcbyjfN3sC84mk/eKUHSPE4mOSe6zz4dSqOMSUik0g20X5b6tu9c+v7dKpVne2bgiQT4Z16zw66ZeF81xXk1s3VKP8yAj1yqRtBRe2l5Zv32/aggAAAAAAACg6ciZhuWdjTJF8/6BlXqpTN1sn1mf99yaubPy/LVy1aJS0PxQVyQ4gkamkDTeo5j9qdd9aJEg6nmhZELRDrB9aOvcpc/sdx2XdzaekCDvmFrQyABJ4z2mjhuKrZ3E6Zx2APRS+L/ts+s/PIcyAQAAAAAAAAzClTMy/gFeioxHReRBEfEGoj5dreIj8kQ9MPZIsPL8tTUReUqCvKqToJGeFI34kkYkI2rs81mxKRnbStSImZX9FzMNyzsbn5Ug9w8WNJKQNJIQNZKop/c6hye11OvOqlxL4Xvbr13/semrAQAAAAAAADA7STmjqdud1ppd9QDhI4sraFIpGklIGklLmEjWOMdkcZIewRusO6rnsSzK5a3lS/sxYyZJ/W/iK22bmCdoZJikERkgajRD6lgk9hWhHlSstmoAcNjavnN9ddZ6AAAAAAAAAMzKIDlzHKkFzVfaFidxBI30S4VkusPZ10qbBKGwHzDP7fDcxbArhdy5tXxpz8tlz0ItaD4uQX7DFzCJJJKtT0rUiJI1mr5/sp26hclp7LyedkCwfGL7zvVH9q1QAAAAAAAAABlOrJyRyQyaz0mQVX/eTEbS5B7t8dNi58x4qxctyLe2li/dMd+KzEY7o8htA8sMUB4yU8apo3VY7aHW49j6iRFcoxBkQd6yfWb9b/apNAAAAAAAAAC9nGg5I2NBc3u1jHiQ91Q7UpJGnOSHTCcVOvtTIRpPKEiTlmnno/ze1tlLH+q/u4NjeWfjHhH5tAT5yWSKRgaKLVur3P5U+5J9HS3NLd+RQu46SvOSAAAAAAAA4Hhy4uVMw8rz1+6pW3RWXcmSmokyRCAMISkUghYL35BCXr919tKhFAp1m1OZonlPctaM9NRwr+mjZOqoreNNGcnbt8+s/9UMZwcAAAAAAACYO8gZw8rz166IyOMS5Ceqd4aImtRxQ4mEQrCtON+VQt65dfbS3+/Tbc+VeqWvD1WzaGSIhNnjAGVJLZethiiP5AdSyMe3z6z/7sFWAwAAAAAAACAPciZBLWkekSA/Xx0xtJ1JEkNsPfTwlDjxcUsK+bfyGrbOXro+7/s7CGpJUyZpfr1aGUumaGMaWkNJ1FHa1Mz3pJDHt8+sf+RwVQcAAAAAAABgDHKmh3po8IMi8i4ROdvbztT3XoM/K+WmFPKsiPx5Ob/lsLYvzcLyzsaDlaQpa2lFjX0+C902pu+KyJNlAmr7zPoLh7QkAAAAAAAAABXImSmohweXs2nKZbgfEJGfliA/Hp0hV9JusuM7IpWM+ZKI/MNRTchMy/LOxlpdx9eLyDkRuThVS1NXbP2vFPJfIvJVEflHEbnKkF8AAAAAAAA4SiBn5kCdrmmWtdbPNVfV8+vHKRUzD+phwmvqVPc4p32h3kpe3D6zfiJkFgAAAAAAABxjROT/AaGvnBGuLJbJAAAAAElFTkSuQmCC)"
-      ],
-      "metadata": {
-        "id": "sh6t_y7KzqBH"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "#  Using SuperGradients (**recipes**)\n",
-        "\n",
-        "This tutorial will explain what **recipes** are, when and how can recipes help you scallable training and reproducing results, and how to use them.\n",
-        "\n"
-      ],
-      "metadata": {
-        "id": "5aISf1B-AGDQ"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "!pip install super_gradients==3.3.1"
-      ],
-      "metadata": {
-        "id": "8uZM-4va5Rpu",
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 1000
-        },
-        "outputId": "a93c1b2d-3b81-4cd7-aeaa-f62f6d6bf81d"
-      },
-      "execution_count": 1,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Collecting super_gradients==3.3.1\n",
-            "  Downloading super_gradients-3.3.1-py3-none-any.whl (6.5 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.5/6.5 MB\u001b[0m \u001b[31m54.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: torch>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (2.1.0+cu118)\n",
-            "Requirement already satisfied: tqdm>=4.57.0 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (4.66.1)\n",
-            "Collecting boto3>=1.17.15 (from super_gradients==3.3.1)\n",
-            "  Downloading boto3-1.28.73-py3-none-any.whl (135 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m135.8/135.8 kB\u001b[0m \u001b[31m16.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: jsonschema>=3.2.0 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (4.19.1)\n",
-            "Collecting Deprecated>=1.2.11 (from super_gradients==3.3.1)\n",
-            "  Downloading Deprecated-1.2.14-py2.py3-none-any.whl (9.6 kB)\n",
-            "Requirement already satisfied: opencv-python>=4.5.1 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (4.8.0.76)\n",
-            "Requirement already satisfied: scipy>=1.6.1 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (1.11.3)\n",
-            "Requirement already satisfied: matplotlib>=3.3.4 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (3.7.1)\n",
-            "Requirement already satisfied: psutil>=5.8.0 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (5.9.5)\n",
-            "Requirement already satisfied: tensorboard>=2.4.1 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (2.14.1)\n",
-            "Requirement already satisfied: setuptools>=21.0.0 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (67.7.2)\n",
-            "Collecting coverage~=5.3.1 (from super_gradients==3.3.1)\n",
-            "  Downloading coverage-5.3.1.tar.gz (684 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m684.5/684.5 kB\u001b[0m \u001b[31m53.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "Requirement already satisfied: torchvision>=0.10.0 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (0.16.0+cu118)\n",
-            "Collecting sphinx~=4.0.2 (from super_gradients==3.3.1)\n",
-            "  Downloading Sphinx-4.0.3-py3-none-any.whl (2.9 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.9/2.9 MB\u001b[0m \u001b[31m114.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting sphinx-rtd-theme (from super_gradients==3.3.1)\n",
-            "  Downloading sphinx_rtd_theme-1.3.0-py2.py3-none-any.whl (2.8 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.8/2.8 MB\u001b[0m \u001b[31m113.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting torchmetrics==0.8 (from super_gradients==3.3.1)\n",
-            "  Downloading torchmetrics-0.8.0-py3-none-any.whl (408 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m408.6/408.6 kB\u001b[0m \u001b[31m46.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting hydra-core>=1.2.0 (from super_gradients==3.3.1)\n",
-            "  Downloading hydra_core-1.3.2-py3-none-any.whl (154 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.5/154.5 kB\u001b[0m \u001b[31m20.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting omegaconf (from super_gradients==3.3.1)\n",
-            "  Downloading omegaconf-2.3.0-py3-none-any.whl (79 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.5/79.5 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting onnxruntime==1.13.1 (from super_gradients==3.3.1)\n",
-            "  Downloading onnxruntime-1.13.1-cp310-cp310-manylinux_2_27_x86_64.whl (4.5 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.5/4.5 MB\u001b[0m \u001b[31m117.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting onnx==1.13.0 (from super_gradients==3.3.1)\n",
-            "  Downloading onnx-1.13.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.5 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.5/13.5 MB\u001b[0m \u001b[31m97.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: pillow!=8.3,>=5.3.0 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (9.4.0)\n",
-            "Requirement already satisfied: pip-tools>=6.12.1 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (6.13.0)\n",
-            "Collecting pyparsing==2.4.5 (from super_gradients==3.3.1)\n",
-            "  Downloading pyparsing-2.4.5-py2.py3-none-any.whl (67 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m68.0/68.0 kB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting einops==0.3.2 (from super_gradients==3.3.1)\n",
-            "  Downloading einops-0.3.2-py3-none-any.whl (25 kB)\n",
-            "Collecting pycocotools==2.0.6 (from super_gradients==3.3.1)\n",
-            "  Downloading pycocotools-2.0.6.tar.gz (24 kB)\n",
-            "  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
-            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
-            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "Requirement already satisfied: protobuf==3.20.3 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (3.20.3)\n",
-            "Collecting treelib==1.6.1 (from super_gradients==3.3.1)\n",
-            "  Downloading treelib-1.6.1.tar.gz (24 kB)\n",
-            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "Collecting termcolor==1.1.0 (from super_gradients==3.3.1)\n",
-            "  Downloading termcolor-1.1.0.tar.gz (3.9 kB)\n",
-            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "Requirement already satisfied: packaging>=20.4 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (23.2)\n",
-            "Requirement already satisfied: wheel>=0.38.0 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (0.41.2)\n",
-            "Requirement already satisfied: pygments>=2.7.4 in /usr/local/lib/python3.10/dist-packages (from super_gradients==3.3.1) (2.16.1)\n",
-            "Collecting stringcase>=1.2.0 (from super_gradients==3.3.1)\n",
-            "  Downloading stringcase-1.2.0.tar.gz (3.0 kB)\n",
-            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "Collecting numpy<=1.23 (from super_gradients==3.3.1)\n",
-            "  Downloading numpy-1.23.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.0 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.0/17.0 MB\u001b[0m \u001b[31m87.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting rapidfuzz (from super_gradients==3.3.1)\n",
-            "  Downloading rapidfuzz-3.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.2 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.2/3.2 MB\u001b[0m \u001b[31m88.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting json-tricks==3.16.1 (from super_gradients==3.3.1)\n",
-            "  Downloading json_tricks-3.16.1-py2.py3-none-any.whl (27 kB)\n",
-            "Collecting onnx-simplifier<1.0,>=0.3.6 (from super_gradients==3.3.1)\n",
-            "  Downloading onnx_simplifier-0.4.35-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.2 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m102.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting data-gradients>=0.2.2 (from super_gradients==3.3.1)\n",
-            "  Downloading data_gradients-0.2.2-py3-none-any.whl (454 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m455.0/455.0 kB\u001b[0m \u001b[31m21.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: typing-extensions>=3.6.2.1 in /usr/local/lib/python3.10/dist-packages (from onnx==1.13.0->super_gradients==3.3.1) (4.5.0)\n",
-            "Collecting coloredlogs (from onnxruntime==1.13.1->super_gradients==3.3.1)\n",
-            "  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: flatbuffers in /usr/local/lib/python3.10/dist-packages (from onnxruntime==1.13.1->super_gradients==3.3.1) (23.5.26)\n",
-            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from onnxruntime==1.13.1->super_gradients==3.3.1) (1.12)\n",
-            "Collecting pyDeprecate==0.3.* (from torchmetrics==0.8->super_gradients==3.3.1)\n",
-            "  Downloading pyDeprecate-0.3.2-py3-none-any.whl (10 kB)\n",
-            "Requirement already satisfied: future in /usr/local/lib/python3.10/dist-packages (from treelib==1.6.1->super_gradients==3.3.1) (0.18.3)\n",
-            "Collecting botocore<1.32.0,>=1.31.73 (from boto3>=1.17.15->super_gradients==3.3.1)\n",
-            "  Downloading botocore-1.31.73-py3-none-any.whl (11.3 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.3/11.3 MB\u001b[0m \u001b[31m114.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting jmespath<2.0.0,>=0.7.1 (from boto3>=1.17.15->super_gradients==3.3.1)\n",
-            "  Downloading jmespath-1.0.1-py3-none-any.whl (20 kB)\n",
-            "Collecting s3transfer<0.8.0,>=0.7.0 (from boto3>=1.17.15->super_gradients==3.3.1)\n",
-            "  Downloading s3transfer-0.7.0-py3-none-any.whl (79 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.8/79.8 kB\u001b[0m \u001b[31m9.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: platformdirs>=2.5.2 in /usr/local/lib/python3.10/dist-packages (from data-gradients>=0.2.2->super_gradients==3.3.1) (3.11.0)\n",
-            "Requirement already satisfied: seaborn in /usr/local/lib/python3.10/dist-packages (from data-gradients>=0.2.2->super_gradients==3.3.1) (0.12.2)\n",
-            "Collecting xhtml2pdf (from data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading xhtml2pdf-0.2.11.tar.gz (108 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m108.3/108.3 kB\u001b[0m \u001b[31m16.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from data-gradients>=0.2.2->super_gradients==3.3.1) (3.1.2)\n",
-            "Collecting imagededup (from data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading imagededup-0.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (176 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m176.0/176.0 kB\u001b[0m \u001b[31m22.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: wrapt<2,>=1.10 in /usr/local/lib/python3.10/dist-packages (from Deprecated>=1.2.11->super_gradients==3.3.1) (1.14.1)\n",
-            "Collecting antlr4-python3-runtime==4.9.* (from hydra-core>=1.2.0->super_gradients==3.3.1)\n",
-            "  Downloading antlr4-python3-runtime-4.9.3.tar.gz (117 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.0/117.0 kB\u001b[0m \u001b[31m16.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.2.0->super_gradients==3.3.1) (23.1.0)\n",
-            "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.2.0->super_gradients==3.3.1) (2023.7.1)\n",
-            "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.2.0->super_gradients==3.3.1) (0.30.2)\n",
-            "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.2.0->super_gradients==3.3.1) (0.10.6)\n",
-            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.4->super_gradients==3.3.1) (1.1.1)\n",
-            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.4->super_gradients==3.3.1) (0.12.1)\n",
-            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.4->super_gradients==3.3.1) (4.43.1)\n",
-            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.4->super_gradients==3.3.1) (1.4.5)\n",
-            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.4->super_gradients==3.3.1) (2.8.2)\n",
-            "Requirement already satisfied: PyYAML>=5.1.0 in /usr/local/lib/python3.10/dist-packages (from omegaconf->super_gradients==3.3.1) (6.0.1)\n",
-            "Requirement already satisfied: rich in /usr/local/lib/python3.10/dist-packages (from onnx-simplifier<1.0,>=0.3.6->super_gradients==3.3.1) (13.6.0)\n",
-            "Requirement already satisfied: build in /usr/local/lib/python3.10/dist-packages (from pip-tools>=6.12.1->super_gradients==3.3.1) (1.0.3)\n",
-            "Requirement already satisfied: click>=8 in /usr/local/lib/python3.10/dist-packages (from pip-tools>=6.12.1->super_gradients==3.3.1) (8.1.7)\n",
-            "Requirement already satisfied: pip>=22.2 in /usr/local/lib/python3.10/dist-packages (from pip-tools>=6.12.1->super_gradients==3.3.1) (23.1.2)\n",
-            "Requirement already satisfied: sphinxcontrib-applehelp in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (1.0.7)\n",
-            "Requirement already satisfied: sphinxcontrib-devhelp in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (1.0.5)\n",
-            "Requirement already satisfied: sphinxcontrib-jsmath in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (1.0.1)\n",
-            "Requirement already satisfied: sphinxcontrib-htmlhelp in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (2.0.4)\n",
-            "Requirement already satisfied: sphinxcontrib-serializinghtml in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (1.1.9)\n",
-            "Requirement already satisfied: sphinxcontrib-qthelp in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (1.0.6)\n",
-            "Collecting docutils<0.18,>=0.14 (from sphinx~=4.0.2->super_gradients==3.3.1)\n",
-            "  Downloading docutils-0.17.1-py2.py3-none-any.whl (575 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m575.5/575.5 kB\u001b[0m \u001b[31m52.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: snowballstemmer>=1.1 in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (2.2.0)\n",
-            "Requirement already satisfied: babel>=1.3 in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (2.13.1)\n",
-            "Requirement already satisfied: alabaster<0.8,>=0.7 in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (0.7.13)\n",
-            "Requirement already satisfied: imagesize in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (1.4.1)\n",
-            "Requirement already satisfied: requests>=2.5.0 in /usr/local/lib/python3.10/dist-packages (from sphinx~=4.0.2->super_gradients==3.3.1) (2.31.0)\n",
-            "Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.4.1->super_gradients==3.3.1) (1.4.0)\n",
-            "Requirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.4.1->super_gradients==3.3.1) (1.59.0)\n",
-            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.4.1->super_gradients==3.3.1) (2.17.3)\n",
-            "Requirement already satisfied: google-auth-oauthlib<1.1,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.4.1->super_gradients==3.3.1) (1.0.0)\n",
-            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.4.1->super_gradients==3.3.1) (3.5)\n",
-            "Requirement already satisfied: six>1.9 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.4.1->super_gradients==3.3.1) (1.16.0)\n",
-            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.4.1->super_gradients==3.3.1) (0.7.2)\n",
-            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.4.1->super_gradients==3.3.1) (3.0.1)\n",
-            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.9.0->super_gradients==3.3.1) (3.12.4)\n",
-            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.9.0->super_gradients==3.3.1) (3.2)\n",
-            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.9.0->super_gradients==3.3.1) (2023.6.0)\n",
-            "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.9.0->super_gradients==3.3.1) (2.1.0)\n",
-            "Collecting sphinxcontrib-jquery<5,>=4 (from sphinx-rtd-theme->super_gradients==3.3.1)\n",
-            "  Downloading sphinxcontrib_jquery-4.1-py2.py3-none-any.whl (121 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.1/121.1 kB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: urllib3<2.1,>=1.25.4 in /usr/local/lib/python3.10/dist-packages (from botocore<1.32.0,>=1.31.73->boto3>=1.17.15->super_gradients==3.3.1) (2.0.7)\n",
-            "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.4.1->super_gradients==3.3.1) (5.3.2)\n",
-            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.4.1->super_gradients==3.3.1) (0.3.0)\n",
-            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.4.1->super_gradients==3.3.1) (4.9)\n",
-            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<1.1,>=0.5->tensorboard>=2.4.1->super_gradients==3.3.1) (1.3.1)\n",
-            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->data-gradients>=0.2.2->super_gradients==3.3.1) (2.1.3)\n",
-            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.5.0->sphinx~=4.0.2->super_gradients==3.3.1) (3.3.1)\n",
-            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.5.0->sphinx~=4.0.2->super_gradients==3.3.1) (3.4)\n",
-            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.5.0->sphinx~=4.0.2->super_gradients==3.3.1) (2023.7.22)\n",
-            "Requirement already satisfied: pyproject_hooks in /usr/local/lib/python3.10/dist-packages (from build->pip-tools>=6.12.1->super_gradients==3.3.1) (1.0.0)\n",
-            "Requirement already satisfied: tomli>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from build->pip-tools>=6.12.1->super_gradients==3.3.1) (2.0.1)\n",
-            "Collecting humanfriendly>=9.1 (from coloredlogs->onnxruntime==1.13.1->super_gradients==3.3.1)\n",
-            "  Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m10.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from imagededup->data-gradients>=0.2.2->super_gradients==3.3.1) (1.2.2)\n",
-            "Requirement already satisfied: PyWavelets in /usr/local/lib/python3.10/dist-packages (from imagededup->data-gradients>=0.2.2->super_gradients==3.3.1) (1.4.1)\n",
-            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich->onnx-simplifier<1.0,>=0.3.6->super_gradients==3.3.1) (3.0.0)\n",
-            "Requirement already satisfied: pandas>=0.25 in /usr/local/lib/python3.10/dist-packages (from seaborn->data-gradients>=0.2.2->super_gradients==3.3.1) (1.5.3)\n",
-            "INFO: pip is looking at multiple versions of sphinxcontrib-applehelp to determine which version is compatible with other requirements. This could take a while.\n",
-            "Collecting sphinxcontrib-applehelp (from sphinx~=4.0.2->super_gradients==3.3.1)\n",
-            "  Downloading sphinxcontrib_applehelp-1.0.6-py3-none-any.whl (120 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m120.0/120.0 kB\u001b[0m \u001b[31m15.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_applehelp-1.0.5-py3-none-any.whl (120 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m120.0/120.0 kB\u001b[0m \u001b[31m15.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_applehelp-1.0.4-py3-none-any.whl (120 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m120.6/120.6 kB\u001b[0m \u001b[31m14.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hINFO: pip is looking at multiple versions of sphinxcontrib-devhelp to determine which version is compatible with other requirements. This could take a while.\n",
-            "Collecting sphinxcontrib-devhelp (from sphinx~=4.0.2->super_gradients==3.3.1)\n",
-            "  Downloading sphinxcontrib_devhelp-1.0.4-py3-none-any.whl (83 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m83.5/83.5 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_devhelp-1.0.3-py3-none-any.whl (83 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m83.5/83.5 kB\u001b[0m \u001b[31m11.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_devhelp-1.0.2-py2.py3-none-any.whl (84 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.7/84.7 kB\u001b[0m \u001b[31m10.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hINFO: pip is looking at multiple versions of sphinxcontrib-htmlhelp to determine which version is compatible with other requirements. This could take a while.\n",
-            "Collecting sphinxcontrib-htmlhelp (from sphinx~=4.0.2->super_gradients==3.3.1)\n",
-            "  Downloading sphinxcontrib_htmlhelp-2.0.3-py3-none-any.whl (99 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.2/99.2 kB\u001b[0m \u001b[31m12.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_htmlhelp-2.0.2-py3-none-any.whl (99 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.2/99.2 kB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_htmlhelp-2.0.1-py3-none-any.whl (99 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.8/99.8 kB\u001b[0m \u001b[31m11.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hINFO: pip is looking at multiple versions of sphinxcontrib-qthelp to determine which version is compatible with other requirements. This could take a while.\n",
-            "Collecting sphinxcontrib-qthelp (from sphinx~=4.0.2->super_gradients==3.3.1)\n",
-            "  Downloading sphinxcontrib_qthelp-1.0.5-py3-none-any.whl (89 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m89.4/89.4 kB\u001b[0m \u001b[31m13.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_qthelp-1.0.4-py3-none-any.whl (89 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m89.4/89.4 kB\u001b[0m \u001b[31m12.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_qthelp-1.0.3-py2.py3-none-any.whl (90 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m90.6/90.6 kB\u001b[0m \u001b[31m11.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hINFO: pip is looking at multiple versions of sphinxcontrib-serializinghtml to determine which version is compatible with other requirements. This could take a while.\n",
-            "Collecting sphinxcontrib-serializinghtml (from sphinx~=4.0.2->super_gradients==3.3.1)\n",
-            "  Downloading sphinxcontrib_serializinghtml-1.1.8-py3-none-any.whl (92 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.6/92.6 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_serializinghtml-1.1.7-py3-none-any.whl (92 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.6/92.6 kB\u001b[0m \u001b[31m10.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_serializinghtml-1.1.6-py3-none-any.whl (92 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.6/92.6 kB\u001b[0m \u001b[31m11.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Downloading sphinxcontrib_serializinghtml-1.1.5-py2.py3-none-any.whl (94 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m94.0/94.0 kB\u001b[0m \u001b[31m13.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->onnxruntime==1.13.1->super_gradients==3.3.1) (1.3.0)\n",
-            "Collecting arabic-reshaper>=3.0.0 (from xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading arabic_reshaper-3.0.0-py3-none-any.whl (20 kB)\n",
-            "Requirement already satisfied: html5lib>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1) (1.1)\n",
-            "Collecting pyHanko>=0.12.1 (from xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading pyHanko-0.20.1-py3-none-any.whl (407 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m407.7/407.7 kB\u001b[0m \u001b[31m36.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting pyhanko-certvalidator>=0.19.5 (from xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading pyhanko_certvalidator-0.25.0-py3-none-any.whl (107 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m107.7/107.7 kB\u001b[0m \u001b[31m13.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting pypdf>=3.1.0 (from xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading pypdf-3.17.0-py3-none-any.whl (277 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m277.4/277.4 kB\u001b[0m \u001b[31m33.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting python-bidi>=0.4.2 (from xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading python_bidi-0.4.2-py2.py3-none-any.whl (30 kB)\n",
-            "Collecting reportlab<4,>=3.5.53 (from xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading reportlab-3.6.13-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.8 MB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.8/2.8 MB\u001b[0m \u001b[31m111.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting svglib>=1.2.1 (from xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading svglib-1.5.1.tar.gz (913 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m913.9/913.9 kB\u001b[0m \u001b[31m70.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "Requirement already satisfied: webencodings in /usr/local/lib/python3.10/dist-packages (from html5lib>=1.0.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1) (0.5.1)\n",
-            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich->onnx-simplifier<1.0,>=0.3.6->super_gradients==3.3.1) (0.1.2)\n",
-            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.25->seaborn->data-gradients>=0.2.2->super_gradients==3.3.1) (2023.3.post1)\n",
-            "Requirement already satisfied: pyasn1<0.6.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard>=2.4.1->super_gradients==3.3.1) (0.5.0)\n",
-            "Collecting asn1crypto>=1.5.1 (from pyHanko>=0.12.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading asn1crypto-1.5.1-py2.py3-none-any.whl (105 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.0/105.0 kB\u001b[0m \u001b[31m15.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting qrcode>=6.1 (from pyHanko>=0.12.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading qrcode-7.4.2-py3-none-any.whl (46 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.2/46.2 kB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: tzlocal>=4.3 in /usr/local/lib/python3.10/dist-packages (from pyHanko>=0.12.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1) (5.2)\n",
-            "Collecting pyhanko-certvalidator>=0.19.5 (from xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading pyhanko_certvalidator-0.24.1-py3-none-any.whl (106 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m106.8/106.8 kB\u001b[0m \u001b[31m13.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: cryptography>=3.3.1 in /usr/local/lib/python3.10/dist-packages (from pyHanko>=0.12.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1) (41.0.5)\n",
-            "Collecting oscrypto>=1.1.0 (from pyhanko-certvalidator>=0.19.5->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading oscrypto-1.3.0-py2.py3-none-any.whl (194 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.6/194.6 kB\u001b[0m \u001b[31m24.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hCollecting uritools>=3.0.1 (from pyhanko-certvalidator>=0.19.5->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading uritools-4.0.2-py3-none-any.whl (10 kB)\n",
-            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<1.1,>=0.5->tensorboard>=2.4.1->super_gradients==3.3.1) (3.2.2)\n",
-            "Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from svglib>=1.2.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1) (4.9.3)\n",
-            "Requirement already satisfied: tinycss2>=0.6.0 in /usr/local/lib/python3.10/dist-packages (from svglib>=1.2.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1) (1.2.1)\n",
-            "Collecting cssselect2>=0.2.0 (from svglib>=1.2.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading cssselect2-0.7.0-py3-none-any.whl (15 kB)\n",
-            "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->imagededup->data-gradients>=0.2.2->super_gradients==3.3.1) (1.3.2)\n",
-            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->imagededup->data-gradients>=0.2.2->super_gradients==3.3.1) (3.2.0)\n",
-            "Requirement already satisfied: cffi>=1.12 in /usr/local/lib/python3.10/dist-packages (from cryptography>=3.3.1->pyHanko>=0.12.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1) (1.16.0)\n",
-            "Collecting pypng (from qrcode>=6.1->pyHanko>=0.12.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1)\n",
-            "  Downloading pypng-0.20220715.0-py3-none-any.whl (58 kB)\n",
-            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.1/58.1 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-            "\u001b[?25hRequirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi>=1.12->cryptography>=3.3.1->pyHanko>=0.12.1->xhtml2pdf->data-gradients>=0.2.2->super_gradients==3.3.1) (2.21)\n",
-            "Building wheels for collected packages: pycocotools, termcolor, treelib, coverage, antlr4-python3-runtime, stringcase, xhtml2pdf, svglib\n",
-            "  Building wheel for pycocotools (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for pycocotools: filename=pycocotools-2.0.6-cp310-cp310-linux_x86_64.whl size=376863 sha256=4349254bdff5da28473c91787b8bcf44cc54ea44a8f360f9e74f9bb29830f38b\n",
-            "  Stored in directory: /root/.cache/pip/wheels/58/e6/f9/f87c8f8be098b51b616871315318329cae12cdb618f4caac93\n",
-            "  Building wheel for termcolor (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for termcolor: filename=termcolor-1.1.0-py3-none-any.whl size=4832 sha256=7d44d084a2787f2eec4d826b9f778a94ef3fe703e57e652f6fcec2cfbad82fc3\n",
-            "  Stored in directory: /root/.cache/pip/wheels/a1/49/46/1b13a65d8da11238af9616b00fdde6d45b0f95d9291bac8452\n",
-            "  Building wheel for treelib (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for treelib: filename=treelib-1.6.1-py3-none-any.whl size=18368 sha256=4f994b13ad6a3b6bdec5d8abca07d384f706bf26db91f17924a7f63dd65a15af\n",
-            "  Stored in directory: /root/.cache/pip/wheels/63/72/8b/76569b82bf280a03c4e294c3b29ee2398217186369c427ed4b\n",
-            "  Building wheel for coverage (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for coverage: filename=coverage-5.3.1-cp310-cp310-linux_x86_64.whl size=235255 sha256=3cb1ed541c5a741a7a0edcd0f0f207c55fb630995c8804985368bb081a0e3892\n",
-            "  Stored in directory: /root/.cache/pip/wheels/e2/70/10/313be697f460d6024cfa94b7f0e22ffc1c53aab718fb4f42af\n",
-            "  Building wheel for antlr4-python3-runtime (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for antlr4-python3-runtime: filename=antlr4_python3_runtime-4.9.3-py3-none-any.whl size=144554 sha256=ae52ba8dbfae62e4a4e657ed9608bf55fcd1c8e636af750a36174fd5623a1c69\n",
-            "  Stored in directory: /root/.cache/pip/wheels/12/93/dd/1f6a127edc45659556564c5730f6d4e300888f4bca2d4c5a88\n",
-            "  Building wheel for stringcase (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for stringcase: filename=stringcase-1.2.0-py3-none-any.whl size=3568 sha256=2d06bc6a96d5f33f7692b91055650a8b975b0edc1c4a222189835442e40e3e2b\n",
-            "  Stored in directory: /root/.cache/pip/wheels/31/ba/22/1a2d952a9ce8aa86e42fda41e2c87fdaf20e238c88bf8df013\n",
-            "  Building wheel for xhtml2pdf (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for xhtml2pdf: filename=xhtml2pdf-0.2.11-py3-none-any.whl size=262644 sha256=e21a23f15a968448177403ee0c1195902c64416578ed3647567c53758149ff5b\n",
-            "  Stored in directory: /root/.cache/pip/wheels/72/77/fb/e473c11c4e30a7680bf5b1b7f1d07ef04932184a2f39118e8d\n",
-            "  Building wheel for svglib (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
-            "  Created wheel for svglib: filename=svglib-1.5.1-py3-none-any.whl size=30904 sha256=a2726cfa21df8737571dd27b061e57db47f4dec40beeadb216c301e055a6e958\n",
-            "  Stored in directory: /root/.cache/pip/wheels/56/9f/90/f37f4b9dbf82987a24ae14f15586e96715cb669a4710b3b85d\n",
-            "Successfully built pycocotools termcolor treelib coverage antlr4-python3-runtime stringcase xhtml2pdf svglib\n",
-            "Installing collected packages: termcolor, stringcase, pypng, json-tricks, einops, asn1crypto, arabic-reshaper, antlr4-python3-runtime, uritools, treelib, sphinxcontrib-serializinghtml, sphinxcontrib-qthelp, sphinxcontrib-htmlhelp, sphinxcontrib-devhelp, sphinxcontrib-applehelp, reportlab, rapidfuzz, qrcode, python-bidi, pypdf, pyparsing, pyDeprecate, oscrypto, omegaconf, numpy, jmespath, humanfriendly, docutils, Deprecated, coverage, sphinx, onnx, hydra-core, cssselect2, coloredlogs, botocore, torchmetrics, svglib, sphinxcontrib-jquery, s3transfer, pyhanko-certvalidator, onnxruntime, onnx-simplifier, sphinx-rtd-theme, pyHanko, pycocotools, imagededup, boto3, xhtml2pdf, data-gradients, super_gradients\n",
-            "  Attempting uninstall: termcolor\n",
-            "    Found existing installation: termcolor 2.3.0\n",
-            "    Uninstalling termcolor-2.3.0:\n",
-            "      Successfully uninstalled termcolor-2.3.0\n",
-            "  Attempting uninstall: sphinxcontrib-serializinghtml\n",
-            "    Found existing installation: sphinxcontrib-serializinghtml 1.1.9\n",
-            "    Uninstalling sphinxcontrib-serializinghtml-1.1.9:\n",
-            "      Successfully uninstalled sphinxcontrib-serializinghtml-1.1.9\n",
-            "  Attempting uninstall: sphinxcontrib-qthelp\n",
-            "    Found existing installation: sphinxcontrib-qthelp 1.0.6\n",
-            "    Uninstalling sphinxcontrib-qthelp-1.0.6:\n",
-            "      Successfully uninstalled sphinxcontrib-qthelp-1.0.6\n",
-            "  Attempting uninstall: sphinxcontrib-htmlhelp\n",
-            "    Found existing installation: sphinxcontrib-htmlhelp 2.0.4\n",
-            "    Uninstalling sphinxcontrib-htmlhelp-2.0.4:\n",
-            "      Successfully uninstalled sphinxcontrib-htmlhelp-2.0.4\n",
-            "  Attempting uninstall: sphinxcontrib-devhelp\n",
-            "    Found existing installation: sphinxcontrib-devhelp 1.0.5\n",
-            "    Uninstalling sphinxcontrib-devhelp-1.0.5:\n",
-            "      Successfully uninstalled sphinxcontrib-devhelp-1.0.5\n",
-            "  Attempting uninstall: sphinxcontrib-applehelp\n",
-            "    Found existing installation: sphinxcontrib-applehelp 1.0.7\n",
-            "    Uninstalling sphinxcontrib-applehelp-1.0.7:\n",
-            "      Successfully uninstalled sphinxcontrib-applehelp-1.0.7\n",
-            "  Attempting uninstall: pyparsing\n",
-            "    Found existing installation: pyparsing 3.1.1\n",
-            "    Uninstalling pyparsing-3.1.1:\n",
-            "      Successfully uninstalled pyparsing-3.1.1\n",
-            "  Attempting uninstall: numpy\n",
-            "    Found existing installation: numpy 1.23.5\n",
-            "    Uninstalling numpy-1.23.5:\n",
-            "      Successfully uninstalled numpy-1.23.5\n",
-            "  Attempting uninstall: docutils\n",
-            "    Found existing installation: docutils 0.18.1\n",
-            "    Uninstalling docutils-0.18.1:\n",
-            "      Successfully uninstalled docutils-0.18.1\n",
-            "  Attempting uninstall: sphinx\n",
-            "    Found existing installation: Sphinx 5.0.2\n",
-            "    Uninstalling Sphinx-5.0.2:\n",
-            "      Successfully uninstalled Sphinx-5.0.2\n",
-            "  Attempting uninstall: pycocotools\n",
-            "    Found existing installation: pycocotools 2.0.7\n",
-            "    Uninstalling pycocotools-2.0.7:\n",
-            "      Successfully uninstalled pycocotools-2.0.7\n",
-            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
-            "lida 0.0.10 requires fastapi, which is not installed.\n",
-            "lida 0.0.10 requires kaleido, which is not installed.\n",
-            "lida 0.0.10 requires python-multipart, which is not installed.\n",
-            "lida 0.0.10 requires uvicorn, which is not installed.\n",
-            "tensorflow 2.14.0 requires numpy>=1.23.5, but you have numpy 1.23.0 which is incompatible.\u001b[0m\u001b[31m\n",
-            "\u001b[0mSuccessfully installed Deprecated-1.2.14 antlr4-python3-runtime-4.9.3 arabic-reshaper-3.0.0 asn1crypto-1.5.1 boto3-1.28.73 botocore-1.31.73 coloredlogs-15.0.1 coverage-5.3.1 cssselect2-0.7.0 data-gradients-0.2.2 docutils-0.17.1 einops-0.3.2 humanfriendly-10.0 hydra-core-1.3.2 imagededup-0.3.2 jmespath-1.0.1 json-tricks-3.16.1 numpy-1.23.0 omegaconf-2.3.0 onnx-1.13.0 onnx-simplifier-0.4.35 onnxruntime-1.13.1 oscrypto-1.3.0 pyDeprecate-0.3.2 pyHanko-0.20.1 pycocotools-2.0.6 pyhanko-certvalidator-0.24.1 pyparsing-2.4.5 pypdf-3.17.0 pypng-0.20220715.0 python-bidi-0.4.2 qrcode-7.4.2 rapidfuzz-3.4.0 reportlab-3.6.13 s3transfer-0.7.0 sphinx-4.0.3 sphinx-rtd-theme-1.3.0 sphinxcontrib-applehelp-1.0.4 sphinxcontrib-devhelp-1.0.2 sphinxcontrib-htmlhelp-2.0.1 sphinxcontrib-jquery-4.1 sphinxcontrib-qthelp-1.0.3 sphinxcontrib-serializinghtml-1.1.5 stringcase-1.2.0 super_gradients-3.3.1 svglib-1.5.1 termcolor-1.1.0 torchmetrics-0.8.0 treelib-1.6.1 uritools-4.0.2 xhtml2pdf-0.2.11\n"
-          ]
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "application/vnd.colab-display-data+json": {
-              "pip_warning": {
-                "packages": [
-                  "numpy",
-                  "pydevd_plugins",
-                  "pyparsing",
-                  "sphinxcontrib"
-                ]
-              }
-            }
-          },
-          "metadata": {}
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "# What is a **recipe**"
-      ],
-      "metadata": {
-        "id": "-1nPOPmc1lGp"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "To train a model, it is necessary to configure **4** main components:\n",
-        "1. **dataset**: what dataset to use, input size, augmentations, etc.\n",
-        "\n",
-        "  ImageNet of size 224x224 with color jitter is one option. CIFAR10 is another. We possibly have our custom dataset and augmentations as-well...\n",
-        "\n",
-        "2. **architecture**: what model to train, how many blocks, dropout rate, etc.\n",
-        "\n",
-        "  Is it ResNet18? ResNet50? Maybe it's YOLO? or our SuperCustomModel with RepVGG backbone, a dropout probability of 0.2 and bottleneck ratio of 0.5?\n",
-        "\n",
-        "3. **training hyperparameters**: number of epochs, initial learning rate, learning rate scheduler, loss function, optimizer, etc.\n",
-        "\n",
-        "  Train for 300 epochs using SGD with a learning rate of 0.01, or maybe 400 epochs with Cosine scheduler and ADAM? Should we use EMA or not? What about weight decay? We can plug our custom loss function, metrics, optimizers and others as-well!\n",
-        "\n",
-        "4. **checkpoints**: location of pretrained weights, location of current training's checkpoints and artifacts, etc."
-      ],
-      "metadata": {
-        "id": "IvWzUj7Q_KeW"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "All recipes can be found [here](https://github.com/Deci-AI/super-gradients/blob/master/docs/assets/SG_img/Training_Recipes.md)"
-      ],
-      "metadata": {
-        "id": "k5aBkCQXbNiW"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "Recipes support out of the box every model, metric or loss that is implemented in SuperGradients, but you can easily extend this to any custom object that you need by \"registering it\". Check out [this tutorial](https://github.com/Deci-AI/super-gradients/tree/master/src/super_gradients/common/registry) for more information."
-      ],
-      "metadata": {
-        "id": "vroKwZSl3zSR"
-      }
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "To standardize these components, SG uses the following hierarchy-based format:\n",
-        "\n",
-        "```\n",
-        ".\n",
-        "├── src/super_gradients/recipes/\n",
-        "│   ├── arch_params/\n",
-        "│   │   ├── default_arch_params.yaml\n",
-        "│   │   ├── resnet50_arch_params.yaml\n",
-        "│   │   ├── yolo_arch_params.yaml\n",
-        "│   │   └── ...         \n",
-        "│   ├── dataset_params/\n",
-        "│   │   ├── imagenet_dataset_params.yaml\n",
-        "│   │   ├── coco_detection_dataset_params.yaml\n",
-        "│   │   └── ...   \n",
-        "│   ├── training_hyperparams/\n",
-        "│   │   ├── imagenet_resnet50_train_params.yaml\n",
-        "│   │   ├── coco2017_yolox_train_params.yaml\n",
-        "│   │   └── ...  \n",
-        "└── └── checkpoint_params/    \n",
-        "        ├── default_checkpoint_params.yaml\n",
-        "        └── ...\n",
-        "```"
-      ],
-      "metadata": {
-        "id": "dooBqeANyLtn"
-      }
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# What is a **recipe**"
+   ],
+   "metadata": {
+    "id": "-1nPOPmc1lGp"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "To train a model, it is necessary to configure **4** main components:\n",
+    "1. **dataset**: what dataset to use, input size, augmentations, etc.\n",
+    "\n",
+    "  ImageNet of size 224x224 with color jitter is one option. CIFAR10 is another. We possibly have our custom dataset and augmentations as-well...\n",
+    "\n",
+    "2. **architecture**: what model to train, how many blocks, dropout rate, etc.\n",
+    "\n",
+    "  Is it ResNet18? ResNet50? Maybe it's YOLO? or our SuperCustomModel with RepVGG backbone, a dropout probability of 0.2 and bottleneck ratio of 0.5?\n",
+    "\n",
+    "3. **training hyperparameters**: number of epochs, initial learning rate, learning rate scheduler, loss function, optimizer, etc.\n",
+    "\n",
+    "  Train for 300 epochs using SGD with a learning rate of 0.01, or maybe 400 epochs with Cosine scheduler and ADAM? Should we use EMA or not? What about weight decay? We can plug our custom loss function, metrics, optimizers and others as-well!\n",
+    "\n",
+    "4. **checkpoints**: location of pretrained weights, location of current training's checkpoints and artifacts, etc."
+   ],
+   "metadata": {
+    "id": "IvWzUj7Q_KeW"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "All recipes can be found [here](https://github.com/Deci-AI/super-gradients/blob/master/docs/assets/SG_img/Training_Recipes.md)"
+   ],
+   "metadata": {
+    "id": "k5aBkCQXbNiW"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "Recipes support out of the box every model, metric or loss that is implemented in SuperGradients, but you can easily extend this to any custom object that you need by \"registering it\". Check out [this tutorial](https://github.com/Deci-AI/super-gradients/tree/master/src/super_gradients/common/registry) for more information."
+   ],
+   "metadata": {
+    "id": "vroKwZSl3zSR"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "To standardize these components, SG uses the following hierarchy-based format:\n",
+    "\n",
+    "```\n",
+    ".\n",
+    "├── src/super_gradients/recipes/\n",
+    "│   ├── arch_params/\n",
+    "│   │   ├── default_arch_params.yaml\n",
+    "│   │   ├── resnet50_arch_params.yaml\n",
+    "│   │   ├── yolo_arch_params.yaml\n",
+    "│   │   └── ...         \n",
+    "│   ├── dataset_params/\n",
+    "│   │   ├── imagenet_dataset_params.yaml\n",
+    "│   │   ├── coco_detection_dataset_params.yaml\n",
+    "│   │   └── ...   \n",
+    "│   ├── training_hyperparams/\n",
+    "│   │   ├── imagenet_resnet50_train_params.yaml\n",
+    "│   │   ├── coco2017_yolox_train_params.yaml\n",
+    "│   │   └── ...  \n",
+    "└── └── checkpoint_params/    \n",
+    "        ├── default_checkpoint_params.yaml\n",
+    "        └── ...\n",
+    "```"
+   ],
+   "metadata": {
+    "id": "dooBqeANyLtn"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "These components are aggregated into a single \"main\" recipe `.yaml` file that inherits the aforementioned dataset, architecture, training and checkpoint params. It is also possible (and recomended for flexibility) to override default settings with custom ones.\n",
+    "\n",
+    "Examples of \"main\" recipes are found at `src/super_gradients/recipes/`. We'll have a glance on `coco2017_yolox.yaml`:\n",
+    "\n",
+    "```\n",
+    "defaults:\n",
+    "  - training_hyperparams: coco2017_yolox_train_params\n",
+    "  - dataset_params: coco_detection_dataset_params\n",
+    "  - arch_params: yolox_s_arch_params\n",
+    "  - checkpoint_params: default_checkpoint_params\n",
+    "\n",
+    "train_dataloader: coco2017_train\n",
+    "val_dataloader: coco2017_val\n",
+    "\n",
+    "model_checkpoints_location: local\n",
+    "\n",
+    "load_checkpoint: False\n",
+    "training_hyperparams:\n",
+    "  initial_lr: 0.001\n",
+    "\n",
+    "architecture: yolox_s\n",
+    "\n",
+    "multi_gpu: DDP\n",
+    "num_gpus: 8\n",
+    "\n",
+    "experiment_suffix: res${dataset_params.train_dataset_params.input_dim}\n",
+    "experiment_name: ${architecture}_coco2017_${experiment_suffix}\n",
+    "```\n",
+    "\n",
+    "We can understand that this recipe consists of `coco_detection_dataset_params` for dataset, `yolox_s_arch_params` for architecture, `coco2017_yolox_train_params` for training, and `default_checkpoint_params` for checkpoints.\n",
+    "\n",
+    "We have overridden the default value of `training_hyperparams.initial_lr` with a value of `0.001`, and we also plan to launch the training using 8 GPUs on DDP mode.\n",
+    "\n",
+    "\n"
+   ],
+   "metadata": {
+    "id": "5mNpNi-q0aJw"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# How to use recipes in SuperGradients"
+   ],
+   "metadata": {
+    "id": "njthhNJR1pJm"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Getting training hyperparameters based on recipe\n",
+    "\n",
+    "Load training hyperparams for ResNet <> ImageNet"
+   ],
+   "metadata": {
+    "id": "DxcgHs9bG-ya"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "from super_gradients.training import training_hyperparams"
+   ],
+   "metadata": {
+    "id": "DFbJpOmo8Lri",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
+    "outputId": "3277b6a0-92f7-43a4-8e69-de4e3153b321"
+   },
+   "execution_count": 2,
+   "outputs": [
     {
-      "cell_type": "markdown",
-      "source": [
-        "These components are aggregated into a single \"main\" recipe `.yaml` file that inherits the aforementioned dataset, architecture, training and checkpoint params. It is also possible (and recomended for flexibility) to override default settings with custom ones.\n",
-        "\n",
-        "Examples of \"main\" recipes are found at `src/super_gradients/recipes/`. We'll have a glance on `coco2017_yolox.yaml`:\n",
-        "\n",
-        "```\n",
-        "defaults:\n",
-        "  - training_hyperparams: coco2017_yolox_train_params\n",
-        "  - dataset_params: coco_detection_dataset_params\n",
-        "  - arch_params: yolox_s_arch_params\n",
-        "  - checkpoint_params: default_checkpoint_params\n",
-        "\n",
-        "train_dataloader: coco2017_train\n",
-        "val_dataloader: coco2017_val\n",
-        "\n",
-        "model_checkpoints_location: local\n",
-        "\n",
-        "load_checkpoint: False\n",
-        "training_hyperparams:\n",
-        "  initial_lr: 0.001\n",
-        "\n",
-        "architecture: yolox_s\n",
-        "\n",
-        "multi_gpu: DDP\n",
-        "num_gpus: 8\n",
-        "\n",
-        "experiment_suffix: res${dataset_params.train_dataset_params.input_dim}\n",
-        "experiment_name: ${architecture}_coco2017_${experiment_suffix}\n",
-        "```\n",
-        "\n",
-        "We can understand that this recipe consists of `coco_detection_dataset_params` for dataset, `yolox_s_arch_params` for architecture, `coco2017_yolox_train_params` for training, and `default_checkpoint_params` for checkpoints.\n",
-        "\n",
-        "We have overridden the default value of `training_hyperparams.initial_lr` with a value of `0.001`, and we also plan to launch the training using 8 GPUs on DDP mode.\n",
-        "\n",
-        "\n"
-      ],
-      "metadata": {
-        "id": "5mNpNi-q0aJw"
-      }
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "The console stream is logged into /root/sg_logs/console.log\n"
+     ]
     },
     {
-      "cell_type": "markdown",
-      "source": [
-        "# How to use recipes in SuperGradients"
-      ],
-      "metadata": {
-        "id": "njthhNJR1pJm"
-      }
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "[2023-10-30 09:36:13] INFO - crash_tips_setup.py - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it\n",
+      "[2023-10-30 09:36:13] WARNING - __init__.py - Failed to import pytorch_quantization\n",
+      "[2023-10-30 09:36:21] INFO - utils.py - NumExpr defaulting to 2 threads.\n",
+      "[2023-10-30 09:36:25] WARNING - calibrator.py - Failed to import pytorch_quantization\n",
+      "[2023-10-30 09:36:25] WARNING - export.py - Failed to import pytorch_quantization\n",
+      "[2023-10-30 09:36:25] WARNING - selective_quantization_utils.py - Failed to import pytorch_quantization\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: boto3 required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: deprecated required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: coverage required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: sphinx-rtd-theme required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: torchmetrics required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: hydra-core required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: omegaconf required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: onnxruntime required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: onnx required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: einops required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: treelib required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: stringcase required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: rapidfuzz required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: json-tricks required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: onnx-simplifier required but not found\u001B[0m\n",
+      "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001B[31mFailed to verify installed packages: data-gradients required but not found\u001B[0m\n"
+     ]
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "# Two options to load same training hyperparameters\n",
+    "training_params_from_yaml_file = training_hyperparams.get('cifar10_resnet')\n",
+    "training_params_predefined = training_hyperparams.cifar10_resnet_train_params()\n",
+    "\n",
+    "# We don't assert values' equality because some are numpy arrays, etc\n",
+    "assert set(training_params_predefined.keys()) == set(training_params_from_yaml_file.keys())\n",
+    "\n",
+    "print(\"TRAINING HYPERPARAMS:\")\n",
+    "for k, v in training_params_predefined.items():\n",
+    "    print(f\"{k}: {v}\")"
+   ],
+   "metadata": {
+    "id": "CIpnwngoJ15h"
+   },
+   "execution_count": 3,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "There are multiple settings in the training hyperparams. All are accessible and modifiable in a key-value way, for example:"
+   ],
+   "metadata": {
+    "id": "OIV_f74ML8sd"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "training_params_predefined['initial_lr'] = 0.05\n",
+    "print(training_params_predefined['initial_lr'])"
+   ],
+   "metadata": {
+    "id": "PjpuYXYtL8aK"
+   },
+   "execution_count": 4,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "You can also overwrite with custom on-the-fly:"
+   ],
+   "metadata": {
+    "id": "QQKb1sFnsgOP"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "training_params_custom = training_hyperparams.cifar10_resnet_train_params(overriding_params={'initial_lr': 0.05})\n",
+    "training_params_custom['initial_lr']"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
+    "id": "t8H6RTDfta1M",
+    "outputId": "66a9836d-f789-4d95-bb1b-40d7a2384224"
+   },
+   "execution_count": 5,
+   "outputs": [
     {
-      "cell_type": "markdown",
-      "source": [
-        "# Getting training hyperparameters based on recipe\n",
-        "\n",
-        "Load training hyperparams for ResNet <> ImageNet"
-      ],
-      "metadata": {
-        "id": "DxcgHs9bG-ya"
-      }
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "TRAINING HYPERPARAMS:\n",
+      "resume: False\n",
+      "run_id: None\n",
+      "resume_path: None\n",
+      "resume_from_remote_sg_logger: False\n",
+      "ckpt_name: ckpt_latest.pth\n",
+      "lr_mode: StepLRScheduler\n",
+      "lr_schedule_function: None\n",
+      "lr_warmup_epochs: 0\n",
+      "lr_warmup_steps: 0\n",
+      "lr_cooldown_epochs: 0\n",
+      "warmup_initial_lr: None\n",
+      "step_lr_update_freq: None\n",
+      "cosine_final_lr_ratio: 0.01\n",
+      "warmup_mode: LinearEpochLRWarmup\n",
+      "lr_updates: [100 150 200]\n",
+      "pre_prediction_callback: None\n",
+      "optimizer: SGD\n",
+      "optimizer_params: {'weight_decay': 0.0001, 'momentum': 0.9}\n",
+      "load_opt_params: True\n",
+      "zero_weight_decay_on_bias_and_bn: False\n",
+      "loss: LabelSmoothingCrossEntropyLoss\n",
+      "criterion_params: {}\n",
+      "ema: False\n",
+      "ema_params: {'decay': 0.9999, 'decay_type': 'exp', 'beta': 15}\n",
+      "train_metrics_list: ['Accuracy', 'Top5']\n",
+      "valid_metrics_list: ['Accuracy', 'Top5']\n",
+      "metric_to_watch: Accuracy\n",
+      "greater_metric_to_watch_is_better: True\n",
+      "launch_tensorboard: False\n",
+      "tensorboard_port: None\n",
+      "tb_files_user_prompt: False\n",
+      "save_tensorboard_to_s3: False\n",
+      "precise_bn: False\n",
+      "precise_bn_batch_size: None\n",
+      "sync_bn: False\n",
+      "silent_mode: False\n",
+      "mixed_precision: False\n",
+      "save_ckpt_epoch_list: []\n",
+      "average_best_models: True\n",
+      "dataset_statistics: False\n",
+      "batch_accumulate: 1\n",
+      "run_validation_freq: 1\n",
+      "run_test_freq: 1\n",
+      "save_model: True\n",
+      "seed: 42\n",
+      "phase_callbacks: []\n",
+      "log_installed_packages: True\n",
+      "clip_grad_norm: None\n",
+      "ckpt_best_name: ckpt_best.pth\n",
+      "max_train_batches: None\n",
+      "max_valid_batches: None\n",
+      "sg_logger: base_sg_logger\n",
+      "sg_logger_params: {'tb_files_user_prompt': False, 'launch_tensorboard': False, 'tensorboard_port': None, 'save_checkpoints_remote': False, 'save_tensorboard_remote': False, 'save_logs_remote': False, 'monitor_system': True}\n",
+      "torch_compile: False\n",
+      "torch_compile_loss: False\n",
+      "torch_compile_options: {'mode': 'reduce-overhead', 'fullgraph': False, 'dynamic': False, 'backend': 'inductor', 'options': None, 'disable': False}\n",
+      "_convert_: all\n",
+      "max_epochs: 250\n",
+      "lr_decay_factor: 0.1\n",
+      "initial_lr: 0.1\n",
+      "0.05\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "from super_gradients.training import training_hyperparams"
-      ],
-      "metadata": {
-        "id": "DFbJpOmo8Lri",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "3277b6a0-92f7-43a4-8e69-de4e3153b321"
-      },
-      "execution_count": 2,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "The console stream is logged into /root/sg_logs/console.log\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "[2023-10-30 09:36:13] INFO - crash_tips_setup.py - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it\n",
-            "[2023-10-30 09:36:13] WARNING - __init__.py - Failed to import pytorch_quantization\n",
-            "[2023-10-30 09:36:21] INFO - utils.py - NumExpr defaulting to 2 threads.\n",
-            "[2023-10-30 09:36:25] WARNING - calibrator.py - Failed to import pytorch_quantization\n",
-            "[2023-10-30 09:36:25] WARNING - export.py - Failed to import pytorch_quantization\n",
-            "[2023-10-30 09:36:25] WARNING - selective_quantization_utils.py - Failed to import pytorch_quantization\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: boto3 required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: deprecated required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: coverage required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: sphinx-rtd-theme required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: torchmetrics required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: hydra-core required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: omegaconf required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: onnxruntime required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: onnx required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: einops required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: treelib required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: stringcase required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: rapidfuzz required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: json-tricks required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: onnx-simplifier required but not found\u001b[0m\n",
-            "[2023-10-30 09:36:25] WARNING - env_sanity_check.py - \u001b[31mFailed to verify installed packages: data-gradients required but not found\u001b[0m\n"
-          ]
-        }
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "0.05"
       ]
+     },
+     "metadata": {},
+     "execution_count": 5
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Getting a `DataLoader` based on a recipe"
+   ],
+   "metadata": {
+    "id": "jaJWfyqH4fSU"
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "Now we'll get a dataloader object from a recipe.\n",
+    "\n"
+   ],
+   "metadata": {
+    "id": "d5CviqXB4lee"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "from super_gradients.training.datasets.classification_datasets.cifar import Cifar10\n",
+    "from super_gradients.training import dataloaders"
+   ],
+   "metadata": {
+    "id": "isMXe8S5WTCq"
+   },
+   "execution_count": 6,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "# Load a predefined dataset\n",
+    "train_dataloader = dataloaders.cifar10_train()\n",
+    "\n",
+    "# OR use your yaml file. Can also override specific params, such as batch_size\n",
+    "train_dataloader = dataloaders.get_data_loader(\n",
+    "        config_name='cifar10_dataset_params',\n",
+    "        dataset_cls=Cifar10,\n",
+    "        train=True,\n",
+    "        dataloader_params={'batch_size': 42}\n",
+    ")\n",
+    "\n",
+    "print(\"batch size:\", train_dataloader.batch_size)\n",
+    "\n",
+    "val_dataloader = dataloaders.cifar10_val()"
+   ],
+   "metadata": {
+    "id": "av42ahGM4hau",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
+    "outputId": "4e153886-827f-4dbd-b5f0-c58cb8095d88"
+   },
+   "execution_count": 7,
+   "outputs": [
     {
-      "cell_type": "code",
-      "source": [
-        "# Two options to load same training hyperparameters\n",
-        "training_params_from_yaml_file = training_hyperparams.get('cifar10_resnet')\n",
-        "training_params_predefined = training_hyperparams.cifar10_resnet_train_params()\n",
-        "\n",
-        "# We don't assert values' equality because some are numpy arrays, etc\n",
-        "assert set(training_params_predefined.keys()) == set(training_params_from_yaml_file.keys())\n",
-        "\n",
-        "print(\"TRAINING HYPERPARAMS:\")\n",
-        "for k, v in training_params_predefined.items():\n",
-        "    print(f\"{k}: {v}\")"
-      ],
-      "metadata": {
-        "id": "CIpnwngoJ15h"
-      },
-      "execution_count": 3,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "There are multiple settings in the training hyperparams. All are accessible and modifiable in a key-value way, for example:"
-      ],
-      "metadata": {
-        "id": "OIV_f74ML8sd"
-      }
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar10/cifar-10-python.tar.gz\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "training_params_predefined['initial_lr'] = 0.05\n",
-        "print(training_params_predefined['initial_lr'])"
-      ],
-      "metadata": {
-        "id": "PjpuYXYtL8aK"
-      },
-      "execution_count": 4,
-      "outputs": []
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "100%|██████████| 170498071/170498071 [00:02<00:00, 82172492.33it/s]\n"
+     ]
     },
     {
-      "cell_type": "markdown",
-      "source": [
-        "You can also overwrite with custom on-the-fly:"
-      ],
-      "metadata": {
-        "id": "QQKb1sFnsgOP"
-      }
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Extracting ./data/cifar10/cifar-10-python.tar.gz to ./data/cifar10\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "training_params_custom = training_hyperparams.cifar10_resnet_train_params(overriding_params={'initial_lr': 0.05})\n",
-        "training_params_custom['initial_lr']"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "t8H6RTDfta1M",
-        "outputId": "66a9836d-f789-4d95-bb1b-40d7a2384224"
-      },
-      "execution_count": 5,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "TRAINING HYPERPARAMS:\n",
-            "resume: False\n",
-            "run_id: None\n",
-            "resume_path: None\n",
-            "resume_from_remote_sg_logger: False\n",
-            "ckpt_name: ckpt_latest.pth\n",
-            "lr_mode: StepLRScheduler\n",
-            "lr_schedule_function: None\n",
-            "lr_warmup_epochs: 0\n",
-            "lr_warmup_steps: 0\n",
-            "lr_cooldown_epochs: 0\n",
-            "warmup_initial_lr: None\n",
-            "step_lr_update_freq: None\n",
-            "cosine_final_lr_ratio: 0.01\n",
-            "warmup_mode: LinearEpochLRWarmup\n",
-            "lr_updates: [100 150 200]\n",
-            "pre_prediction_callback: None\n",
-            "optimizer: SGD\n",
-            "optimizer_params: {'weight_decay': 0.0001, 'momentum': 0.9}\n",
-            "load_opt_params: True\n",
-            "zero_weight_decay_on_bias_and_bn: False\n",
-            "loss: LabelSmoothingCrossEntropyLoss\n",
-            "criterion_params: {}\n",
-            "ema: False\n",
-            "ema_params: {'decay': 0.9999, 'decay_type': 'exp', 'beta': 15}\n",
-            "train_metrics_list: ['Accuracy', 'Top5']\n",
-            "valid_metrics_list: ['Accuracy', 'Top5']\n",
-            "metric_to_watch: Accuracy\n",
-            "greater_metric_to_watch_is_better: True\n",
-            "launch_tensorboard: False\n",
-            "tensorboard_port: None\n",
-            "tb_files_user_prompt: False\n",
-            "save_tensorboard_to_s3: False\n",
-            "precise_bn: False\n",
-            "precise_bn_batch_size: None\n",
-            "sync_bn: False\n",
-            "silent_mode: False\n",
-            "mixed_precision: False\n",
-            "save_ckpt_epoch_list: []\n",
-            "average_best_models: True\n",
-            "dataset_statistics: False\n",
-            "batch_accumulate: 1\n",
-            "run_validation_freq: 1\n",
-            "run_test_freq: 1\n",
-            "save_model: True\n",
-            "seed: 42\n",
-            "phase_callbacks: []\n",
-            "log_installed_packages: True\n",
-            "clip_grad_norm: None\n",
-            "ckpt_best_name: ckpt_best.pth\n",
-            "max_train_batches: None\n",
-            "max_valid_batches: None\n",
-            "sg_logger: base_sg_logger\n",
-            "sg_logger_params: {'tb_files_user_prompt': False, 'launch_tensorboard': False, 'tensorboard_port': None, 'save_checkpoints_remote': False, 'save_tensorboard_remote': False, 'save_logs_remote': False, 'monitor_system': True}\n",
-            "torch_compile: False\n",
-            "torch_compile_loss: False\n",
-            "torch_compile_options: {'mode': 'reduce-overhead', 'fullgraph': False, 'dynamic': False, 'backend': 'inductor', 'options': None, 'disable': False}\n",
-            "_convert_: all\n",
-            "max_epochs: 250\n",
-            "lr_decay_factor: 0.1\n",
-            "initial_lr: 0.1\n",
-            "0.05\n"
-          ]
-        },
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "0.05"
-            ]
-          },
-          "metadata": {},
-          "execution_count": 5
-        }
-      ]
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:557: UserWarning: This DataLoader will create 8 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
+      "  warnings.warn(_create_warning_msg(\n"
+     ]
     },
     {
-      "cell_type": "markdown",
-      "source": [
-        "# Getting a `DataLoader` based on a recipe"
-      ],
-      "metadata": {
-        "id": "jaJWfyqH4fSU"
-      }
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Files already downloaded and verified\n",
+      "batch size: 42\n",
+      "Files already downloaded and verified\n"
+     ]
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Getting a model"
+   ],
+   "metadata": {
+    "id": "7NwNPzpu4hgs"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "from super_gradients.training import models"
+   ],
+   "metadata": {
+    "id": "Dwe9iez7ffw2"
+   },
+   "execution_count": 8,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "model = models.get('resnet18', num_classes=10)"
+   ],
+   "metadata": {
+    "id": "Feho5xg-YhlU"
+   },
+   "execution_count": 9,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Launch a training, based on model, dataset, training hyperparameters"
+   ],
+   "metadata": {
+    "id": "YU68Mj6p4vN5"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "from super_gradients.training import Trainer"
+   ],
+   "metadata": {
+    "id": "jkjs7eLzgZmr"
+   },
+   "execution_count": 10,
+   "outputs": []
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "trainer = Trainer(\"recipe_example\", ckpt_root_dir=\"experiments\")\n",
+    "\n",
+    "# For the sake of this demonstration we will change the max epochs to 3\n",
+    "training_params_from_yaml_file['max_epochs'] = 3\n",
+    "\n",
+    "trainer.train(\n",
+    "    model=model,\n",
+    "    training_params=training_params_from_yaml_file,\n",
+    "    train_loader=train_dataloader,\n",
+    "    valid_loader=val_dataloader\n",
+    ")"
+   ],
+   "metadata": {
+    "id": "XUQrw1k74kDE",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
+    "outputId": "3100a0a8-c9bb-4f02-a725-23ecf06b1acb"
+   },
+   "execution_count": 11,
+   "outputs": [
     {
-      "cell_type": "markdown",
-      "source": [
-        "Now we'll get a dataloader object from a recipe.\n",
-        "\n"
-      ],
-      "metadata": {
-        "id": "d5CviqXB4lee"
-      }
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "[2023-10-30 09:36:36] WARNING - sg_trainer.py - Train dataset size % batch_size != 0 and drop_last=False, this might result in smaller last batch.\n",
+      "[2023-10-30 09:36:45] INFO - sg_trainer.py - Starting a new run with `run_id=RUN_20231030_093645_854856`\n",
+      "[2023-10-30 09:36:45] INFO - sg_trainer.py - Checkpoints directory: experiments/recipe_example/RUN_20231030_093645_854856\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "from super_gradients.training.datasets.classification_datasets.cifar import Cifar10\n",
-        "from super_gradients.training import dataloaders"
-      ],
-      "metadata": {
-        "id": "isMXe8S5WTCq"
-      },
-      "execution_count": 6,
-      "outputs": []
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "The console stream is now moved to experiments/recipe_example/RUN_20231030_093645_854856/console_Oct30_09_36_45.txt\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "# Load a predefined dataset\n",
-        "train_dataloader = dataloaders.cifar10_train()\n",
-        "\n",
-        "# OR use your yaml file. Can also override specific params, such as batch_size\n",
-        "train_dataloader = dataloaders.get_data_loader(\n",
-        "        config_name='cifar10_dataset_params',\n",
-        "        dataset_cls=Cifar10,\n",
-        "        train=True,\n",
-        "        dataloader_params={'batch_size': 42}\n",
-        ")\n",
-        "\n",
-        "print(\"batch size:\", train_dataloader.batch_size)\n",
-        "\n",
-        "val_dataloader = dataloaders.cifar10_val()"
-      ],
-      "metadata": {
-        "id": "av42ahGM4hau",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "4e153886-827f-4dbd-b5f0-c58cb8095d88"
-      },
-      "execution_count": 7,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar10/cifar-10-python.tar.gz\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "100%|██████████| 170498071/170498071 [00:02<00:00, 82172492.33it/s]\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Extracting ./data/cifar10/cifar-10-python.tar.gz to ./data/cifar10\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:557: UserWarning: This DataLoader will create 8 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
-            "  warnings.warn(_create_warning_msg(\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Files already downloaded and verified\n",
-            "batch size: 42\n",
-            "Files already downloaded and verified\n"
-          ]
-        }
-      ]
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "[2023-10-30 09:36:47] INFO - sg_trainer_utils.py - TRAINING PARAMETERS:\n",
+      "    - Mode:                         Single GPU\n",
+      "    - Number of GPUs:               1          (1 available on the machine)\n",
+      "    - Full dataset size:            50000      (len(train_set))\n",
+      "    - Batch size per GPU:           42         (batch_size)\n",
+      "    - Batch Accumulate:             1          (batch_accumulate)\n",
+      "    - Total batch size:             42         (num_gpus * batch_size)\n",
+      "    - Effective Batch size:         42         (num_gpus * batch_size * batch_accumulate)\n",
+      "    - Iterations per epoch:         1191       (len(train_loader))\n",
+      "    - Gradient updates per epoch:   1191       (len(train_loader) / batch_accumulate)\n",
+      "\n",
+      "[2023-10-30 09:36:47] INFO - sg_trainer.py - Started training for 3 epochs (0/2)\n",
+      "\n",
+      "Train epoch 0: 100%|██████████| 1191/1191 [01:11<00:00, 16.67it/s, Accuracy=0.301, LabelSmoothingCrossEntropyLoss=1.98, Top5=0.842, gpu_mem=0.26]\n",
+      "Validating: 100%|██████████| 20/20 [00:07<00:00,  2.84it/s]\n",
+      "[2023-10-30 09:38:06] INFO - base_sg_logger.py - Checkpoint saved in experiments/recipe_example/RUN_20231030_093645_854856/ckpt_best.pth\n",
+      "[2023-10-30 09:38:06] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.4129999876022339\n"
+     ]
     },
     {
-      "cell_type": "markdown",
-      "source": [
-        "# Getting a model"
-      ],
-      "metadata": {
-        "id": "7NwNPzpu4hgs"
-      }
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "===========================================================\n",
+      "SUMMARY OF EPOCH 0\n",
+      "├── Train\n",
+      "│   ├── Labelsmoothingcrossentropyloss = 1.9838\n",
+      "│   ├── Accuracy = 0.3006\n",
+      "│   └── Top5 = 0.8419\n",
+      "└── Validation\n",
+      "    ├── Labelsmoothingcrossentropyloss = 1.5593\n",
+      "    ├── Accuracy = 0.413\n",
+      "    └── Top5 = 0.9116\n",
+      "\n",
+      "===========================================================\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "from super_gradients.training import models"
-      ],
-      "metadata": {
-        "id": "Dwe9iez7ffw2"
-      },
-      "execution_count": 8,
-      "outputs": []
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "Train epoch 1: 100%|██████████| 1191/1191 [01:01<00:00, 19.37it/s, Accuracy=0.415, LabelSmoothingCrossEntropyLoss=1.58, Top5=0.905, gpu_mem=0.308]\n",
+      "Validating epoch 1: 100%|██████████| 20/20 [00:08<00:00,  2.24it/s]\n",
+      "[2023-10-30 09:39:17] INFO - base_sg_logger.py - Checkpoint saved in experiments/recipe_example/RUN_20231030_093645_854856/ckpt_best.pth\n",
+      "[2023-10-30 09:39:17] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.47769999504089355\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "model = models.get('resnet18', num_classes=10)"
-      ],
-      "metadata": {
-        "id": "Feho5xg-YhlU"
-      },
-      "execution_count": 9,
-      "outputs": []
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "===========================================================\n",
+      "SUMMARY OF EPOCH 1\n",
+      "├── Train\n",
+      "│   ├── Labelsmoothingcrossentropyloss = 1.5782\n",
+      "│   │   ├── Epoch N-1      = 1.9838 (\u001B[32m↘ -0.4057\u001B[0m)\n",
+      "│   │   └── Best until now = 1.9838 (\u001B[32m↘ -0.4057\u001B[0m)\n",
+      "│   ├── Accuracy = 0.4151\n",
+      "│   │   ├── Epoch N-1      = 0.3006 (\u001B[32m↗ 0.1146\u001B[0m)\n",
+      "│   │   └── Best until now = 0.3006 (\u001B[32m↗ 0.1146\u001B[0m)\n",
+      "│   └── Top5 = 0.9055\n",
+      "│       ├── Epoch N-1      = 0.8419 (\u001B[32m↗ 0.0636\u001B[0m)\n",
+      "│       └── Best until now = 0.8419 (\u001B[32m↗ 0.0636\u001B[0m)\n",
+      "└── Validation\n",
+      "    ├── Labelsmoothingcrossentropyloss = 1.4904\n",
+      "    │   ├── Epoch N-1      = 1.5593 (\u001B[32m↘ -0.0689\u001B[0m)\n",
+      "    │   └── Best until now = 1.5593 (\u001B[32m↘ -0.0689\u001B[0m)\n",
+      "    ├── Accuracy = 0.4777\n",
+      "    │   ├── Epoch N-1      = 0.413  (\u001B[32m↗ 0.0647\u001B[0m)\n",
+      "    │   └── Best until now = 0.413  (\u001B[32m↗ 0.0647\u001B[0m)\n",
+      "    └── Top5 = 0.932\n",
+      "        ├── Epoch N-1      = 0.9116 (\u001B[32m↗ 0.0204\u001B[0m)\n",
+      "        └── Best until now = 0.9116 (\u001B[32m↗ 0.0204\u001B[0m)\n",
+      "\n",
+      "===========================================================\n"
+     ]
     },
     {
-      "cell_type": "markdown",
-      "source": [
-        "# Launch a training, based on model, dataset, training hyperparameters"
-      ],
-      "metadata": {
-        "id": "YU68Mj6p4vN5"
-      }
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "Train epoch 2: 100%|██████████| 1191/1191 [00:59<00:00, 19.89it/s, Accuracy=0.489, LabelSmoothingCrossEntropyLoss=1.41, Top5=0.928, gpu_mem=0.308]\n",
+      "Validating epoch 2: 100%|██████████| 20/20 [00:09<00:00,  2.11it/s]\n",
+      "[2023-10-30 09:40:27] INFO - base_sg_logger.py - Checkpoint saved in experiments/recipe_example/RUN_20231030_093645_854856/ckpt_best.pth\n",
+      "[2023-10-30 09:40:27] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.5166000127792358\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "from super_gradients.training import Trainer"
-      ],
-      "metadata": {
-        "id": "jkjs7eLzgZmr"
-      },
-      "execution_count": 10,
-      "outputs": []
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "===========================================================\n",
+      "SUMMARY OF EPOCH 2\n",
+      "├── Train\n",
+      "│   ├── Labelsmoothingcrossentropyloss = 1.4117\n",
+      "│   │   ├── Epoch N-1      = 1.5782 (\u001B[32m↘ -0.1664\u001B[0m)\n",
+      "│   │   └── Best until now = 1.5782 (\u001B[32m↘ -0.1664\u001B[0m)\n",
+      "│   ├── Accuracy = 0.4885\n",
+      "│   │   ├── Epoch N-1      = 0.4151 (\u001B[32m↗ 0.0734\u001B[0m)\n",
+      "│   │   └── Best until now = 0.4151 (\u001B[32m↗ 0.0734\u001B[0m)\n",
+      "│   └── Top5 = 0.9283\n",
+      "│       ├── Epoch N-1      = 0.9055 (\u001B[32m↗ 0.0228\u001B[0m)\n",
+      "│       └── Best until now = 0.9055 (\u001B[32m↗ 0.0228\u001B[0m)\n",
+      "└── Validation\n",
+      "    ├── Labelsmoothingcrossentropyloss = 1.5115\n",
+      "    │   ├── Epoch N-1      = 1.4904 (\u001B[31m↗ 0.021\u001B[0m)\n",
+      "    │   └── Best until now = 1.4904 (\u001B[31m↗ 0.021\u001B[0m)\n",
+      "    ├── Accuracy = 0.5166\n",
+      "    │   ├── Epoch N-1      = 0.4777 (\u001B[32m↗ 0.0389\u001B[0m)\n",
+      "    │   └── Best until now = 0.4777 (\u001B[32m↗ 0.0389\u001B[0m)\n",
+      "    └── Top5 = 0.9226\n",
+      "        ├── Epoch N-1      = 0.932  (\u001B[31m↘ -0.0094\u001B[0m)\n",
+      "        └── Best until now = 0.932  (\u001B[31m↘ -0.0094\u001B[0m)\n",
+      "\n",
+      "===========================================================\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "trainer = Trainer(\"recipe_example\", ckpt_root_dir=\"experiments\")\n",
-        "\n",
-        "# For the sake of this demonstration we will change the max epochs to 3\n",
-        "training_params_from_yaml_file['max_epochs'] = 3\n",
-        "\n",
-        "trainer.train(\n",
-        "    model=model,\n",
-        "    training_params=training_params_from_yaml_file,\n",
-        "    train_loader=train_dataloader,\n",
-        "    valid_loader=val_dataloader\n",
-        ")"
-      ],
-      "metadata": {
-        "id": "XUQrw1k74kDE",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "3100a0a8-c9bb-4f02-a725-23ecf06b1acb"
-      },
-      "execution_count": 11,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "[2023-10-30 09:36:36] WARNING - sg_trainer.py - Train dataset size % batch_size != 0 and drop_last=False, this might result in smaller last batch.\n",
-            "[2023-10-30 09:36:45] INFO - sg_trainer.py - Starting a new run with `run_id=RUN_20231030_093645_854856`\n",
-            "[2023-10-30 09:36:45] INFO - sg_trainer.py - Checkpoints directory: experiments/recipe_example/RUN_20231030_093645_854856\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "The console stream is now moved to experiments/recipe_example/RUN_20231030_093645_854856/console_Oct30_09_36_45.txt\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "[2023-10-30 09:36:47] INFO - sg_trainer_utils.py - TRAINING PARAMETERS:\n",
-            "    - Mode:                         Single GPU\n",
-            "    - Number of GPUs:               1          (1 available on the machine)\n",
-            "    - Full dataset size:            50000      (len(train_set))\n",
-            "    - Batch size per GPU:           42         (batch_size)\n",
-            "    - Batch Accumulate:             1          (batch_accumulate)\n",
-            "    - Total batch size:             42         (num_gpus * batch_size)\n",
-            "    - Effective Batch size:         42         (num_gpus * batch_size * batch_accumulate)\n",
-            "    - Iterations per epoch:         1191       (len(train_loader))\n",
-            "    - Gradient updates per epoch:   1191       (len(train_loader) / batch_accumulate)\n",
-            "\n",
-            "[2023-10-30 09:36:47] INFO - sg_trainer.py - Started training for 3 epochs (0/2)\n",
-            "\n",
-            "Train epoch 0: 100%|██████████| 1191/1191 [01:11<00:00, 16.67it/s, Accuracy=0.301, LabelSmoothingCrossEntropyLoss=1.98, Top5=0.842, gpu_mem=0.26]\n",
-            "Validating: 100%|██████████| 20/20 [00:07<00:00,  2.84it/s]\n",
-            "[2023-10-30 09:38:06] INFO - base_sg_logger.py - Checkpoint saved in experiments/recipe_example/RUN_20231030_093645_854856/ckpt_best.pth\n",
-            "[2023-10-30 09:38:06] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.4129999876022339\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "===========================================================\n",
-            "SUMMARY OF EPOCH 0\n",
-            "├── Train\n",
-            "│   ├── Labelsmoothingcrossentropyloss = 1.9838\n",
-            "│   ├── Accuracy = 0.3006\n",
-            "│   └── Top5 = 0.8419\n",
-            "└── Validation\n",
-            "    ├── Labelsmoothingcrossentropyloss = 1.5593\n",
-            "    ├── Accuracy = 0.413\n",
-            "    └── Top5 = 0.9116\n",
-            "\n",
-            "===========================================================\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "Train epoch 1: 100%|██████████| 1191/1191 [01:01<00:00, 19.37it/s, Accuracy=0.415, LabelSmoothingCrossEntropyLoss=1.58, Top5=0.905, gpu_mem=0.308]\n",
-            "Validating epoch 1: 100%|██████████| 20/20 [00:08<00:00,  2.24it/s]\n",
-            "[2023-10-30 09:39:17] INFO - base_sg_logger.py - Checkpoint saved in experiments/recipe_example/RUN_20231030_093645_854856/ckpt_best.pth\n",
-            "[2023-10-30 09:39:17] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.47769999504089355\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "===========================================================\n",
-            "SUMMARY OF EPOCH 1\n",
-            "├── Train\n",
-            "│   ├── Labelsmoothingcrossentropyloss = 1.5782\n",
-            "│   │   ├── Epoch N-1      = 1.9838 (\u001b[32m↘ -0.4057\u001b[0m)\n",
-            "│   │   └── Best until now = 1.9838 (\u001b[32m↘ -0.4057\u001b[0m)\n",
-            "│   ├── Accuracy = 0.4151\n",
-            "│   │   ├── Epoch N-1      = 0.3006 (\u001b[32m↗ 0.1146\u001b[0m)\n",
-            "│   │   └── Best until now = 0.3006 (\u001b[32m↗ 0.1146\u001b[0m)\n",
-            "│   └── Top5 = 0.9055\n",
-            "│       ├── Epoch N-1      = 0.8419 (\u001b[32m↗ 0.0636\u001b[0m)\n",
-            "│       └── Best until now = 0.8419 (\u001b[32m↗ 0.0636\u001b[0m)\n",
-            "└── Validation\n",
-            "    ├── Labelsmoothingcrossentropyloss = 1.4904\n",
-            "    │   ├── Epoch N-1      = 1.5593 (\u001b[32m↘ -0.0689\u001b[0m)\n",
-            "    │   └── Best until now = 1.5593 (\u001b[32m↘ -0.0689\u001b[0m)\n",
-            "    ├── Accuracy = 0.4777\n",
-            "    │   ├── Epoch N-1      = 0.413  (\u001b[32m↗ 0.0647\u001b[0m)\n",
-            "    │   └── Best until now = 0.413  (\u001b[32m↗ 0.0647\u001b[0m)\n",
-            "    └── Top5 = 0.932\n",
-            "        ├── Epoch N-1      = 0.9116 (\u001b[32m↗ 0.0204\u001b[0m)\n",
-            "        └── Best until now = 0.9116 (\u001b[32m↗ 0.0204\u001b[0m)\n",
-            "\n",
-            "===========================================================\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "Train epoch 2: 100%|██████████| 1191/1191 [00:59<00:00, 19.89it/s, Accuracy=0.489, LabelSmoothingCrossEntropyLoss=1.41, Top5=0.928, gpu_mem=0.308]\n",
-            "Validating epoch 2: 100%|██████████| 20/20 [00:09<00:00,  2.11it/s]\n",
-            "[2023-10-30 09:40:27] INFO - base_sg_logger.py - Checkpoint saved in experiments/recipe_example/RUN_20231030_093645_854856/ckpt_best.pth\n",
-            "[2023-10-30 09:40:27] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.5166000127792358\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "===========================================================\n",
-            "SUMMARY OF EPOCH 2\n",
-            "├── Train\n",
-            "│   ├── Labelsmoothingcrossentropyloss = 1.4117\n",
-            "│   │   ├── Epoch N-1      = 1.5782 (\u001b[32m↘ -0.1664\u001b[0m)\n",
-            "│   │   └── Best until now = 1.5782 (\u001b[32m↘ -0.1664\u001b[0m)\n",
-            "│   ├── Accuracy = 0.4885\n",
-            "│   │   ├── Epoch N-1      = 0.4151 (\u001b[32m↗ 0.0734\u001b[0m)\n",
-            "│   │   └── Best until now = 0.4151 (\u001b[32m↗ 0.0734\u001b[0m)\n",
-            "│   └── Top5 = 0.9283\n",
-            "│       ├── Epoch N-1      = 0.9055 (\u001b[32m↗ 0.0228\u001b[0m)\n",
-            "│       └── Best until now = 0.9055 (\u001b[32m↗ 0.0228\u001b[0m)\n",
-            "└── Validation\n",
-            "    ├── Labelsmoothingcrossentropyloss = 1.5115\n",
-            "    │   ├── Epoch N-1      = 1.4904 (\u001b[31m↗ 0.021\u001b[0m)\n",
-            "    │   └── Best until now = 1.4904 (\u001b[31m↗ 0.021\u001b[0m)\n",
-            "    ├── Accuracy = 0.5166\n",
-            "    │   ├── Epoch N-1      = 0.4777 (\u001b[32m↗ 0.0389\u001b[0m)\n",
-            "    │   └── Best until now = 0.4777 (\u001b[32m↗ 0.0389\u001b[0m)\n",
-            "    └── Top5 = 0.9226\n",
-            "        ├── Epoch N-1      = 0.932  (\u001b[31m↘ -0.0094\u001b[0m)\n",
-            "        └── Best until now = 0.932  (\u001b[31m↘ -0.0094\u001b[0m)\n",
-            "\n",
-            "===========================================================\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "[2023-10-30 09:40:28] INFO - sg_trainer.py - RUNNING ADDITIONAL TEST ON THE AVERAGED MODEL...\n",
-            "Validating epoch 3:  90%|█████████ | 18/20 [00:06<00:00,  4.26it/s]"
-          ]
-        }
-      ]
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "[2023-10-30 09:40:28] INFO - sg_trainer.py - RUNNING ADDITIONAL TEST ON THE AVERAGED MODEL...\n",
+      "Validating epoch 3:  90%|█████████ | 18/20 [00:06<00:00,  4.26it/s]"
+     ]
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Launch a training based on a **recipe** in a single line!\n",
+    "\n",
+    "To load a recipe, you should pass the following CLI argument: `--config-name=my_recipe`, and you also can override settings using `nested.key=value` syntax.\n",
+    "\n",
+    "For this example we will set the number of workers for train & validation data loaders to two.\n",
+    "\n",
+    "The full override command would look like `dataset_params.train_dataloader_params.num_workers=2 dataset_params.val_dataloader_params.num_workers=2`. To save the time SuperGradients offers a list of shortcut settings to achieve the same result: `num_workers=2`.\n",
+    "\n",
+    "You can read more about shortcuts [here](https://docs.deci.ai/super-gradients/latest/documentation/source/Recipes_Training.html#command-line-override-shortcuts):"
+   ],
+   "metadata": {
+    "id": "OnNaB_1Pwpq-"
+   }
+  },
+  {
+   "cell_type": "code",
+   "source": [
+    "!python -m super_gradients.train_from_recipe --config-name=cifar10_resnet num_workers=2"
+   ],
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
     },
+    "id": "MTF3sl9SLnDe",
+    "outputId": "14892eef-deeb-4e54-f92f-aab86d393120"
+   },
+   "execution_count": null,
+   "outputs": [
     {
-      "cell_type": "markdown",
-      "source": [
-        "# Launch a training based on a **recipe** in a single line!\n",
-        "\n",
-        "To load a recipe, you should pass the following CLI argument: `--config-name=my_recipe`, and you also can override settings using `nested.key=value` syntax.\n",
-        "\n",
-        "For this example we will set the number of workers for train & validation data loaders to two.\n",
-        "\n",
-        "The full override command would look like `dataset_params.train_dataloader_params.num_workers=2 dataset_params.val_dataloader_params.num_workers=2`. To save the time SuperGradients offers a list of shortcut settings to achieve the same result: `num_workers=2`.\n",
-        "\n",
-        "You can read more about shortcuts [here](https://docs.deci.ai/super-gradients/latest/documentation/source/Recipes_Training.html#command-line-override-shortcuts):"
-      ],
-      "metadata": {
-        "id": "OnNaB_1Pwpq-"
-      }
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "\rValidating epoch 3: 100%|██████████| 20/20 [00:06<00:00,  3.04it/s]\n",
+      "[2023-10-30 09:40:35] INFO - base_sg_logger.py - [CLEANUP] - Successfully stopped system monitoring process\n"
+     ]
     },
     {
-      "cell_type": "code",
-      "source": [
-        "!python -m super_gradients.train_from_recipe --config-name=cifar10_resnet num_workers=2"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "MTF3sl9SLnDe",
-        "outputId": "14892eef-deeb-4e54-f92f-aab86d393120"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stderr",
-          "text": [
-            "\rValidating epoch 3: 100%|██████████| 20/20 [00:06<00:00,  3.04it/s]\n",
-            "[2023-10-30 09:40:35] INFO - base_sg_logger.py - [CLEANUP] - Successfully stopped system monitoring process\n"
-          ]
-        },
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "The console stream is logged into /root/sg_logs/console.log\n",
-            "[2023-10-30 09:40:38] INFO - crash_tips_setup.py - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it\n",
-            "[2023-10-30 09:40:38] WARNING - __init__.py - Failed to import pytorch_quantization\n",
-            "2023-10-30 09:40:40.342167: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-            "2023-10-30 09:40:40.342228: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-            "2023-10-30 09:40:40.342273: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-            "2023-10-30 09:40:41.986540: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
-            "[2023-10-30 09:40:43] INFO - utils.py - NumExpr defaulting to 2 threads.\n",
-            "[2023-10-30 09:40:44] WARNING - calibrator.py - Failed to import pytorch_quantization\n",
-            "[2023-10-30 09:40:44] WARNING - export.py - Failed to import pytorch_quantization\n",
-            "[2023-10-30 09:40:44] WARNING - selective_quantization_utils.py - Failed to import pytorch_quantization\n",
-            "[2023-10-30 09:40:45,095][HYDRA] A checkpoints directory was just created at \"/usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints\". To work with another directory, please set \"ckpt_root_dir\"\n",
-            "[2023-10-30 09:40:45,179][super_gradients.training.models.model_factory][WARNING] - Passing num_classes through arch_params is deprecated and will be removed in the next version. Pass num_classes explicitly to models.get\n",
-            "Files already downloaded and verified\n",
-            "Files already downloaded and verified\n",
-            "[2023-10-30 09:40:47,165][super_gradients.training.sg_trainer.sg_trainer][WARNING] - Train dataset size % batch_size != 0 and drop_last=False, this might result in smaller last batch.\n",
-            "[2023-10-30 09:40:47,388][super_gradients.training.sg_trainer.sg_trainer][INFO] - Starting a new run with `run_id=RUN_20231030_094047_388228`\n",
-            "[2023-10-30 09:40:47,388][super_gradients.training.sg_trainer.sg_trainer][INFO] - Checkpoints directory: /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228\n",
-            "The console stream is now moved to /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/console_Oct30_09_40_47.txt\n",
-            "[2023-10-30 09:40:48] INFO - sg_trainer_utils.py - TRAINING PARAMETERS:\n",
-            "    - Mode:                         OFF\n",
-            "    - Number of GPUs:               1          (1 available on the machine)\n",
-            "    - Full dataset size:            50000      (len(train_set))\n",
-            "    - Batch size per GPU:           256        (batch_size)\n",
-            "    - Batch Accumulate:             1          (batch_accumulate)\n",
-            "    - Total batch size:             256        (num_gpus * batch_size)\n",
-            "    - Effective Batch size:         256        (num_gpus * batch_size * batch_accumulate)\n",
-            "    - Iterations per epoch:         196        (len(train_loader))\n",
-            "    - Gradient updates per epoch:   196        (len(train_loader) / batch_accumulate)\n",
-            "\n",
-            "[2023-10-30 09:40:48] INFO - sg_trainer.py - Started training for 250 epochs (0/249)\n",
-            "\n",
-            "Train epoch 0: 100% 196/196 [00:53<00:00,  3.66it/s, Accuracy=0.299, LabelSmoothingCrossEntropyLoss=1.99, Top5=0.824, gpu_mem=1.71]\n",
-            "Validating: 100% 20/20 [00:08<00:00,  2.28it/s]\n",
-            "[2023-10-30 09:41:51] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
-            "[2023-10-30 09:41:51] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.40869998931884766\n",
-            "===========================================================\n",
-            "SUMMARY OF EPOCH 0\n",
-            "├── Train\n",
-            "│   ├── Labelsmoothingcrossentropyloss = 1.9859\n",
-            "│   ├── Accuracy = 0.2986\n",
-            "│   └── Top5 = 0.8244\n",
-            "└── Validation\n",
-            "    ├── Labelsmoothingcrossentropyloss = 1.6115\n",
-            "    ├── Accuracy = 0.4087\n",
-            "    └── Top5 = 0.8996\n",
-            "\n",
-            "===========================================================\n",
-            "Train epoch 1: 100% 196/196 [00:52<00:00,  3.75it/s, Accuracy=0.451, LabelSmoothingCrossEntropyLoss=1.48, Top5=0.92, gpu_mem=2.32]\n",
-            "Validating epoch 1: 100% 20/20 [00:06<00:00,  3.10it/s]\n",
-            "[2023-10-30 09:42:50] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
-            "[2023-10-30 09:42:50] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.46369999647140503\n",
-            "===========================================================\n",
-            "SUMMARY OF EPOCH 1\n",
-            "├── Train\n",
-            "│   ├── Labelsmoothingcrossentropyloss = 1.482\n",
-            "│   │   ├── Epoch N-1      = 1.9859 (\u001b[32m↘ -0.504\u001b[0m)\n",
-            "│   │   └── Best until now = 1.9859 (\u001b[32m↘ -0.504\u001b[0m)\n",
-            "│   ├── Accuracy = 0.4515\n",
-            "│   │   ├── Epoch N-1      = 0.2986 (\u001b[32m↗ 0.1529\u001b[0m)\n",
-            "│   │   └── Best until now = 0.2986 (\u001b[32m↗ 0.1529\u001b[0m)\n",
-            "│   └── Top5 = 0.9198\n",
-            "│       ├── Epoch N-1      = 0.8244 (\u001b[32m↗ 0.0954\u001b[0m)\n",
-            "│       └── Best until now = 0.8244 (\u001b[32m↗ 0.0954\u001b[0m)\n",
-            "└── Validation\n",
-            "    ├── Labelsmoothingcrossentropyloss = 1.537\n",
-            "    │   ├── Epoch N-1      = 1.6115 (\u001b[32m↘ -0.0744\u001b[0m)\n",
-            "    │   └── Best until now = 1.6115 (\u001b[32m↘ -0.0744\u001b[0m)\n",
-            "    ├── Accuracy = 0.4637\n",
-            "    │   ├── Epoch N-1      = 0.4087 (\u001b[32m↗ 0.055\u001b[0m)\n",
-            "    │   └── Best until now = 0.4087 (\u001b[32m↗ 0.055\u001b[0m)\n",
-            "    └── Top5 = 0.9121\n",
-            "        ├── Epoch N-1      = 0.8996 (\u001b[32m↗ 0.0125\u001b[0m)\n",
-            "        └── Best until now = 0.8996 (\u001b[32m↗ 0.0125\u001b[0m)\n",
-            "\n",
-            "===========================================================\n",
-            "Train epoch 2: 100% 196/196 [00:52<00:00,  3.70it/s, Accuracy=0.546, LabelSmoothingCrossEntropyLoss=1.24, Top5=0.947, gpu_mem=2.32]\n",
-            "Validating epoch 2: 100% 20/20 [00:08<00:00,  2.24it/s]\n",
-            "[2023-10-30 09:43:53] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
-            "[2023-10-30 09:43:53] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.5842999815940857\n",
-            "===========================================================\n",
-            "SUMMARY OF EPOCH 2\n",
-            "├── Train\n",
-            "│   ├── Labelsmoothingcrossentropyloss = 1.2429\n",
-            "│   │   ├── Epoch N-1      = 1.482  (\u001b[32m↘ -0.2391\u001b[0m)\n",
-            "│   │   └── Best until now = 1.482  (\u001b[32m↘ -0.2391\u001b[0m)\n",
-            "│   ├── Accuracy = 0.5457\n",
-            "│   │   ├── Epoch N-1      = 0.4515 (\u001b[32m↗ 0.0942\u001b[0m)\n",
-            "│   │   └── Best until now = 0.4515 (\u001b[32m↗ 0.0942\u001b[0m)\n",
-            "│   └── Top5 = 0.9473\n",
-            "│       ├── Epoch N-1      = 0.9198 (\u001b[32m↗ 0.0275\u001b[0m)\n",
-            "│       └── Best until now = 0.9198 (\u001b[32m↗ 0.0275\u001b[0m)\n",
-            "└── Validation\n",
-            "    ├── Labelsmoothingcrossentropyloss = 1.1701\n",
-            "    │   ├── Epoch N-1      = 1.537  (\u001b[32m↘ -0.367\u001b[0m)\n",
-            "    │   └── Best until now = 1.537  (\u001b[32m↘ -0.367\u001b[0m)\n",
-            "    ├── Accuracy = 0.5843\n",
-            "    │   ├── Epoch N-1      = 0.4637 (\u001b[32m↗ 0.1206\u001b[0m)\n",
-            "    │   └── Best until now = 0.4637 (\u001b[32m↗ 0.1206\u001b[0m)\n",
-            "    └── Top5 = 0.957\n",
-            "        ├── Epoch N-1      = 0.9121 (\u001b[32m↗ 0.0449\u001b[0m)\n",
-            "        └── Best until now = 0.9121 (\u001b[32m↗ 0.0449\u001b[0m)\n",
-            "\n",
-            "===========================================================\n",
-            "Train epoch 3: 100% 196/196 [00:53<00:00,  3.65it/s, Accuracy=0.631, LabelSmoothingCrossEntropyLoss=1.03, Top5=0.966, gpu_mem=2.32]\n",
-            "Validating epoch 3: 100% 20/20 [00:07<00:00,  2.54it/s]\n",
-            "[2023-10-30 09:44:56] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
-            "[2023-10-30 09:44:56] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.6061000227928162\n",
-            "===========================================================\n",
-            "SUMMARY OF EPOCH 3\n",
-            "├── Train\n",
-            "│   ├── Labelsmoothingcrossentropyloss = 1.031\n",
-            "│   │   ├── Epoch N-1      = 1.2429 (\u001b[32m↘ -0.2119\u001b[0m)\n",
-            "│   │   └── Best until now = 1.2429 (\u001b[32m↘ -0.2119\u001b[0m)\n",
-            "│   ├── Accuracy = 0.6308\n",
-            "│   │   ├── Epoch N-1      = 0.5457 (\u001b[32m↗ 0.0852\u001b[0m)\n",
-            "│   │   └── Best until now = 0.5457 (\u001b[32m↗ 0.0852\u001b[0m)\n",
-            "│   └── Top5 = 0.9658\n",
-            "│       ├── Epoch N-1      = 0.9473 (\u001b[32m↗ 0.0186\u001b[0m)\n",
-            "│       └── Best until now = 0.9473 (\u001b[32m↗ 0.0186\u001b[0m)\n",
-            "└── Validation\n",
-            "    ├── Labelsmoothingcrossentropyloss = 1.137\n",
-            "    │   ├── Epoch N-1      = 1.1701 (\u001b[32m↘ -0.0331\u001b[0m)\n",
-            "    │   └── Best until now = 1.1701 (\u001b[32m↘ -0.0331\u001b[0m)\n",
-            "    ├── Accuracy = 0.6061\n",
-            "    │   ├── Epoch N-1      = 0.5843 (\u001b[32m↗ 0.0218\u001b[0m)\n",
-            "    │   └── Best until now = 0.5843 (\u001b[32m↗ 0.0218\u001b[0m)\n",
-            "    └── Top5 = 0.9646\n",
-            "        ├── Epoch N-1      = 0.957  (\u001b[32m↗ 0.0076\u001b[0m)\n",
-            "        └── Best until now = 0.957  (\u001b[32m↗ 0.0076\u001b[0m)\n",
-            "\n",
-            "===========================================================\n",
-            "Train epoch 4: 100% 196/196 [00:53<00:00,  3.66it/s, Accuracy=0.688, LabelSmoothingCrossEntropyLoss=0.88, Top5=0.976, gpu_mem=2.32]\n",
-            "Validating epoch 4: 100% 20/20 [00:06<00:00,  3.14it/s]\n",
-            "[2023-10-30 09:45:57] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
-            "[2023-10-30 09:45:57] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.6848999857902527\n",
-            "===========================================================\n",
-            "SUMMARY OF EPOCH 4\n",
-            "├── Train\n",
-            "│   ├── Labelsmoothingcrossentropyloss = 0.8802\n",
-            "│   │   ├── Epoch N-1      = 1.031  (\u001b[32m↘ -0.1508\u001b[0m)\n",
-            "│   │   └── Best until now = 1.031  (\u001b[32m↘ -0.1508\u001b[0m)\n",
-            "│   ├── Accuracy = 0.6876\n",
-            "│   │   ├── Epoch N-1      = 0.6308 (\u001b[32m↗ 0.0567\u001b[0m)\n",
-            "│   │   └── Best until now = 0.6308 (\u001b[32m↗ 0.0567\u001b[0m)\n",
-            "│   └── Top5 = 0.9755\n",
-            "│       ├── Epoch N-1      = 0.9658 (\u001b[32m↗ 0.0097\u001b[0m)\n",
-            "│       └── Best until now = 0.9658 (\u001b[32m↗ 0.0097\u001b[0m)\n",
-            "└── Validation\n",
-            "    ├── Labelsmoothingcrossentropyloss = 0.9194\n",
-            "    │   ├── Epoch N-1      = 1.137  (\u001b[32m↘ -0.2175\u001b[0m)\n",
-            "    │   └── Best until now = 1.137  (\u001b[32m↘ -0.2175\u001b[0m)\n",
-            "    ├── Accuracy = 0.6849\n",
-            "    │   ├── Epoch N-1      = 0.6061 (\u001b[32m↗ 0.0788\u001b[0m)\n",
-            "    │   └── Best until now = 0.6061 (\u001b[32m↗ 0.0788\u001b[0m)\n",
-            "    └── Top5 = 0.9715\n",
-            "        ├── Epoch N-1      = 0.9646 (\u001b[32m↗ 0.0069\u001b[0m)\n",
-            "        └── Best until now = 0.9646 (\u001b[32m↗ 0.0069\u001b[0m)\n",
-            "\n",
-            "===========================================================\n",
-            "Train epoch 5: 100% 196/196 [00:53<00:00,  3.64it/s, Accuracy=0.722, LabelSmoothingCrossEntropyLoss=0.784, Top5=0.982, gpu_mem=2.32]\n",
-            "Validating epoch 5: 100% 20/20 [00:08<00:00,  2.24it/s]\n",
-            "[2023-10-30 09:47:01] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
-            "[2023-10-30 09:47:01] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.7394999861717224\n",
-            "===========================================================\n",
-            "SUMMARY OF EPOCH 5\n",
-            "├── Train\n",
-            "│   ├── Labelsmoothingcrossentropyloss = 0.7844\n",
-            "│   │   ├── Epoch N-1      = 0.8802 (\u001b[32m↘ -0.0958\u001b[0m)\n",
-            "│   │   └── Best until now = 0.8802 (\u001b[32m↘ -0.0958\u001b[0m)\n",
-            "│   ├── Accuracy = 0.7219\n",
-            "│   │   ├── Epoch N-1      = 0.6876 (\u001b[32m↗ 0.0344\u001b[0m)\n",
-            "│   │   └── Best until now = 0.6876 (\u001b[32m↗ 0.0344\u001b[0m)\n",
-            "│   └── Top5 = 0.9821\n",
-            "│       ├── Epoch N-1      = 0.9755 (\u001b[32m↗ 0.0066\u001b[0m)\n",
-            "│       └── Best until now = 0.9755 (\u001b[32m↗ 0.0066\u001b[0m)\n",
-            "└── Validation\n",
-            "    ├── Labelsmoothingcrossentropyloss = 0.7526\n",
-            "    │   ├── Epoch N-1      = 0.9194 (\u001b[32m↘ -0.1668\u001b[0m)\n",
-            "    │   └── Best until now = 0.9194 (\u001b[32m↘ -0.1668\u001b[0m)\n",
-            "    ├── Accuracy = 0.7395\n",
-            "    │   ├── Epoch N-1      = 0.6849 (\u001b[32m↗ 0.0546\u001b[0m)\n",
-            "    │   └── Best until now = 0.6849 (\u001b[32m↗ 0.0546\u001b[0m)\n",
-            "    └── Top5 = 0.984\n",
-            "        ├── Epoch N-1      = 0.9715 (\u001b[32m↗ 0.0125\u001b[0m)\n",
-            "        └── Best until now = 0.9715 (\u001b[32m↗ 0.0125\u001b[0m)\n",
-            "\n",
-            "===========================================================\n",
-            "Train epoch 6:  58% 113/196 [00:31<00:18,  4.61it/s, Accuracy=0.754, LabelSmoothingCrossEntropyLoss=0.692, Top5=0.988, gpu_mem=2.32]"
-          ]
-        }
-      ]
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "The console stream is logged into /root/sg_logs/console.log\n",
+      "[2023-10-30 09:40:38] INFO - crash_tips_setup.py - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it\n",
+      "[2023-10-30 09:40:38] WARNING - __init__.py - Failed to import pytorch_quantization\n",
+      "2023-10-30 09:40:40.342167: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "2023-10-30 09:40:40.342228: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "2023-10-30 09:40:40.342273: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "2023-10-30 09:40:41.986540: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
+      "[2023-10-30 09:40:43] INFO - utils.py - NumExpr defaulting to 2 threads.\n",
+      "[2023-10-30 09:40:44] WARNING - calibrator.py - Failed to import pytorch_quantization\n",
+      "[2023-10-30 09:40:44] WARNING - export.py - Failed to import pytorch_quantization\n",
+      "[2023-10-30 09:40:44] WARNING - selective_quantization_utils.py - Failed to import pytorch_quantization\n",
+      "[2023-10-30 09:40:45,095][HYDRA] A checkpoints directory was just created at \"/usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints\". To work with another directory, please set \"ckpt_root_dir\"\n",
+      "[2023-10-30 09:40:45,179][super_gradients.training.models.model_factory][WARNING] - Passing num_classes through arch_params is deprecated and will be removed in the next version. Pass num_classes explicitly to models.get\n",
+      "Files already downloaded and verified\n",
+      "Files already downloaded and verified\n",
+      "[2023-10-30 09:40:47,165][super_gradients.training.sg_trainer.sg_trainer][WARNING] - Train dataset size % batch_size != 0 and drop_last=False, this might result in smaller last batch.\n",
+      "[2023-10-30 09:40:47,388][super_gradients.training.sg_trainer.sg_trainer][INFO] - Starting a new run with `run_id=RUN_20231030_094047_388228`\n",
+      "[2023-10-30 09:40:47,388][super_gradients.training.sg_trainer.sg_trainer][INFO] - Checkpoints directory: /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228\n",
+      "The console stream is now moved to /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/console_Oct30_09_40_47.txt\n",
+      "[2023-10-30 09:40:48] INFO - sg_trainer_utils.py - TRAINING PARAMETERS:\n",
+      "    - Mode:                         OFF\n",
+      "    - Number of GPUs:               1          (1 available on the machine)\n",
+      "    - Full dataset size:            50000      (len(train_set))\n",
+      "    - Batch size per GPU:           256        (batch_size)\n",
+      "    - Batch Accumulate:             1          (batch_accumulate)\n",
+      "    - Total batch size:             256        (num_gpus * batch_size)\n",
+      "    - Effective Batch size:         256        (num_gpus * batch_size * batch_accumulate)\n",
+      "    - Iterations per epoch:         196        (len(train_loader))\n",
+      "    - Gradient updates per epoch:   196        (len(train_loader) / batch_accumulate)\n",
+      "\n",
+      "[2023-10-30 09:40:48] INFO - sg_trainer.py - Started training for 250 epochs (0/249)\n",
+      "\n",
+      "Train epoch 0: 100% 196/196 [00:53<00:00,  3.66it/s, Accuracy=0.299, LabelSmoothingCrossEntropyLoss=1.99, Top5=0.824, gpu_mem=1.71]\n",
+      "Validating: 100% 20/20 [00:08<00:00,  2.28it/s]\n",
+      "[2023-10-30 09:41:51] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
+      "[2023-10-30 09:41:51] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.40869998931884766\n",
+      "===========================================================\n",
+      "SUMMARY OF EPOCH 0\n",
+      "├── Train\n",
+      "│   ├── Labelsmoothingcrossentropyloss = 1.9859\n",
+      "│   ├── Accuracy = 0.2986\n",
+      "│   └── Top5 = 0.8244\n",
+      "└── Validation\n",
+      "    ├── Labelsmoothingcrossentropyloss = 1.6115\n",
+      "    ├── Accuracy = 0.4087\n",
+      "    └── Top5 = 0.8996\n",
+      "\n",
+      "===========================================================\n",
+      "Train epoch 1: 100% 196/196 [00:52<00:00,  3.75it/s, Accuracy=0.451, LabelSmoothingCrossEntropyLoss=1.48, Top5=0.92, gpu_mem=2.32]\n",
+      "Validating epoch 1: 100% 20/20 [00:06<00:00,  3.10it/s]\n",
+      "[2023-10-30 09:42:50] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
+      "[2023-10-30 09:42:50] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.46369999647140503\n",
+      "===========================================================\n",
+      "SUMMARY OF EPOCH 1\n",
+      "├── Train\n",
+      "│   ├── Labelsmoothingcrossentropyloss = 1.482\n",
+      "│   │   ├── Epoch N-1      = 1.9859 (\u001B[32m↘ -0.504\u001B[0m)\n",
+      "│   │   └── Best until now = 1.9859 (\u001B[32m↘ -0.504\u001B[0m)\n",
+      "│   ├── Accuracy = 0.4515\n",
+      "│   │   ├── Epoch N-1      = 0.2986 (\u001B[32m↗ 0.1529\u001B[0m)\n",
+      "│   │   └── Best until now = 0.2986 (\u001B[32m↗ 0.1529\u001B[0m)\n",
+      "│   └── Top5 = 0.9198\n",
+      "│       ├── Epoch N-1      = 0.8244 (\u001B[32m↗ 0.0954\u001B[0m)\n",
+      "│       └── Best until now = 0.8244 (\u001B[32m↗ 0.0954\u001B[0m)\n",
+      "└── Validation\n",
+      "    ├── Labelsmoothingcrossentropyloss = 1.537\n",
+      "    │   ├── Epoch N-1      = 1.6115 (\u001B[32m↘ -0.0744\u001B[0m)\n",
+      "    │   └── Best until now = 1.6115 (\u001B[32m↘ -0.0744\u001B[0m)\n",
+      "    ├── Accuracy = 0.4637\n",
+      "    │   ├── Epoch N-1      = 0.4087 (\u001B[32m↗ 0.055\u001B[0m)\n",
+      "    │   └── Best until now = 0.4087 (\u001B[32m↗ 0.055\u001B[0m)\n",
+      "    └── Top5 = 0.9121\n",
+      "        ├── Epoch N-1      = 0.8996 (\u001B[32m↗ 0.0125\u001B[0m)\n",
+      "        └── Best until now = 0.8996 (\u001B[32m↗ 0.0125\u001B[0m)\n",
+      "\n",
+      "===========================================================\n",
+      "Train epoch 2: 100% 196/196 [00:52<00:00,  3.70it/s, Accuracy=0.546, LabelSmoothingCrossEntropyLoss=1.24, Top5=0.947, gpu_mem=2.32]\n",
+      "Validating epoch 2: 100% 20/20 [00:08<00:00,  2.24it/s]\n",
+      "[2023-10-30 09:43:53] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
+      "[2023-10-30 09:43:53] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.5842999815940857\n",
+      "===========================================================\n",
+      "SUMMARY OF EPOCH 2\n",
+      "├── Train\n",
+      "│   ├── Labelsmoothingcrossentropyloss = 1.2429\n",
+      "│   │   ├── Epoch N-1      = 1.482  (\u001B[32m↘ -0.2391\u001B[0m)\n",
+      "│   │   └── Best until now = 1.482  (\u001B[32m↘ -0.2391\u001B[0m)\n",
+      "│   ├── Accuracy = 0.5457\n",
+      "│   │   ├── Epoch N-1      = 0.4515 (\u001B[32m↗ 0.0942\u001B[0m)\n",
+      "│   │   └── Best until now = 0.4515 (\u001B[32m↗ 0.0942\u001B[0m)\n",
+      "│   └── Top5 = 0.9473\n",
+      "│       ├── Epoch N-1      = 0.9198 (\u001B[32m↗ 0.0275\u001B[0m)\n",
+      "│       └── Best until now = 0.9198 (\u001B[32m↗ 0.0275\u001B[0m)\n",
+      "└── Validation\n",
+      "    ├── Labelsmoothingcrossentropyloss = 1.1701\n",
+      "    │   ├── Epoch N-1      = 1.537  (\u001B[32m↘ -0.367\u001B[0m)\n",
+      "    │   └── Best until now = 1.537  (\u001B[32m↘ -0.367\u001B[0m)\n",
+      "    ├── Accuracy = 0.5843\n",
+      "    │   ├── Epoch N-1      = 0.4637 (\u001B[32m↗ 0.1206\u001B[0m)\n",
+      "    │   └── Best until now = 0.4637 (\u001B[32m↗ 0.1206\u001B[0m)\n",
+      "    └── Top5 = 0.957\n",
+      "        ├── Epoch N-1      = 0.9121 (\u001B[32m↗ 0.0449\u001B[0m)\n",
+      "        └── Best until now = 0.9121 (\u001B[32m↗ 0.0449\u001B[0m)\n",
+      "\n",
+      "===========================================================\n",
+      "Train epoch 3: 100% 196/196 [00:53<00:00,  3.65it/s, Accuracy=0.631, LabelSmoothingCrossEntropyLoss=1.03, Top5=0.966, gpu_mem=2.32]\n",
+      "Validating epoch 3: 100% 20/20 [00:07<00:00,  2.54it/s]\n",
+      "[2023-10-30 09:44:56] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
+      "[2023-10-30 09:44:56] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.6061000227928162\n",
+      "===========================================================\n",
+      "SUMMARY OF EPOCH 3\n",
+      "├── Train\n",
+      "│   ├── Labelsmoothingcrossentropyloss = 1.031\n",
+      "│   │   ├── Epoch N-1      = 1.2429 (\u001B[32m↘ -0.2119\u001B[0m)\n",
+      "│   │   └── Best until now = 1.2429 (\u001B[32m↘ -0.2119\u001B[0m)\n",
+      "│   ├── Accuracy = 0.6308\n",
+      "│   │   ├── Epoch N-1      = 0.5457 (\u001B[32m↗ 0.0852\u001B[0m)\n",
+      "│   │   └── Best until now = 0.5457 (\u001B[32m↗ 0.0852\u001B[0m)\n",
+      "│   └── Top5 = 0.9658\n",
+      "│       ├── Epoch N-1      = 0.9473 (\u001B[32m↗ 0.0186\u001B[0m)\n",
+      "│       └── Best until now = 0.9473 (\u001B[32m↗ 0.0186\u001B[0m)\n",
+      "└── Validation\n",
+      "    ├── Labelsmoothingcrossentropyloss = 1.137\n",
+      "    │   ├── Epoch N-1      = 1.1701 (\u001B[32m↘ -0.0331\u001B[0m)\n",
+      "    │   └── Best until now = 1.1701 (\u001B[32m↘ -0.0331\u001B[0m)\n",
+      "    ├── Accuracy = 0.6061\n",
+      "    │   ├── Epoch N-1      = 0.5843 (\u001B[32m↗ 0.0218\u001B[0m)\n",
+      "    │   └── Best until now = 0.5843 (\u001B[32m↗ 0.0218\u001B[0m)\n",
+      "    └── Top5 = 0.9646\n",
+      "        ├── Epoch N-1      = 0.957  (\u001B[32m↗ 0.0076\u001B[0m)\n",
+      "        └── Best until now = 0.957  (\u001B[32m↗ 0.0076\u001B[0m)\n",
+      "\n",
+      "===========================================================\n",
+      "Train epoch 4: 100% 196/196 [00:53<00:00,  3.66it/s, Accuracy=0.688, LabelSmoothingCrossEntropyLoss=0.88, Top5=0.976, gpu_mem=2.32]\n",
+      "Validating epoch 4: 100% 20/20 [00:06<00:00,  3.14it/s]\n",
+      "[2023-10-30 09:45:57] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
+      "[2023-10-30 09:45:57] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.6848999857902527\n",
+      "===========================================================\n",
+      "SUMMARY OF EPOCH 4\n",
+      "├── Train\n",
+      "│   ├── Labelsmoothingcrossentropyloss = 0.8802\n",
+      "│   │   ├── Epoch N-1      = 1.031  (\u001B[32m↘ -0.1508\u001B[0m)\n",
+      "│   │   └── Best until now = 1.031  (\u001B[32m↘ -0.1508\u001B[0m)\n",
+      "│   ├── Accuracy = 0.6876\n",
+      "│   │   ├── Epoch N-1      = 0.6308 (\u001B[32m↗ 0.0567\u001B[0m)\n",
+      "│   │   └── Best until now = 0.6308 (\u001B[32m↗ 0.0567\u001B[0m)\n",
+      "│   └── Top5 = 0.9755\n",
+      "│       ├── Epoch N-1      = 0.9658 (\u001B[32m↗ 0.0097\u001B[0m)\n",
+      "│       └── Best until now = 0.9658 (\u001B[32m↗ 0.0097\u001B[0m)\n",
+      "└── Validation\n",
+      "    ├── Labelsmoothingcrossentropyloss = 0.9194\n",
+      "    │   ├── Epoch N-1      = 1.137  (\u001B[32m↘ -0.2175\u001B[0m)\n",
+      "    │   └── Best until now = 1.137  (\u001B[32m↘ -0.2175\u001B[0m)\n",
+      "    ├── Accuracy = 0.6849\n",
+      "    │   ├── Epoch N-1      = 0.6061 (\u001B[32m↗ 0.0788\u001B[0m)\n",
+      "    │   └── Best until now = 0.6061 (\u001B[32m↗ 0.0788\u001B[0m)\n",
+      "    └── Top5 = 0.9715\n",
+      "        ├── Epoch N-1      = 0.9646 (\u001B[32m↗ 0.0069\u001B[0m)\n",
+      "        └── Best until now = 0.9646 (\u001B[32m↗ 0.0069\u001B[0m)\n",
+      "\n",
+      "===========================================================\n",
+      "Train epoch 5: 100% 196/196 [00:53<00:00,  3.64it/s, Accuracy=0.722, LabelSmoothingCrossEntropyLoss=0.784, Top5=0.982, gpu_mem=2.32]\n",
+      "Validating epoch 5: 100% 20/20 [00:08<00:00,  2.24it/s]\n",
+      "[2023-10-30 09:47:01] INFO - base_sg_logger.py - Checkpoint saved in /usr/local/lib/python3.10/dist-packages/super_gradients/checkpoints/resnet18_cifar_interpolation_check/RUN_20231030_094047_388228/ckpt_best.pth\n",
+      "[2023-10-30 09:47:01] INFO - sg_trainer.py - Best checkpoint overriden: validation Accuracy: 0.7394999861717224\n",
+      "===========================================================\n",
+      "SUMMARY OF EPOCH 5\n",
+      "├── Train\n",
+      "│   ├── Labelsmoothingcrossentropyloss = 0.7844\n",
+      "│   │   ├── Epoch N-1      = 0.8802 (\u001B[32m↘ -0.0958\u001B[0m)\n",
+      "│   │   └── Best until now = 0.8802 (\u001B[32m↘ -0.0958\u001B[0m)\n",
+      "│   ├── Accuracy = 0.7219\n",
+      "│   │   ├── Epoch N-1      = 0.6876 (\u001B[32m↗ 0.0344\u001B[0m)\n",
+      "│   │   └── Best until now = 0.6876 (\u001B[32m↗ 0.0344\u001B[0m)\n",
+      "│   └── Top5 = 0.9821\n",
+      "│       ├── Epoch N-1      = 0.9755 (\u001B[32m↗ 0.0066\u001B[0m)\n",
+      "│       └── Best until now = 0.9755 (\u001B[32m↗ 0.0066\u001B[0m)\n",
+      "└── Validation\n",
+      "    ├── Labelsmoothingcrossentropyloss = 0.7526\n",
+      "    │   ├── Epoch N-1      = 0.9194 (\u001B[32m↘ -0.1668\u001B[0m)\n",
+      "    │   └── Best until now = 0.9194 (\u001B[32m↘ -0.1668\u001B[0m)\n",
+      "    ├── Accuracy = 0.7395\n",
+      "    │   ├── Epoch N-1      = 0.6849 (\u001B[32m↗ 0.0546\u001B[0m)\n",
+      "    │   └── Best until now = 0.6849 (\u001B[32m↗ 0.0546\u001B[0m)\n",
+      "    └── Top5 = 0.984\n",
+      "        ├── Epoch N-1      = 0.9715 (\u001B[32m↗ 0.0125\u001B[0m)\n",
+      "        └── Best until now = 0.9715 (\u001B[32m↗ 0.0125\u001B[0m)\n",
+      "\n",
+      "===========================================================\n",
+      "Train epoch 6:  58% 113/196 [00:31<00:18,  4.61it/s, Accuracy=0.754, LabelSmoothingCrossEntropyLoss=0.692, Top5=0.988, gpu_mem=2.32]"
+     ]
     }
-  ]
+   ]
+  }
+ ]
 }
diff --git a/tests/deci_core_unit_test_suite_runner.py b/tests/deci_core_unit_test_suite_runner.py
index 6b0271e404..9202564cfa 100644
--- a/tests/deci_core_unit_test_suite_runner.py
+++ b/tests/deci_core_unit_test_suite_runner.py
@@ -48,6 +48,7 @@
 from tests.unit_tests.test_deprecations import DeprecationsUnitTest
 from tests.unit_tests.test_min_samples_single_node import TestMinSamplesSingleNode
 from tests.unit_tests.test_train_with_torch_scheduler import TrainWithTorchSchedulerTest
+from tests.unit_tests.test_version_check import TestVersionCheck
 from tests.unit_tests.test_yolo_nas_pose import YoloNASPoseTests
 from tests.unit_tests.train_with_intialized_param_args_test import TrainWithInitializedObjectsTest
 from tests.unit_tests.pretrained_models_unit_test import PretrainedModelsUnitTest
@@ -166,6 +167,7 @@ def _add_modules_to_unit_tests_suite(self):
         self.unit_tests_suite.addTest(self.test_loader.loadTestsFromModule(PoseEstimationSampleTest))
         self.unit_tests_suite.addTest(self.test_loader.loadTestsFromModule(TestMixedPrecisionDisabled))
         self.unit_tests_suite.addTest(self.test_loader.loadTestsFromModule(DynamicModelTests))
+        self.unit_tests_suite.addTest(self.test_loader.loadTestsFromModule(TestVersionCheck))
 
     def _add_modules_to_end_to_end_tests_suite(self):
         """
diff --git a/tests/unit_tests/test_version_check.py b/tests/unit_tests/test_version_check.py
new file mode 100644
index 0000000000..1226e3349f
--- /dev/null
+++ b/tests/unit_tests/test_version_check.py
@@ -0,0 +1,34 @@
+import unittest
+
+from tests.verify_notebook_version import try_extract_super_gradients_version_from_pip_install_command
+
+
+class TestVersionCheck(unittest.TestCase):
+    def test_pip_install_no_version(self):
+        self.assertIsNone(try_extract_super_gradients_version_from_pip_install_command("!pip install super-gradients"))
+
+    def test_pip_install_major_only(self):
+        self.assertEquals(try_extract_super_gradients_version_from_pip_install_command("!pip install super-gradients==3"), "3")
+
+    def test_pip_install_major_minor(self):
+        self.assertEquals(try_extract_super_gradients_version_from_pip_install_command("!pip install super-gradients==3.0"), "3.0")
+
+    def test_pip_install_major_patch(self):
+        self.assertEquals(try_extract_super_gradients_version_from_pip_install_command("!pip install super-gradients==3.3.1"), "3.3.1")
+
+    def test_pip_install_with_extra_args(self):
+        self.assertEquals(try_extract_super_gradients_version_from_pip_install_command("!pip install -q super-gradients==3.3.1"), "3.3.1")
+        self.assertEquals(try_extract_super_gradients_version_from_pip_install_command("!pip install super-gradients==3.3.1 --extra-index-url=foobar"), "3.3.1")
+
+    def test_pip_install_with_space(self):
+        self.assertEquals(try_extract_super_gradients_version_from_pip_install_command("! pip install -q super-gradients==3.3.1"), "3.3.1")
+
+    def test_pip_install_with_stdout_redirect(self):
+        self.assertEquals(try_extract_super_gradients_version_from_pip_install_command("! pip install -q super-gradients==3.3.1 &> /dev/null"), "3.3.1")
+
+    def test_pip_install_with_extra_packages(self):
+        self.assertEquals(try_extract_super_gradients_version_from_pip_install_command("! pip install super-gradients==3.3.1 torch==2.0 numpy>2"), "3.3.1")
+
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/tests/verify_notebook_version.py b/tests/verify_notebook_version.py
index f5ceec54da..774ab3a94e 100644
--- a/tests/verify_notebook_version.py
+++ b/tests/verify_notebook_version.py
@@ -1,5 +1,7 @@
 import re
 import sys
+from typing import Optional
+
 import super_gradients
 import nbformat
 
@@ -19,6 +21,22 @@ def get_first_cell_content(notebook_path):
     return first_cell_content
 
 
+def try_extract_super_gradients_version_from_pip_install_command(input: str) -> Optional[str]:
+    """
+    Extracts the version of super_gradients from a string like `!pip install super_gradients=={version}` command.
+    A pip install may contain extra arguments, e.g. `!pip install -q super_gradients=={version} torch=={another version}`.
+
+    :param input: A string that contains a `!pip install super_gradients=={version}` command.
+    :return: The version of super_gradients.
+    """
+    pattern = re.compile(r"pip\s+install.*?super-gradients==([0-9]+(?:\.[0-9]+)*(?:\.[0-9]+)?)")
+    match = re.search(pattern, input)
+    if match:
+        return match.group(1)
+    else:
+        return None
+
+
 def main():
     """
     This script is used to verify that the version of the SG package matches the version of SG installed in the notebook.
@@ -29,13 +47,9 @@ def main():
     first_cell_content = get_first_cell_content(notebook_path)
     print(first_cell_content)
 
-    # Check if the first cell contains "!pip install super_gradients=={version}" using regex and extract the version
-    pattern = re.compile(r"^!pip install super_gradients==([\d\.]+)")
-
     for line in first_cell_content.splitlines():
-        match = re.search(pattern, line)
-        if match:
-            sg_version_in_notebook = match.group(1)
+        sg_version_in_notebook = try_extract_super_gradients_version_from_pip_install_command(line)
+        if sg_version_in_notebook is not None:
             if sg_version_in_notebook == super_gradients.__version__:
                 return 0
             else: