Cleaned notebooks removing the stored output

benchmark/notebooks/LLM Score Experimentation.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": null,
    "id": "15386da8",
    "metadata": {},
    "outputs": [],
@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": null,
    "id": "e9d1c3a6",
    "metadata": {},
    "outputs": [],
@@ -96,7 +96,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": null,
    "id": "8ff9cd33",
    "metadata": {},
    "outputs": [],
@@ -123,7 +123,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": null,
    "id": "d0bfdce5",
    "metadata": {},
    "outputs": [],
@@ -203,7 +203,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": null,
    "id": "3de1d6d4",
    "metadata": {},
    "outputs": [],
@@ -276,7 +276,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "a5bf2f5c",
    "metadata": {},
    "outputs": [],
@@ -288,7 +288,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
+   "execution_count": null,
    "id": "1cd01a4c",
    "metadata": {},
    "outputs": [],
@@ -300,20 +300,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": null,
    "id": "72e6ac91",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "REFERENCE: 66.5 6.0 0.0\n",
-      "RUBRIC: 65.0 4.0 0.0\n",
-      "QUESTION: 87.0 6.5 0.0\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# response3 - the worst one\n",
     "print('REFERENCE:', reference_response_percentage, reference_response_scale, reference_response_binary)\n",
@@ -323,20 +313,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 83,
+   "execution_count": null,
    "id": "a66014ee",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "REFERENCE: 100.0 10.0 1.0\n",
-      "RUBRIC: 88.0 7.5 1.0\n",
-      "QUESTION: 87.0 7.5 1.0\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# reference_response - the best one\n",
     "print('REFERENCE:', reference_response_ideal_percentage, reference_response_ideal_scale, reference_response_ideal_binary)\n",