Delete BERTić code.ipynb

BERTić code.ipynb

@@ -1,877 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "ac15a924",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "=== Treniranje i evaluacija za trening skup: train_combined ===\n",
-      "\n",
-      "--- Fine-tuning model: classla/bcms-bertic ---\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Some weights of ElectraForSequenceClassification were not initialized from the model checkpoint at classla/bcms-bertic and are newly initialized: ['classifier.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.bias', 'classifier.out_proj.weight']\n",
-      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "aed062bba63e49b5a657521638acc86c",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/7577 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "\n",
-       "    <div>\n",
-       "      \n",
-       "      <progress value='1422' max='1422' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1422/1422 45:18, Epoch 3/3]\n",
-       "    </div>\n",
-       "    <table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       " <tr style=\"text-align: left;\">\n",
-       "      <th>Step</th>\n",
-       "      <th>Training Loss</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <td>50</td>\n",
-       "      <td>0.929600</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>100</td>\n",
-       "      <td>0.843100</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>150</td>\n",
-       "      <td>0.744100</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>200</td>\n",
-       "      <td>0.645000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>250</td>\n",
-       "      <td>0.633000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>300</td>\n",
-       "      <td>0.641400</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>350</td>\n",
-       "      <td>0.618200</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>400</td>\n",
-       "      <td>0.594200</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>450</td>\n",
-       "      <td>0.578800</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>500</td>\n",
-       "      <td>0.484900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>550</td>\n",
-       "      <td>0.436400</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>600</td>\n",
-       "      <td>0.485900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>650</td>\n",
-       "      <td>0.484800</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>700</td>\n",
-       "      <td>0.509100</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>750</td>\n",
-       "      <td>0.437300</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>800</td>\n",
-       "      <td>0.518500</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>850</td>\n",
-       "      <td>0.512200</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>900</td>\n",
-       "      <td>0.410600</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>950</td>\n",
-       "      <td>0.471700</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1000</td>\n",
-       "      <td>0.401200</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1050</td>\n",
-       "      <td>0.374100</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1100</td>\n",
-       "      <td>0.397300</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1150</td>\n",
-       "      <td>0.363700</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1200</td>\n",
-       "      <td>0.325300</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1250</td>\n",
-       "      <td>0.291000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1300</td>\n",
-       "      <td>0.335900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1350</td>\n",
-       "      <td>0.395900</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>1400</td>\n",
-       "      <td>0.331800</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table><p>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Evaluacija na test skupu test-1\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "fb87532e026a4d0b8aa72d5cbfc4fb2a",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/653 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Evaluacija: {'eval_loss': 0.8313503265380859, 'eval_accuracy': 0.7136294027565084, 'eval_f1_macro': 0.624180014657386, 'eval_runtime': 16.74, 'eval_samples_per_second': 39.008, 'eval_steps_per_second': 1.254, 'epoch': 3.0}\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Confusion Matrix:\n",
-      "[[109  48   8]\n",
-      " [ 70 328  32]\n",
-      " [  4  25  29]]\n",
-      "\n",
-      "Classification Report:\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "    negative       0.60      0.66      0.63       165\n",
-      "     neutral       0.82      0.76      0.79       430\n",
-      "    positive       0.42      0.50      0.46        58\n",
-      "\n",
-      "    accuracy                           0.71       653\n",
-      "   macro avg       0.61      0.64      0.62       653\n",
-      "weighted avg       0.73      0.71      0.72       653\n",
-      "\n",
-      "Predikcije spremljene u results_train_combined/predictions_test_1.csv\n",
-      "\n",
-      "Evaluacija na test skupu test-2\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "109da4be6d1d4c0d826f1320e481d4e1",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/741 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Evaluacija: {'eval_loss': 0.23835134506225586, 'eval_accuracy': 0.9257759784075573, 'eval_f1_macro': 0.907760132195386, 'eval_runtime': 19.6933, 'eval_samples_per_second': 37.627, 'eval_steps_per_second': 1.219, 'epoch': 3.0}\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Confusion Matrix:\n",
-      "[[197  16   3]\n",
-      " [ 14 410   7]\n",
-      " [  3  12  79]]\n",
-      "\n",
-      "Classification Report:\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "    negative       0.92      0.91      0.92       216\n",
-      "     neutral       0.94      0.95      0.94       431\n",
-      "    positive       0.89      0.84      0.86        94\n",
-      "\n",
-      "    accuracy                           0.93       741\n",
-      "   macro avg       0.91      0.90      0.91       741\n",
-      "weighted avg       0.93      0.93      0.93       741\n",
-      "\n",
-      "Predikcije spremljene u results_train_combined/predictions_test_2.csv\n",
-      "\n",
-      "Evaluacija na test skupu test-3\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3b91d6b9cfde4469a865dd69c79b4f34",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/793 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Evaluacija: {'eval_loss': 0.8141497373580933, 'eval_accuracy': 0.7679697351828499, 'eval_f1_macro': 0.7678761268324849, 'eval_runtime': 20.857, 'eval_samples_per_second': 38.021, 'eval_steps_per_second': 1.199, 'epoch': 3.0}\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Confusion Matrix:\n",
-      "[[212  51   4]\n",
-      " [  7 250   6]\n",
-      " [  6 110 147]]\n",
-      "\n",
-      "Classification Report:\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "    negative       0.94      0.79      0.86       267\n",
-      "     neutral       0.61      0.95      0.74       263\n",
-      "    positive       0.94      0.56      0.70       263\n",
-      "\n",
-      "    accuracy                           0.77       793\n",
-      "   macro avg       0.83      0.77      0.77       793\n",
-      "weighted avg       0.83      0.77      0.77       793\n",
-      "\n",
-      "Predikcije spremljene u results_train_combined/predictions_test_3.csv\n",
-      "\n",
-      "\n",
-      "=== Treniranje i evaluacija za trening skup: train_2 ===\n",
-      "\n",
-      "--- Fine-tuning model: classla/bcms-bertic ---\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Some weights of ElectraForSequenceClassification were not initialized from the model checkpoint at classla/bcms-bertic and are newly initialized: ['classifier.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.bias', 'classifier.out_proj.weight']\n",
-      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a7f4d6a07e7544b38dc869d92f60dbf0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/2221 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "\n",
-       "    <div>\n",
-       "      \n",
-       "      <progress value='417' max='417' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [417/417 09:50, Epoch 3/3]\n",
-       "    </div>\n",
-       "    <table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       " <tr style=\"text-align: left;\">\n",
-       "      <th>Step</th>\n",
-       "      <th>Training Loss</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <td>50</td>\n",
-       "      <td>0.998700</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>100</td>\n",
-       "      <td>0.815300</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>150</td>\n",
-       "      <td>0.685500</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>200</td>\n",
-       "      <td>0.542600</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>250</td>\n",
-       "      <td>0.520300</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>300</td>\n",
-       "      <td>0.464000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>350</td>\n",
-       "      <td>0.380800</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>400</td>\n",
-       "      <td>0.328300</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table><p>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Evaluacija na test skupu test-1\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4816fe0de415465ca0d982ff0ddc9f1b",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/653 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Evaluacija: {'eval_loss': 0.8404552340507507, 'eval_accuracy': 0.6906584992343032, 'eval_f1_macro': 0.5999228826553304, 'eval_runtime': 15.1161, 'eval_samples_per_second': 43.199, 'eval_steps_per_second': 1.389, 'epoch': 3.0}\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Confusion Matrix:\n",
-      "[[116  42   7]\n",
-      " [ 86 309  35]\n",
-      " [  7  25  26]]\n",
-      "\n",
-      "Classification Report:\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "    negative       0.56      0.70      0.62       165\n",
-      "     neutral       0.82      0.72      0.77       430\n",
-      "    positive       0.38      0.45      0.41        58\n",
-      "\n",
-      "    accuracy                           0.69       653\n",
-      "   macro avg       0.59      0.62      0.60       653\n",
-      "weighted avg       0.72      0.69      0.70       653\n",
-      "\n",
-      "Predikcije spremljene u results_train_2/predictions_test_1.csv\n",
-      "\n",
-      "Evaluacija na test skupu test-2\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6459394251ff4731938cb87fdba6c9bd",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/741 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Evaluacija: {'eval_loss': 0.5182289481163025, 'eval_accuracy': 0.8083670715249662, 'eval_f1_macro': 0.7534545808339037, 'eval_runtime': 17.475, 'eval_samples_per_second': 42.403, 'eval_steps_per_second': 1.373, 'epoch': 3.0}\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Confusion Matrix:\n",
-      "[[163  44   9]\n",
-      " [ 32 381  18]\n",
-      " [ 10  29  55]]\n",
-      "\n",
-      "Classification Report:\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "    negative       0.80      0.75      0.77       216\n",
-      "     neutral       0.84      0.88      0.86       431\n",
-      "    positive       0.67      0.59      0.62        94\n",
-      "\n",
-      "    accuracy                           0.81       741\n",
-      "   macro avg       0.77      0.74      0.75       741\n",
-      "weighted avg       0.80      0.81      0.81       741\n",
-      "\n",
-      "Predikcije spremljene u results_train_2/predictions_test_2.csv\n",
-      "\n",
-      "Evaluacija na test skupu test-3\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "aed4ce93c6614d97abd44fe642c0b3fa",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/793 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Evaluacija: {'eval_loss': 0.9036539793014526, 'eval_accuracy': 0.7112232030264817, 'eval_f1_macro': 0.7055643128874013, 'eval_runtime': 18.7008, 'eval_samples_per_second': 42.405, 'eval_steps_per_second': 1.337, 'epoch': 3.0}\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/torch/utils/data/dataloader.py:683: UserWarning: 'pin_memory' argument is set as true but not supported on MPS now, then device pinned memory won't be used.\n",
-      "  warnings.warn(warn_msg)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Confusion Matrix:\n",
-      "[[204  53  10]\n",
-      " [ 17 239   7]\n",
-      " [ 13 129 121]]\n",
-      "\n",
-      "Classification Report:\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "    negative       0.87      0.76      0.81       267\n",
-      "     neutral       0.57      0.91      0.70       263\n",
-      "    positive       0.88      0.46      0.60       263\n",
-      "\n",
-      "    accuracy                           0.71       793\n",
-      "   macro avg       0.77      0.71      0.71       793\n",
-      "weighted avg       0.77      0.71      0.71       793\n",
-      "\n",
-      "Predikcije spremljene u results_train_2/predictions_test_3.csv\n"
-     ]
-    }
-   ],
-   "source": [
-    "import pandas as pd\n",
-    "import torch\n",
-    "from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments\n",
-    "from datasets import Dataset\n",
-    "from sklearn.metrics import classification_report, confusion_matrix\n",
-    "\n",
-    "def load_and_prepare_data(train_path):\n",
-    "    df = pd.read_csv(train_path)\n",
-    "    df = df.rename(columns={\"Label\": \"label\"})\n",
-    "    return Dataset.from_pandas(df)\n",
-    "\n",
-    "def load_and_prepare_test_data(test_path):\n",
-    "    df = pd.read_csv(test_path)\n",
-    "    df = df.rename(columns={\"Label\": \"label\"})\n",
-    "    return Dataset.from_pandas(df), df\n",
-    "\n",
-    "def tokenize_dataset(dataset, tokenizer):\n",
-    "    def tokenize_function(examples):\n",
-    "        return tokenizer(examples['Sentence'], padding='max_length', truncation=True, max_length=128)\n",
-    "    tokenized = dataset.map(tokenize_function, batched=True)\n",
-    "    tokenized.set_format(type='torch', columns=['input_ids', 'attention_mask', 'label'])\n",
-    "    return tokenized\n",
-    "\n",
-    "def compute_metrics(eval_pred):\n",
-    "    logits, labels = eval_pred\n",
-    "    preds = torch.argmax(torch.tensor(logits), axis=1).numpy()\n",
-    "    report = classification_report(labels, preds, output_dict=True)\n",
-    "    acc = report['accuracy']\n",
-    "    f1 = report['macro avg']['f1-score']\n",
-    "    return {'accuracy': acc, 'f1_macro': f1}\n",
-    "\n",
-    "def train_and_evaluate(model_name, train_dataset, test_datasets, raw_test_dfs, output_base_dir):\n",
-    "    print(f\"\\n--- Fine-tuning model: {model_name} ---\")\n",
-    "\n",
-    "    tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
-    "    model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=3)\n",
-    "\n",
-    "    tokenized_train = tokenize_dataset(train_dataset, tokenizer)\n",
-    "\n",
-    "    training_args = TrainingArguments(\n",
-    "        output_dir=f\"{output_base_dir}/model\",\n",
-    "        learning_rate=2e-5,\n",
-    "        per_device_train_batch_size=16,\n",
-    "        per_device_eval_batch_size=32,\n",
-    "        num_train_epochs=3,\n",
-    "        weight_decay=0.01,\n",
-    "        load_best_model_at_end=False,\n",
-    "        logging_dir=f\"{output_base_dir}/logs\",\n",
-    "        logging_steps=50,\n",
-    "        save_total_limit=2,\n",
-    "        seed=42,\n",
-    "    )\n",
-    "\n",
-    "    trainer = Trainer(\n",
-    "        model=model,\n",
-    "        args=training_args,\n",
-    "        train_dataset=tokenized_train,\n",
-    "        compute_metrics=compute_metrics,\n",
-    "    )\n",
-    "\n",
-    "    # Treniraj model\n",
-    "    trainer.train()\n",
-    "\n",
-    "    # Spremi model nakon treninga\n",
-    "    trainer.save_model()\n",
-    "\n",
-    "    # Evaluiraj i predvidi na svakom test skupu\n",
-    "    for i, (test_dataset, raw_test_df) in enumerate(zip(test_datasets, raw_test_dfs), start=1):\n",
-    "        print(f\"\\nEvaluacija na test skupu test-{i}\")\n",
-    "\n",
-    "        tokenized_test = tokenize_dataset(test_dataset, tokenizer)\n",
-    "        eval_results = trainer.evaluate(eval_dataset=tokenized_test)\n",
-    "        print(f\"Evaluacija: {eval_results}\")\n",
-    "\n",
-    "        predictions_output = trainer.predict(tokenized_test)\n",
-    "        preds = torch.argmax(torch.tensor(predictions_output.predictions), axis=1).numpy()\n",
-    "        labels = predictions_output.label_ids\n",
-    "\n",
-    "        print(\"Confusion Matrix:\")\n",
-    "        print(confusion_matrix(labels, preds))\n",
-    "\n",
-    "        print(\"\\nClassification Report:\")\n",
-    "        print(classification_report(labels, preds, target_names=['negative', 'neutral', 'positive']))\n",
-    "\n",
-    "        # Spremi predikcije u CSV\n",
-    "        output_df = raw_test_df.copy()\n",
-    "        output_df['predicted_label'] = preds\n",
-    "        output_df['correct'] = output_df['label'] == output_df['predicted_label']\n",
-    "        output_csv = f\"{output_base_dir}/predictions_test_{i}.csv\"\n",
-    "        output_df.to_csv(output_csv, index=False)\n",
-    "        print(f\"Predikcije spremljene u {output_csv}\")\n",
-    "\n",
-    "if __name__ == \"__main__\":\n",
-    "    # Učitaj trening skupove zasebno\n",
-    "    train_files = {\n",
-    "        \"train_combined\": \"TRAIN.csv\",\n",
-    "        \"train_2\": \"train-2.csv\"\n",
-    "    }\n",
-    "\n",
-    "    # Učitaj test skupove\n",
-    "    test_files = [\"test-1.csv\", \"test-2.csv\", \"test-3.csv\"]\n",
-    "    test_datasets = []\n",
-    "    raw_test_dfs = []\n",
-    "    for f in test_files:\n",
-    "        ds, df = load_and_prepare_test_data(f)\n",
-    "        test_datasets.append(ds)\n",
-    "        raw_test_dfs.append(df)\n",
-    "\n",
-    "    model_name = \"classla/bcms-bertic\"\n",
-    "\n",
-    "    # Za svaki trening skup treniraj i evaluiraj model na sva tri testa\n",
-    "    for train_name, train_path in train_files.items():\n",
-    "        print(f\"\\n\\n=== Treniranje i evaluacija za trening skup: {train_name} ===\")\n",
-    "        train_dataset = load_and_prepare_data(train_path)\n",
-    "        output_dir = f\"results_{train_name}\"\n",
-    "        train_and_evaluate(model_name, train_dataset, test_datasets, raw_test_dfs, output_dir)\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.13.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}