Update fine_tuning.ipynb

Author: bansalkanav

Module 9 - GenAI (LLMs and Prompt Engineering)/3. HuggingFace Tutorial Series (Handson)/4. Fine Tuning/fine_tuning.ipynb

@@ -9,20 +9,8 @@
  "\n",
  "Reference: \n",
  "https://huggingface.co/docs/transformers/training#train-a-tensorflow-model-with-keras \n",
- "https://huggingface.co/learn/nlp-course/chapter3/3?fw=tf\n",
  "\n",
  "\n",
- "https://learnopencv.com/fine-tuning-bert/ \n",
- "\n",
- "\n",
- "\n",
- "\n",
- "https://www.youtube.com/watch?v=RgpANRh44ao \n",
- "Notebook Link: https://www.kaggle.com/code/preatcher/emotion-detection-by-using-bert\n",
- "Github App Link: https://github.com/Abhishekjl/Sentiment-analyis-BERT-Trained-\n",
- "\n",
- "There are significant benefits to using a pretrained model. It reduces computation costs, your carbon footprint, and allows you to use state-of-the-art models without having to train one from scratch. 🤗 Transformers provides access to thousands of pretrained models for a wide range of tasks. When you use a pretrained model, you train it on a dataset specific to your task. This is known as fine-tuning, an incredibly powerful training technique. \n",
- "\n",
  "**Steps**\n",
  "1. Load the data\n",
  "2. Apply tokenization to the dataset\n",
@@ -31,7 +19,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 2,
+ "execution_count": 1,
  "id": "0c5291d1-83ad-4e36-a3b9-0aeb161118fc",
  "metadata": {},
  "outputs": [
@@ -51,7 +39,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 1,
+ "execution_count": 2,
  "id": "aba7b9e3-d558-45a1-9b03-ef697e243cba",
  "metadata": {},
  "outputs": [
@@ -61,34 +49,17 @@
  "text": [
  "2.16.1\n"
  ]
- },
- {
- "ename": "AttributeError",
- "evalue": "module 'keras._tf_keras.keras' has no attribute '__version__'",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[1;32mIn[1], line 8\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m keras\n\u001b[0;32m 6\u001b[0m \u001b[38;5;28mprint\u001b[39m(tf\u001b[38;5;241m.\u001b[39m__version__)\n\u001b[1;32m----> 8\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[43mkeras\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__version__\u001b[49m)\n",
- "File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\tensorflow\\python\\util\\lazy_loader.py:211\u001b[0m, in \u001b[0;36mKerasLazyLoader.__getattr__\u001b[1;34m(self, item)\u001b[0m\n\u001b[0;32m 207\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m(\n\u001b[0;32m 208\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mitem\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m` is not available with Keras 3.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 209\u001b[0m )\n\u001b[0;32m 210\u001b[0m module \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_load()\n\u001b[1;32m--> 211\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mmodule\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mitem\u001b[49m\u001b[43m)\u001b[49m\n",
- "\u001b[1;31mAttributeError\u001b[0m: module 'keras._tf_keras.keras' has no attribute '__version__'"
- ]
  }
  ],
  "source": [
- "# TensorFlow and tf.keras\n",
- "\n",
  "import tensorflow as tf\n",
- "from tensorflow import keras\n",
- "\n",
- "print(tf.__version__)\n",
  "\n",
- "print(keras.__version__)"
+ "print(tf.__version__)"
  ]
  },
  {
  "cell_type": "code",
- "execution_count": 1,
+ "execution_count": 3,
  "id": "a9c3a86f-dd64-48a6-b6dd-6013d2ae9412",
  "metadata": {},
  "outputs": [],
@@ -98,7 +69,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 2,
+ "execution_count": 4,
  "id": "a8733911-db8b-40bf-82e3-2a052515d1f5",
  "metadata": {},
  "outputs": [
@@ -198,7 +169,7 @@
  "4 NEW YORK -- Indecision marked the dollar's ton... "
  ]
  },
- "execution_count": 2,
+ "execution_count": 4,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -211,7 +182,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 3,
+ "execution_count": 5,
  "id": "67609b5a-6160-4c9b-9ff4-3e2306372e19",
  "metadata": {},
  "outputs": [
@@ -221,7 +192,7 @@
  "(8000, 5)"
  ]
  },
- "execution_count": 3,
+ "execution_count": 5,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -232,7 +203,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 4,
+ "execution_count": 6,
  "id": "4c109e2e-d967-43f7-812e-18acbe145acb",
  "metadata": {},
  "outputs": [
@@ -246,7 +217,7 @@
  "Name: proportion, dtype: float64"
  ]
  },
- "execution_count": 4,
+ "execution_count": 6,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -257,7 +228,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 5,
+ "execution_count": 7,
  "id": "f924c3d2-75bd-44d4-825f-8a37d1108f84",
  "metadata": {},
  "outputs": [
@@ -270,7 +241,7 @@
  "Name: proportion, dtype: float64"
  ]
  },
- "execution_count": 5,
+ "execution_count": 7,
  "metadata": {},
  "output_type": "execute_result"
  }
@@ -285,7 +256,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 9,
+ "execution_count": 8,
  "id": "efa3c67b-8201-44eb-8506-e094e7dc07db",
  "metadata": {},
  "outputs": [],
@@ -298,7 +269,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 10,
+ "execution_count": 9,
  "id": "ab2914ad-44ca-47cb-98ee-4227b6a31097",
  "metadata": {},
  "outputs": [],
@@ -311,7 +282,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 12,
+ "execution_count": 10,
  "id": "d9e3a194-b9c9-4041-90f9-cfd43fff9f4b",
  "metadata": {},
  "outputs": [
@@ -337,76 +308,10 @@
  },
  {
  "cell_type": "code",
- "execution_count": 13,
+ "execution_count": 11,
  "id": "a9272140-12e4-4c8a-9307-cbd135bfc15b",
  "metadata": {},
- "outputs": [
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "e3fb92a246514e888ec7379e1da18a62",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "tokenizer_config.json: 0%| | 0.00/28.0 [00:00<?, ?B/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "C:\\Users\\DELL\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\huggingface_hub\\file_download.py:149: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\DELL\\.cache\\huggingface\\hub\\models--distilbert-base-uncased. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
- "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
- " warnings.warn(message)\n"
- ]
- },
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "70dfac598d3f48e0a494c914c6150693",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "config.json: 0%| | 0.00/483 [00:00<?, ?B/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "b861ceae22df4de399324abee8cee86a",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "vocab.txt: 0%| | 0.00/232k [00:00<?, ?B/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "0e910174400d4409a950e6069f2f724b",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "tokenizer.json: 0%| | 0.00/466k [00:00<?, ?B/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
  "source": [
  "from transformers import AutoTokenizer\n",
  "\n",