{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "0N_aoZZc8idM",
"outputId": "707308cb-1c0f-4563-97ec-82a1b7e5f47c"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: transformers in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (4.49.0)\n",
"Requirement already satisfied: seaborn in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (0.13.2)\n",
"Requirement already satisfied: accelerate in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (1.4.0)\n",
"Requirement already satisfied: datasets in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (3.3.2)\n",
"Requirement already satisfied: filelock in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (3.17.0)\n",
"Requirement already satisfied: huggingface-hub<1.0,>=0.26.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (0.29.1)\n",
"Requirement already satisfied: numpy>=1.17 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (1.26.4)\n",
"Requirement already satisfied: packaging>=20.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (24.2)\n",
"Requirement already satisfied: pyyaml>=5.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (6.0.2)\n",
"Requirement already satisfied: regex!=2019.12.17 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (2024.11.6)\n",
"Requirement already satisfied: requests in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (2.32.3)\n",
"Requirement already satisfied: tokenizers<0.22,>=0.21 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (0.21.0)\n",
"Requirement already satisfied: safetensors>=0.4.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (0.5.3)\n",
"Requirement already satisfied: tqdm>=4.27 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from transformers) (4.67.1)\n",
"Requirement already satisfied: pandas>=1.2 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from seaborn) (2.1.4)\n",
"Requirement already satisfied: matplotlib!=3.6.1,>=3.4 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from seaborn) (3.8.2)\n",
"Requirement already satisfied: psutil in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from accelerate) (7.0.0)\n",
"Requirement already satisfied: torch>=2.0.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from accelerate) (2.2.1+cu121)\n",
"Requirement already satisfied: pyarrow>=15.0.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from datasets) (19.0.1)\n",
"Requirement already satisfied: dill<0.3.9,>=0.3.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from datasets) (0.3.8)\n",
"Requirement already satisfied: xxhash in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from datasets) (3.5.0)\n",
"Requirement already satisfied: multiprocess<0.70.17 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from datasets) (0.70.16)\n",
"Requirement already satisfied: fsspec<=2024.12.0,>=2023.1.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from fsspec[http]<=2024.12.0,>=2023.1.0->datasets) (2024.12.0)\n",
"Requirement already satisfied: aiohttp in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from datasets) (3.11.13)\n",
"Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from aiohttp->datasets) (2.4.6)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from aiohttp->datasets) (1.3.2)\n",
"Requirement already satisfied: async-timeout<6.0,>=4.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from aiohttp->datasets) (5.0.1)\n",
"Requirement already satisfied: attrs>=17.3.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from aiohttp->datasets) (25.1.0)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from aiohttp->datasets) (1.5.0)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from aiohttp->datasets) (6.1.0)\n",
"Requirement already satisfied: propcache>=0.2.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from aiohttp->datasets) (0.3.0)\n",
"Requirement already satisfied: yarl<2.0,>=1.17.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from aiohttp->datasets) (1.18.3)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from huggingface-hub<1.0,>=0.26.0->transformers) (4.12.2)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.3.1)\n",
"Requirement already satisfied: cycler>=0.10 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (4.56.0)\n",
"Requirement already satisfied: kiwisolver>=1.3.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (1.4.8)\n",
"Requirement already satisfied: pillow>=8 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (11.1.0)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (3.2.1)\n",
"Requirement already satisfied: python-dateutil>=2.7 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (2.9.0.post0)\n",
"Requirement already satisfied: pytz>=2020.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from pandas>=1.2->seaborn) (2025.1)\n",
"Requirement already satisfied: tzdata>=2022.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from pandas>=1.2->seaborn) (2025.1)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from requests->transformers) (3.4.1)\n",
"Requirement already satisfied: idna<4,>=2.5 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from requests->transformers) (3.10)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from requests->transformers) (2.3.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from requests->transformers) (2025.1.31)\n",
"Requirement already satisfied: sympy in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (1.13.3)\n",
"Requirement already satisfied: networkx in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (3.4.2)\n",
"Requirement already satisfied: jinja2 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (3.1.5)\n",
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (12.1.105)\n",
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (12.1.105)\n",
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (12.1.105)\n",
"Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (8.9.2.26)\n",
"Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (12.1.3.1)\n",
"Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (11.0.2.54)\n",
"Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (10.3.2.106)\n",
"Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (11.4.5.107)\n",
"Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (12.1.0.106)\n",
"Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (2.19.3)\n",
"Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (12.1.105)\n",
"Requirement already satisfied: triton==2.2.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from torch>=2.0.0->accelerate) (2.2.0)\n",
"Requirement already satisfied: nvidia-nvjitlink-cu12 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=2.0.0->accelerate) (12.8.61)\n",
"Requirement already satisfied: six>=1.5 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib!=3.6.1,>=3.4->seaborn) (1.17.0)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from jinja2->torch>=2.0.0->accelerate) (3.0.2)\n",
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /system/conda/miniconda3/envs/cloudspace/lib/python3.10/site-packages (from sympy->torch>=2.0.0->accelerate) (1.3.0)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"pip install transformers seaborn accelerate datasets "
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"id": "cw0_yg1N8idU"
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"from transformers import DistilBertTokenizer, DistilBertForSequenceClassification, Trainer, TrainingArguments\n",
"import torch\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"id": "TZsG_m5A8idW",
"outputId": "058be4b2-4846-4bb5-803a-908991d3406c"
},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
label
\n",
"
text
\n",
"
label_text
\n",
"
\n",
" \n",
" \n",
"
\n",
"
0
\n",
"
0
\n",
"
I got 'new' tires from them and within two wee...
\n",
"
1 star
\n",
"
\n",
"
\n",
"
1
\n",
"
0
\n",
"
Don't waste your time. We had two different p...
\n",
"
1 star
\n",
"
\n",
"
\n",
"
2
\n",
"
0
\n",
"
All I can say is the worst! We were the only 2...
\n",
"
1 star
\n",
"
\n",
"
\n",
"
3
\n",
"
0
\n",
"
I have been to this restaurant twice and was d...
\n",
"
1 star
\n",
"
\n",
"
\n",
"
4
\n",
"
0
\n",
"
Food was NOT GOOD at all! My husband & I ate h...
\n",
"
1 star
\n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" label text label_text\n",
"0 0 I got 'new' tires from them and within two wee... 1 star\n",
"1 0 Don't waste your time. We had two different p... 1 star\n",
"2 0 All I can say is the worst! We were the only 2... 1 star\n",
"3 0 I have been to this restaurant twice and was d... 1 star\n",
"4 0 Food was NOT GOOD at all! My husband & I ate h... 1 star"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"splits = {'train': 'train.jsonl', 'test': 'test.jsonl'}\n",
"# df= pd.read_json(\"hf://datasets/SetFit/yelp_review_full/\"+ splits[\"train\"],lines=True)\n",
"df= pd.read_json(\"hf://datasets/SetFit/yelp_review_full/\"+ splits[\"test\"],lines=True)\n",
"# df = pd.concat([train, test])\n",
"# Display the first few rows of the dataset\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "wSPmd46I8idX"
},
"outputs": [],
"source": [
"df['count'] = df['text'].apply(lambda x: len(x.split()))"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"id": "trUolmbT8idY",
"outputId": "250e9be2-1235-4cb6-dc33-193aba44f8ce"
},
"outputs": [
{
"data": {
"text/plain": [
"
\n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"{'eval_loss': 0.830126166343689,\n",
" 'eval_runtime': 123.0163,\n",
" 'eval_samples_per_second': 81.29,\n",
" 'eval_steps_per_second': 10.161,\n",
" 'epoch': 1.0}"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"trainer.evaluate()"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"id": "_BJ2qyEg8idh",
"outputId": "60c46065-7b7c-4b9d-9be9-57c04eeafef6"
},
"outputs": [
{
"data": {
"text/plain": [
"('./distlbert_fine_tuned_model/tokenizer_config.json',\n",
" './distlbert_fine_tuned_model/special_tokens_map.json',\n",
" './distlbert_fine_tuned_model/vocab.txt',\n",
" './distlbert_fine_tuned_model/added_tokens.json')"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"save_directory = \"./distlbert_fine_tuned_model\"\n",
"\n",
"model.save_pretrained(save_directory)\n",
"\n",
"tokenizer.save_pretrained(save_directory)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'I got \\'new\\' tires from them and within two weeks got a flat. I took my car to a local mechanic to see if i could get the hole patched, but they said the reason I had a flat was because the previous patch had blown - WAIT, WHAT? I just got the tire and never needed to have it patched? This was supposed to be a new tire. \\\\nI took the tire over to Flynn\\'s and they told me that someone punctured my tire, then tried to patch it. So there are resentful tire slashers? I find that very unlikely. After arguing with the guy and telling him that his logic was far fetched he said he\\'d give me a new tire \\\\\"this time\\\\\". \\\\nI will never go back to Flynn\\'s b/c of the way this guy treated me and the simple fact that they gave me a used tire!'"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['text'][110]"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"3"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['label'][1100]"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"id": "KG1FaZ6B8idh",
"outputId": "00562409-91da-4c4c-e917-97a6de141297"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Predicted Category: 0\n"
]
}
],
"source": [
"def predict_class(text):\n",
" inputs = tokenizer(text, return_tensors=\"pt\", truncation=True, padding=True, max_length=512).to(\"cuda\")\n",
"\n",
" with torch.no_grad():\n",
" outputs = model(**inputs)\n",
"\n",
" prediction_value = torch.argmax(outputs.logits, dim=1).item()\n",
"\n",
" \n",
" return f\"Predicted Category: {prediction_value}\"\n",
"\n",
"# Example usage (do not run)the browser's clipboard. Please make sure you have granted access for this website to\n",
"print(predict_class(df['text'][0]))\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "IaHrvFXe8idi",
"outputId": "fe7af587-33f4-4e4f-9ab4-59a2218f9c24"
},
"outputs": [],
"source": [
"import shutil\n",
"\n",
"# Specify the folder to be zipped\n",
"folder_path = \"distilbert_fine_tuned_model\" # Replace with your actual folder name\n",
"zip_name = \"distilbert_fine_tuned_model.zip\" # Desired zip file name\n",
"\n",
"# Create a zip archive\n",
"shutil.make_archive(zip_name.replace('.zip', ''), 'zip', folder_path)\n",
"\n",
"print(f\"Folder '{folder_path}' has been zipped as '{zip_name}'.\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"colab": {
"provenance": []
},
"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": "3.10.10"
}
},
"nbformat": 4,
"nbformat_minor": 4
}