"
+ ],
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ "
\n",
+ " [18336/18336 43:51, Epoch 3/3]\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | Epoch | \n",
+ " Training Loss | \n",
+ " Validation Loss | \n",
+ " Accuracy | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 1 | \n",
+ " 0.671300 | \n",
+ " 0.398400 | \n",
+ " 0.861502 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 0.161700 | \n",
+ " 0.342772 | \n",
+ " 0.917948 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 0.223200 | \n",
+ " 0.307898 | \n",
+ " 0.934391 | \n",
+ "
\n",
+ " \n",
+ "
"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "TrainOutput(global_step=18336, training_loss=0.35104223199146656, metrics={'train_runtime': 2634.5925, 'train_samples_per_second': 55.678, 'train_steps_per_second': 6.96, 'total_flos': 4731334255614960.0, 'train_loss': 0.35104223199146656, 'epoch': 3.0})"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 23
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#export\n",
+ "model.save_pretrained(\"./fine_tuned_sentiment_model\")\n",
+ "tokenizer.save_pretrained(\"./fine_tuned_sentiment_model\")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "_yqjZpPdPTDf",
+ "outputId": "f9ceeed8-6f91-48f0-cdf8-64d40ed69ac7"
+ },
+ "execution_count": 24,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "('./fine_tuned_sentiment_model/tokenizer_config.json',\n",
+ " './fine_tuned_sentiment_model/special_tokens_map.json',\n",
+ " './fine_tuned_sentiment_model/vocab.json',\n",
+ " './fine_tuned_sentiment_model/merges.txt',\n",
+ " './fine_tuned_sentiment_model/added_tokens.json',\n",
+ " './fine_tuned_sentiment_model/tokenizer.json')"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 24
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#check performance\n",
+ "from transformers import pipeline\n",
+ "\n",
+ "# Load the fine-tuned model\n",
+ "classifier = pipeline(\"sentiment-analysis\", model=\"./fine_tuned_sentiment_model\", tokenizer=tokenizer)\n",
+ "\n",
+ "# Test with a new sentence\n",
+ "result = classifier(\"This product is okay!\")\n",
+ "print(result)\n"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "7aVmYPaqPafd",
+ "outputId": "93000e2d-5589-486f-e369-1565d4065964"
+ },
+ "execution_count": 28,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Device set to use cuda:0\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "[{'label': 'positive', 'score': 0.9967034459114075}]\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#Code taken from Hugging Face\n",
+ "\n",
+ "from transformers import AutoModelForSequenceClassification\n",
+ "from transformers import TFAutoModelForSequenceClassification\n",
+ "from transformers import AutoTokenizer, AutoConfig\n",
+ "import numpy as np\n",
+ "from scipy.special import softmax\n",
+ "# Preprocess text (username and link placeholders)\n",
+ "def preprocess(text):\n",
+ " new_text = []\n",
+ " for t in text.split(\" \"):\n",
+ " t = '@user' if t.startswith('@') and len(t) > 1 else t\n",
+ " t = 'http' if t.startswith('http') else t\n",
+ " new_text.append(t)\n",
+ " return \" \".join(new_text)\n",
+ "MODEL = \"./fine_tuned_sentiment_model\"\n",
+ "# PT\n",
+ "model = AutoModelForSequenceClassification.from_pretrained(MODEL)\n",
+ "#model.save_pretrained(MODEL)\n",
+ "text = \"This product is good\"\n",
+ "text = preprocess(text)\n",
+ "encoded_input = tokenizer(text, return_tensors='pt')\n",
+ "output = model(**encoded_input)\n",
+ "scores = output[0][0].detach().numpy()\n",
+ "scores = softmax(scores)\n",
+ "# # TF\n",
+ "# model = TFAutoModelForSequenceClassification.from_pretrained(MODEL)\n",
+ "# model.save_pretrained(MODEL)\n",
+ "# text = \"Covid cases are increasing fast!\"\n",
+ "# encoded_input = tokenizer(text, return_tensors='tf')\n",
+ "# output = model(encoded_input)\n",
+ "# scores = output[0][0].numpy()\n",
+ "# scores = softmax(scores)\n",
+ "# Print labels and scores\n",
+ "ranking = np.argsort(scores)\n",
+ "ranking = ranking[::-1]\n",
+ "for i in range(scores.shape[0]):\n",
+ " l = config.id2label[ranking[i]]\n",
+ " s = scores[ranking[i]]\n",
+ " print(f\"{i+1}) {l} {np.round(float(s), 4)}\")\n"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "xI9tjyKtPj3d",
+ "outputId": "ee67abd1-898f-4920-fd4b-a67ea48bcd6f"
+ },
+ "execution_count": 32,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "1) positive 0.9989\n",
+ "2) negative 0.0008\n",
+ "3) neutral 0.0003\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from google.colab import files\n",
+ "import shutil\n",
+ "\n",
+ "# Zip the folder\n",
+ "shutil.make_archive(\"./fine_tuned_sentiment_model\", 'zip', \"./fine_tuned_sentiment_model\")\n"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 35
+ },
+ "id": "pnYmuqzrRCXf",
+ "outputId": "d064f50f-2b20-42f8-b501-41d4fbea214d"
+ },
+ "execution_count": 39,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "'/content/fine_tuned_sentiment_model.zip'"
+ ],
+ "application/vnd.google.colaboratory.intrinsic+json": {
+ "type": "string"
+ }
+ },
+ "metadata": {},
+ "execution_count": 39
+ }
+ ]
+ }
+ ]
+}
\ No newline at end of file