Update t5_training.ipynb

t5_training.ipynb

@@ -25,6 +25,7 @@
     "from transformers import T5ForConditionalGeneration, T5Tokenizer\n",
     "from datasets import Dataset\n",
     "from transformers import Trainer, TrainingArguments\n",
+    "import json\n",
     "\n",
     "# Load pre-trained FLAN-T5 model and tokenizer\n",
     "model_name = \"google/flan-t5-large\"  # FLAN-T5 Base Model\n",
@@ -32,14 +33,7 @@
     "model = T5ForConditionalGeneration.from_pretrained(model_name)\n",
     "\n",
     "# Example input-output pair for fine-tuning\n",
-    "data = {\n",
-    "    \"input_text\": [\n",
-    "        \"What are the key differences between classification and regression tasks in supervised learning, and how do you determine which algorithm to use for a specific problem? e How does clustering differ from dimensionality reduction, and can you provide real-world examples of where each is applied?\"\n",
-    "    ],\n",
-    "    \"output_text\": [\n",
-    "        \"@ What are the key differences between classification and regression tasks in supervised learning, and how do you determine which algorithm to use for a specific problem? @ How does clustering differ from dimensionality reduction, and can you provide real-world examples of where each is applied?\"\n",
-    "    ]\n",
-    "}\n",
+    "data = json.load('t5train.json')\n",
     "\n",
     "# Convert the data to a Hugging Face dataset\n",
     "dataset = Dataset.from_dict(data)\n",