Update of Jupyter Notebook

Poetry_Fusion_using_Llama_3.2.ipynb

@@ -55,9 +55,7 @@
         "\n",
         "We will use a selected dataset that includes various poet styles. This dataset will be preprocessed \n",
         "to highlight stylistic characteristics for model fine-tuning, focusing on continuous and meaningful \n",
-        "poetic text for optimal style fusion.\n",
-        "\n",
-        "*Note: Ensure the dataset is accessible and formatted to match model input requirements.*\n"
+        "poetic text for optimal style fusion."
       ]
     },
     {
@@ -174,7 +172,7 @@
         "id": "xNqIYtQcUBSm"
       },
       "source": [
-        "Let's also load the tokenizer below"
+        "The tokenizer is loaded below."
       ]
     },
     {
@@ -328,7 +326,7 @@
         "id": "aTBJVE4PaJwK"
       },
       "source": [
-        "Here we will use the [`SFTTrainer` from TRL library](https://huggingface.co/docs/trl/main/en/sft_trainer) that gives a wrapper around transformers `Trainer` to easily fine-tune models on instruction based datasets using PEFT adapters. Let's first load the training arguments below. We choose sepcific arguments for our usecase."
+        "Here we will use the [`SFTTrainer` from TRL library](https://huggingface.co/docs/trl/main/en/sft_trainer) that gives a wrapper around transformers `Trainer` to easily fine-tune models on instruction based datasets using PEFT adapters. The training arguments are loaded below. We choose sepcific arguments for our usecase."
       ]
     },
     {
@@ -483,7 +481,7 @@
         "id": "JjvisllacNZM"
       },
       "source": [
-        "Now let's train the model! Simply call `trainer.train()`"
+        "Now let's train the model! Simply call `trainer.train()`. It will require wandb.ai API key."
       ]
     },
     {