updated text class paragraph

app.py

@@ -58,7 +58,7 @@ with gr.Blocks(
                             <p><b>Model:</b> Tiny Bert <br>
                             <b>Dataset:</b> IMDB Movie review dataset <br>
                             <b>NLP Task:</b> Text Classification</p>
-                            <p>I don’t know why but I just enjoy doing this. Maybe it’s my way of dealing with stress or something but I just do it about once every week. Generally I’ll carry around a sack and creep around in a sort of crouch-walking position making goblin noises, then I’ll walk around my house and pick up various different “trinkets” and put them in my bag while saying stuff like “I’ll be having that” and laughing maniacally in my goblin voice (“trinkets” can include anything from stuff I find on the ground to cutlery or other utensils). The other day I was talking with my neighbours and they mentioned hearing weird noises like what I wrote about and I was just internally screaming the entire conversation.</p>
+                            <p>Text classification is an NLP task that focuses on automatically ascribing a predefined category or labels to an input prompt. In this demonstration the tiny bert model has been used to classify the text on the basis of sentiment analysis, where the labels (negative and positive) will indicate the emotional state expressed by the input prompt. The tiny bert model was chosen as in its base state its ability to perform sentiment analysis is quite poor, displayed by the untrained model, which often fails to correctly ascribe the label to the sentiment. The models were trained on the IMDB dataset which includes a large number of sentiment pairs pulled from IMDB movie reviews. We can see that when training is performed over [XX] of epochs we see an increase in X% of training time for the LoRA trained model.</p>
                             """)
                 
             with gr.Column(scale=0.3,variant="panel"):