Update app.py

app.py

@@ -32,8 +32,8 @@ train_texts, val_texts, train_labels, val_labels = train_test_split(
 tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
 
 # Tokenize the conversations
-train_encodings = tokenizer(train_texts, truncation=True, padding=True, max_length=512)
-val_encodings = tokenizer(val_texts, truncation=True, padding=True, max_length=512)
+train_encodings = tokenizer(train_texts, truncation=True, padding=True, max_length=128)
+val_encodings = tokenizer(val_texts, truncation=True, padding=True, max_length=128)
 
 # Create PyTorch datasets
 train_dataset = Dataset.from_dict({
@@ -59,8 +59,8 @@ training_args = TrainingArguments(
     eval_strategy='epoch',  # Evaluate at the end of each epoch
     save_strategy='epoch',       # Save model at the end of each epoch
     learning_rate=2e-5,
-    per_device_train_batch_size=8,
-    per_device_eval_batch_size=8,
+    per_device_train_batch_size=12,
+    per_device_eval_batch_size=12,
     num_train_epochs=3,
     weight_decay=0.01,
     logging_dir='./logs',