Update app.py

app.py

@@ -391,7 +391,6 @@
 
 # if __name__ == "__main__":
 #     main()
-
 import streamlit as st
 import matplotlib.pyplot as plt
 import torch
@@ -433,7 +432,8 @@ def load_data(dataset_name, train_size=20, test_size=20, num_clients=2, use_utf8
         tokenizer = T5Tokenizer.from_pretrained(model_name)
 
         def utf8_encode_function(examples):
-            examples["input_ids"] = [tokenizer(text.encode('utf-8'), return_tensors="pt")["input_ids"].squeeze().tolist() for text in examples["text"]]
+            encoded_texts = [text.encode('utf-8') for text in examples["text"]]
+            examples["input_ids"] = [tokenizer(list(encoded_text), return_tensors="pt", padding='max_length', truncation=True, max_length=512)["input_ids"].squeeze().tolist() for encoded_text in encoded_texts]
             return examples
 
         tokenized_datasets = raw_datasets.map(utf8_encode_function, batched=True)
@@ -611,7 +611,6 @@ def plot_metrics(rounds, clients, memory_usage):
         for msg in debug_messages:
             st.write(msg)
 
-        # Placeholder for actual loss and accuracy values, assuming they're included in the messages
         losses = [float(re.search(r'loss=([\d\.]+)', msg).group(1)) for msg in debug_messages if 'loss=' in msg]
         accuracies = [float(re.search(r'accuracy=([\d\.]+)', msg).group(1)) for msg in debug_messages if 'accuracy=' in msg]