Update app.py

app.py

@@ -5,16 +5,21 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingA
 from transformers import DataCollatorForLanguageModeling
 import torch
 from huggingface_hub import Repository, HfFolder
+import subprocess
 
 # Authenticate Hugging Face Hub
 hf_token = st.secrets["HF_TOKEN"]  # Store your token in the Hugging Face Space Secrets
 HfFolder.save_token(hf_token)
 
-import os
-
 # Set Git user identity
-os.system('git config user.email "[email protected]"')
-os.system('git config user.name "Nilesh"')
+def set_git_config():
+    try:
+        subprocess.run(['git', 'config', 'user.email', '[email protected]'], check=True)
+        subprocess.run(['git', 'config', 'user.name', 'Nilesh'], check=True)
+    except subprocess.CalledProcessError as e:
+        st.error(f"Git configuration error: {str(e)}")
+
+set_git_config()
 
 @st.cache_data
 def load_data(file_path):
@@ -64,6 +69,16 @@ def create_dataset(data, tokenizer, max_length):
         })
     return inputs
 
+class SimpleDataset(torch.utils.data.Dataset):
+    def __init__(self, encodings):
+        self.encodings = encodings
+
+    def __getitem__(self, idx):
+        return {key: val[idx] for key, val in self.encodings[idx].items()}
+
+    def __len__(self):
+        return len(self.encodings)
+
 def main():
     st.title("Model Training with Streamlit")
 
@@ -94,17 +109,6 @@ def main():
     st.write("Tokenizing dataset...")
     tokenized_dataset = create_dataset(data, tokenizer, max_length)
 
-    # Convert tokenized_dataset to a torch Dataset
-    class SimpleDataset(torch.utils.data.Dataset):
-        def __init__(self, encodings):
-            self.encodings = encodings
-
-        def __getitem__(self, idx):
-            return {key: val[idx] for key, val in self.encodings[idx].items()}
-
-        def __len__(self):
-            return len(self.encodings)
-
     dataset = SimpleDataset(tokenized_dataset)
 
     # Define training arguments