Update app.py

app.py

@@ -71,18 +71,10 @@ if (should_train_model=='1'): #train model
     bias_non_fleet = 1.0
     epochs_to_run = 15
 
-    #file_path_train = train_file + ".csv"
-    #file_path_test = test_file + ".csv"
-
-    # Read the CSV files into pandas DataFrames they will later by converted to DataTables and used to train and evaluate the model
-    #file_train_df = pd.read_csv(file_path_train)
-    #file_test_df = pd.read_csv(file_path_test)
-
     file_path_train = train_file + ".csv"
     file_path_test = test_file + ".csv"
 
     # Read the CSV files into pandas DataFrames they will later by converted to DataTables and used to train and evaluate the model
-    #file_train_df = pd.read_csv(file_path_train)
     
     file_train_df = fetch_and_update_training_data(file_path_train)
     file_test_df = pd.read_csv(file_path_test)
@@ -181,7 +173,6 @@ if (should_train_model=='1'): #train model
         accuracy = (preds == labels).astype(float).mean()
         return {"accuracy": accuracy}
 
-
     training_args = TrainingArguments(
         output_dir='./results',
         num_train_epochs=epochs_to_run,
@@ -195,10 +186,6 @@ if (should_train_model=='1'): #train model
         evaluation_strategy="epoch",
     )
 
-    # notice the bias_non_float in next line (it is given a value at top of code)
-    # class_weights = torch.tensor([1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,bias_non_fleet,1.0,1.0])  # Replace with your actual class weights
-    # class_weights = class_weights.to('cuda' if torch.cuda.is_available() else 'cpu')
-
     # This is needed b/c loss_fn is swapped out in order to use weighted loss
     # Any class weights that are not equal to one will make the model more (if greater than one) or less (if less than one)sensitive to given label
     class CustomTrainer(Trainer):
@@ -222,14 +209,6 @@ if (should_train_model=='1'): #train model
         tokenizer=tokenizer
     )
 
-    # Train the model and set timer to measure the training time
-    start_time = time.time()
-    trainer.train()
-    end_time = time.time()
-    execution_time = end_time - start_time
-
-    print(f"Execution Time: {execution_time:.2f} seconds")
-
     # send validation prompts through the model - will be used in error-analysis matrix below
     preds_output = trainer.predict(emotions_encoded["validation"])    
     
@@ -311,14 +290,12 @@ if (should_train_model=='1'): #train model
     create_repo(repo_id=repo_name, token=api_token, exist_ok=True)
 
     # Upload the model and tokenizer to the Hugging Face repository
-    
     upload_folder(
         folder_path=f"{model_save_path}",
         path_in_repo=f"{model_save_path}",
         repo_id=repo_name,
         token=api_token,
-        commit_message="Push model",
-        #overwrite=True  # Force overwrite existing files
+        commit_message="Push model and tokenizer",
     )
         
 else: