Update app.py

app.py

@@ -118,9 +118,9 @@ def train_function_no_sweeps(base_model_path):   #, train_dataset, test_dataset)
     base_model = get_peft_model(base_model, peft_config)
 
     # Use the accelerator
-    base_model = Accelerator.prepare(base_model)
-    train_dataset = Accelerator.prepare(train_dataset)
-    test_dataset = Accelerator.prepare(test_dataset)
+    base_model = accelerator.prepare(base_model)
+    train_dataset = accelerator.prepare(train_dataset)
+    test_dataset = accelerator.prepare(test_dataset)
 
     timestamp = datetime.now().strftime('%Y-%m-%d_%H-%M-%S')
 
@@ -205,7 +205,7 @@ test_labels = truncate_labels(test_labels, max_sequence_length)
 train_dataset = Dataset.from_dict({k: v for k, v in train_tokenized.items()}).add_column("labels", train_labels)
 test_dataset = Dataset.from_dict({k: v for k, v in test_tokenized.items()}).add_column("labels", test_labels)
 
-'''
+
 # Compute Class Weights
 classes = [0, 1]  
 flat_train_labels = [label for sublist in train_labels for label in sublist]
@@ -213,6 +213,7 @@ class_weights = compute_class_weight(class_weight='balanced', classes=classes, y
 accelerator = Accelerator()
 class_weights = torch.tensor(class_weights, dtype=torch.float32).to(accelerator.device)
 
+'''
 # inference
 # Path to the saved LoRA model
 model_path = "AmelieSchreiber/esm2_t12_35M_lora_binding_sites_v2_cp3"