deve

app.py

@@ -166,7 +166,6 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
                 
             elif os.access(f'/data/{hub_id.strip()}_validation_dataset', os.R_OK):                    
                 dataset = load_dataset(dataset_name.strip())
-                dataset['train'] = dataset['train'].select(range(15000))
                 train_size = len(dataset['train'])
                 third_size = train_size // 3
                 del dataset['test']
@@ -183,9 +182,7 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
             
                                            
             if os.access(f'/data/{hub_id.strip()}_train_dataset', os.R_OK) and not os.access(f'/data/{hub_id.strip()}_train_dataset3', os.R_OK):
-                dataset = load_dataset(dataset_name.strip())
-                dataset['train'] = dataset['train'].select(range(15000))
-                dataset['validation'] = dataset['validation'].select(range(2000))             
+                dataset = load_dataset(dataset_name.strip())           
                 train_size = len(dataset['train'])
                 third_size = train_size // 3                
                 second_third = dataset['train'].select(range(third_size, third_size*2))
@@ -201,7 +198,6 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
         except Exception as e:
             print(f"An error occurred: {str(e)}, TB: {traceback.format_exc()}")
             dataset = load_dataset(dataset_name.strip())
-            dataset['train'] = dataset['train'].select(range(15000))
             train_size = len(dataset['train'])
             third_size = train_size // 3            
             # Tokenize the dataset