dev

app.py

@@ -131,8 +131,8 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
             
             elif os.access(f'/data/{hub_id.strip()}_train_dataset3', os.R_OK):                        
                 dataset = load_dataset(dataset_name.strip())
-                dataset['test'] = dataset['test'].select(range(1200))
-                dataset['train'] = dataset['train'].select(range(12000))
+                dataset['test'] = dataset['test'].select(range(800))
+                dataset['train'] = dataset['train'].select(range(8000))
                 del dataset['train']
                 del dataset['validation']
                 test_set = dataset.map(tokenize_function, batched=True)
@@ -141,7 +141,7 @@ 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(12000))
+                dataset['train'] = dataset['train'].select(range(8000))
                 train_size = len(dataset['train'])
                 third_size = train_size // 3
                 del dataset['test']
@@ -159,7 +159,7 @@ 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(12000))
+                dataset['train'] = dataset['train'].select(range(8000))
                 dataset['validation'] = dataset['validation'].select(range(200))
                 train_size = len(dataset['train'])
                 third_size = train_size // 3                
@@ -175,7 +175,7 @@ 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(12000))
+            dataset['train'] = dataset['train'].select(range(8000))
             train_size = len(dataset['train'])
             third_size = train_size // 3            
             # Tokenize the dataset