dev

app.py

@@ -109,6 +109,8 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
             return model_inputs
     
         #max_length = 512
+        # Load the dataset
+        dataset = load_dataset(dataset_name.strip())          
         train_size = len(dataset['train'])
         half_size = train_size // 2  
         max_length = model.get_input_embeddings().weight.shape[0]
@@ -127,9 +129,7 @@ def fine_tune_model(model, dataset_name, hub_id, api_key, num_epochs, batch_size
                 eval_dataset=tokenized_test_dataset,
                 compute_metrics=compute_metrics,
             )            
-        except:
-            # Load the dataset
-            dataset = load_dataset(dataset_name.strip())                                  
+        except:                                            
             tokenizer = AutoTokenizer.from_pretrained('google/t5-efficient-tiny-nh8')
             # Tokenize the dataset