same device for evaluate between model and input

qwen_classifier/evaluate.py

@@ -83,7 +83,6 @@ def _preprocessing(df):
 
     # Concatenate the encoded tags with the original DataFrame
     df = pd.concat([df, encoded_df], axis=1)
-    print(df.columns)
     texts = df["prob_desc_description"].values.tolist()
     labels = df[TAG_NAMES].values.tolist()
 
@@ -136,7 +135,8 @@ def _evaluate_local(test_data_path, hf_repo):
 
     with torch.no_grad():
         for batch in dataloader:
-            batch = {k: v.to(DEVICE) for k, v in batch.items()}
+            print(f"EVALUATION RUNNING ON {global_model.device}")
+            batch = {k: v.to(global_model.device) for k, v in batch.items()}
             labels = batch["labels"].type(torch.float32)
 
             logits = global_model(batch["input_ids"], batch["attention_mask"])