Logs

app.py

@@ -152,11 +152,6 @@ def evaluate_model(model, dataloader, device):
     print(len(all_labels))
     all_preds = np.asarray(all_preds, dtype=np.float32)
     all_labels = np.asarray(all_labels, dtype=np.float32)
-    print("Flattened sizes")
-    print(all_preds.size)
-    print(all_labels.size)
-    all_preds = all_preds.flatten()
-    all_labels = all_labels.flatten()
     accuracy = accuracy_score(all_labels, all_preds)
     precision, recall, f1, _ = precision_recall_fscore_support(all_labels, all_preds, average='micro')
 
@@ -199,9 +194,8 @@ dataloader = DataLoader(tokenized_data['train'], batch_size=batch_size, collate_
 # create testing data loader
 test_dataloader = DataLoader(tokenized_data['test'], batch_size=batch_size, collate_fn=data_collator)
 
-# TEMPORARY - for testing
-teacher_accuracy, teacher_precision, teacher_recall, teacher_f1 = evaluate_model(teacher_model, test_dataloader, device)
-print(f"Teacher (test) - Accuracy: {teacher_accuracy:.4f}, Precision: {teacher_precision:.4f}, Recall: {teacher_recall:.4f}, F1 Score: {teacher_f1:.4f}")
+untrained_student_accuracy, untrained_student_precision, untrained_student_recall, untrained_student_f1 = evaluate_model(student_model, test_dataloader, device)
+print(f"Untrained Student (test) - Accuracy: {untrained_student_accuracy:.4f}, Precision: {untrained_student_precision:.4f}, Recall: {untrained_student_recall:.4f}, F1 Score: {untrained_student_f1:.4f}")
 
 # put student model in train mode
 student_model.train()