[Example] Fix duplicated (#2154)

* [Example] GCN on ogbn-arxiv dataset

* Add README.md

* Update GCN implementation on ogbn-arxiv

* Update GCN on ogbn-arxiv

* Fix typo

* Use evaluator to get results

* Fix duplicated

* Fix duplicated
Co-authored-by: Mufei Li <mufeili1996@gmail.com>
Co-authored-by: Zihao Ye <expye@outlook.com>

examples/pytorch/ogb/ogbn-arxiv/gcn.py

@@ -134,9 +134,8 @@ def run(args, graph, labels, train_idx, val_idx, test_idx, evaluator, n_running)
 
         lr_scheduler.step(loss)
 
-        train_acc, val_acc, test_acc, train_loss, val_loss, test_loss = evaluate(
-            model, graph, labels, train_idx, val_idx, test_idx, args.use_labels
-        )
+        toc = time.time()
+        total_time += toc - tic
 
         # if val_acc > best_val_acc:
         if val_loss < best_val_loss: