[FIX] not training when epoch is small (#3006)

* solving bug where for small epochs and large gradient_accumulation_steps we never train

* black formatting

* no need to change these files

examples/run_glue.py

@@ -233,7 +233,11 @@ def train(args, train_dataset, model, tokenizer):
                 loss.backward()
 
             tr_loss += loss.item()
-            if (step + 1) % args.gradient_accumulation_steps == 0:
+            if (step + 1) % args.gradient_accumulation_steps == 0 or (
+                # last step in epoch but step is always smaller than gradient_accumulation_steps
+                len(epoch_iterator) <= args.gradient_accumulation_steps
+                and (step + 1) == len(epoch_iterator)
+            ):
                 if args.fp16:
                     torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm)
                 else: