gradient norm clipping should be done right before calling the optimiser - fixing run_glue and run_ner as well

examples/run_glue.py

@@ -154,13 +154,16 @@ def train(args, train_dataset, model, tokenizer):
             if args.fp16:
                 with amp.scale_loss(loss, optimizer) as scaled_loss:
                     scaled_loss.backward()
-                torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm)
             else:
                 loss.backward()
-                torch.nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm)
 
             tr_loss += loss.item()
             if (step + 1) % args.gradient_accumulation_steps == 0 and not args.tpu:
+                if args.fp16:
+                    torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm)
+                else:
+                    torch.nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm)
+
                 optimizer.step()
                 scheduler.step()  # Update learning rate schedule
                 model.zero_grad()