Fixing mode in evaluate during training

examples/run_ner.py

@@ -153,7 +153,7 @@ def train(args, train_dataset, model, tokenizer, labels, pad_token_label_id):
                 if args.local_rank in [-1, 0] and args.logging_steps > 0 and global_step % args.logging_steps == 0:
                     # Log metrics
                     if args.local_rank == -1 and args.evaluate_during_training:  # Only evaluate when single GPU otherwise metrics may not average well
-                        results, _ = evaluate(args, model, tokenizer, labels, pad_token_label_id)
+                        results, _ = evaluate(args, model, tokenizer, labels, pad_token_label_id, mode="dev")
                         for key, value in results.items():
                             tb_writer.add_scalar("eval_{}".format(key), value, global_step)
                     tb_writer.add_scalar("lr", scheduler.get_lr()[0], global_step)