diff --git a/examples/run_glue.py b/examples/run_glue.py
index 527e4400..ea5ac5bb 100644
--- a/examples/run_glue.py
+++ b/examples/run_glue.py
@@ -22,6 +22,7 @@ import glob
 import logging
 import os
 import random
+import json
 
 import numpy as np
 import torch
@@ -171,13 +172,21 @@ def train(args, train_dataset, model, tokenizer):
 
                 if args.local_rank in [-1, 0] and args.logging_steps > 0 and global_step % args.logging_steps == 0:
                     # Log metrics
+                    logs = {'step': global_step}
                     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)
                         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)
-                    tb_writer.add_scalar('loss', (tr_loss - logging_loss)/args.logging_steps, global_step)
+                            eval_key = 'eval_{}'.format(key)
+                            tb_writer.add_scalar(eval_key, value, global_step)
+                            logs[eval_key] = str(value)
                     logging_loss = tr_loss
+                    loss_scalar = (tr_loss - logging_loss) / args.logging_steps
+                    learning_rate_scalar = scheduler.get_lr()[0]
+                    tb_writer.add_scalar('lr', learning_rate_scalar, global_step)
+                    tb_writer.add_scalar('loss', loss_scalar, global_step)
+                    logs['learning_rate'] = learning_rate_scalar
+                    logs['loss'] = loss_scalar
+                    print(json.dumps(logs))
 
                 if args.local_rank in [-1, 0] and args.save_steps > 0 and global_step % args.save_steps == 0:
                     # Save model checkpoint