Fix importing unofficial TF models

Importing unofficial TF models seems to be working well, at least for me.
This PR resolves #50.

pytorch_pretrained_bert/convert_tf_checkpoint_to_pytorch.py

@@ -50,7 +50,7 @@ def convert_tf_checkpoint_to_pytorch(tf_checkpoint_path, bert_config_file, pytor
         name = name.split('/')
         # adam_v and adam_m are variables used in AdamWeightDecayOptimizer to calculated m and v
         # which are not required for using pretrained model
-        if any(n in ["adam_v", "adam_m"] for n in name):
+        if any(n in ["adam_v", "adam_m", "global_step"] for n in name):
             print("Skipping {}".format("/".join(name)))
             continue
         pointer = model