Errors in saving trained models

Hi, when running
```
cbow = CBOWClassifier()
trainer = dy.AdagradTrainer(cbow.model) #where mode is a parameter collection
loss = cbow.get_loss(train_set[0], True)
loss_value = loss.value()
loss.backward()
trainer.update()
cbow.model.save("best_tmp.model")

cbow = CBOWClassifier()
cbow.model.populate("best_tmp.model")
```

The out is unreadable and the load fails.
While commenting out the `trainer.update()` line makes the save/load work

```
cbow = CBOWClassifier()
trainer = dy.AdagradTrainer(cbow.model)
loss = cbow.get_loss(train_set[0], True)
loss_value = loss.value()
loss.backward()
#trainer.update()
cbow.model.save("best_tmp.model")

cbow = CBOWClassifier()
cbow.model.populate("best_tmp.model")
```

Using DyNet 2.0.3 trough jupyter notebook
There are no error msgs the kernel just disconnect and reconnect back after few minutes(!?)

Reproduce the DyNet 2.0.3 snippet in a Jupyter notebook, comparing behavior with and without AdagradTrainer.update(). Start from the CBOWClassifier model.save and model.populate calls; done means saving after the update produces readable output, reloads successfully, and does not disconnect the kernel.

Written by the indexing model from the issue text.