Can anyone reproduce the baseline results reported in the paper with the current version of codes?

I think the following codes should be inserted here: https://github.com/alexa/massive/blob/main/src/massive/utils/training_utils.py#L472

```
for i, x in enumerate(lab): 
    if x == -100: 
        pred[i] = -100
```