Yubo Zheng

I'm facing the same problem as all generated sentences are the same sentence. It seems that the pre-trained encoder makes all the features similar.

Anyone solved this problem?

> I found how to fix this problem. > > In eval_decoding.py file, > > `predictions=tokenizer.encode(predicted_string)` this code should be changed to `predictions=tokenizer.encode(predicted_string[0])` > > predicted_string is list, so we...