Unexpected result from transformer model prediction

Beginners
1

Hello.
Working with huggingface transformers for Masked Language Task I have expected that prediction will return the same input string plus tokens for masked ones:

    from transformers import BertConfig, BertTokenizer, BertForMaskedLM
    
    model1 = BertForMaskedLM.from_pretrained("bert-base-uncased")
    tokenizer1 = BertTokenizer.from_pretrained("bert-base-uncased")
    
    # Read the rest of this [MASK] to understand things in more detail
    text = ["Read the rest of this [MASK] to understand things in more detail"]
    encoding1 = tokenizer1(text, return_tensors="pt")
    
    # forward pass
    outputs1 = model1(**encoding1)
    outputs1.logits.argmax(-1)

The output is :

    tensor([[1012, 3191, 1996, 2717, 1997, 2023, 2338, 2000, 3305, 2477, 1999, 2062,
             1012, 1012]])

But when I have decoded the output I did not find last input token detail :

tokenizer1.convert_ids_to_tokens([1012, 3191, 1996, 2717, 1997, 2023, 2338, 2000, 3305, 2477, 1999, 2062, 1012, 1012])


    ['.',
     'read',
     'the',
     'rest',
     'of',
     'this',
     'book',
     'to',
     'understand',
     'things',
     'in',
     'more',
     '.',
     '.']

Maybe I’m using it incorrectly model? Any other reason?