There is no SEP token appended

[shabie]

You have a [SEP] or an equivalent token at the end which I think is not what the authors used:

docformer/src/docformer/dataset.py

Lines 260 to 261 in ae1ce38

	token_boxes = [[0, 0, 0, 0]] + token_boxes + [[1000, 1000, 1000, 1000]]
	unnormalized_token_boxes = [[0, 0, 0, 0]] + unnormalized_token_boxes + [[1000, 1000, 1000, 1000]]

See the first paragraph of the sub-section "Language Features" in the section 3.1

[uakarsh]

You can check it now, I have updated it, and for the bounding boxes as well, I removed the [1000,1000,1000,1000]