Logan
Logan
After some debugging, this happens when a batch isn't full. tmp.size(0) != res.size(0), which is causing the error in as_strided This could maybe be fixed by padding each batch to...
Nope, I just moved on to a different relation extraction model. If you are curious, currently [ATLOP ](https://github.com/wzhouad/ATLOP) has state-of-the-art on DocRED (63% F1). It is a much simpler model...
Yea, 12GB may not be enough. The curse of deep learning 😆
@IKeepMoving I used the weights they provide from their GitHub page (see the releases pane on the right side). No need to re-train unless you really want to :)
Thanks!
"exit code 137" means out of memory, so you don't have enough memory to train. I would decrease the batch size to 1 or 2
Any update on this? Further support for the windows key would be greatly appreciated 😄
For me personally, I have also hit this issue. When calculating things like rouge score, if you are predicting special tokens that are missing spaces, the rouge score won't be...
It's a bit of a long story, but basically, my output has special tokens during the ROUGE calculation to avoid places where the model fails to put the full word...
Just an idea, but you could probably model document hierarchy by adding special tokens to the tokenizer. For example, DocVQA is trained using an input like 'my question?', and the...