Closed basteran closed 5 months ago
Hi, see my comment
https://github.com/microsoft/unilm/issues/1429#issuecomment-1900139771
(I just saw you also opened an issue here before I replied there)
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.
Please note that issues that do not follow the contributing guidelines are likely to be ignored.
Hi I am still working on this issue with @ydshieh , we will update it whenever we have news!
Hi @basteran
Please see https://discuss.huggingface.co/t/kosmos-2-fine-tuning/75691/32?u=ydshieh
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.
Please note that issues that do not follow the contributing guidelines are likely to be ignored.
System Info
transformers
version: 4.36.2Who can help?
I think the person in charge of Kosmos-2 is @ydshieh
Information
Tasks
examples
folder (such as GLUE/SQuAD, ...)Reproduction
This issue refers to another issue reported on the official Kosmos repository!
Hello everyone, thank you very much for your contribution. I appreciate the effort and consistency in uploading the code for such many models and maintaining this repository.
I saw Kosmos-2 and I quickly thought I could fine-tune it on my downstream task. But I couldn't find any example of how to do it. I see there is on the official Kosmos repository a little "guide" for Training the model, but I don't know if they're referring to the Pre-training or further fine-tuning, I'm interested in the second one.
So I tried to implement it myself using the
transformers
library, but I'm getting errors during the Fine-Tuning procedure.and the resulting errors:
I can't figure out the issue. It says that the model did not return a loss, which means it didn't compute it. It looks like the
processor
did not return anylabels
and theTrainer
could not compute the loss...Expected behavior
I would expect to train the model on my data, i.e. to compute the loss, perform gradient updates, etc.