Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

NER finetuning - checkpoint problem #61

Closed
zampierimatteo91 opened this issue Nov 20, 2019 · 3 comments
Closed

NER finetuning - checkpoint problem #61

zampierimatteo91 opened this issue Nov 20, 2019 · 3 comments

Comments

@zampierimatteo91
Copy link

zampierimatteo91 commented Nov 20, 2019

Hi all,
Sorry to bother you with stupid mistakes.

I am trying to fine-tune the NER model to later run a prediction on a dataset I have.
I am trying to run the fine-tuning on a dataset I have, formatted as the ones you provided.
I downloaded the biobert_v1.1_pubmed model, but it doesn't contain any model.ckpt per se; instead, there are model.ckpt-1000000.meta, model.ckpt-1000000.index, and model.ckpt-1000000.data-00000-of-00001.

Using one of those gives error though.

Thanks

@ManousogiannisM
Copy link

Hi,

Based on tensorflow/models#2676 (comment) ,
using just model.ckpt (without .index or -1000000.meta) worked for me.

@zampierimatteo91
Copy link
Author

Hi @ManousogiannisM ,

Thanks for the reply!

Using model.ckpt-1000000 worked fine!
I now have to solve just the usage of tensorflow-gpu :p

Thanks again and good day

@AndreasSaka
Copy link

@zampierimatteo91

I am trying to run the fine-tuning on a dataset I have, formatted as the ones you provided.

can you elaborate on how you performed this task ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants