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

Using "bert_ft" as a starting point to further training #21

Open
yvanrousset opened this issue Sep 27, 2023 · 0 comments
Open

Using "bert_ft" as a starting point to further training #21

yvanrousset opened this issue Sep 27, 2023 · 0 comments

Comments

@yvanrousset
Copy link

Hi everyone,

I would like to used "bert_ft" as a starting model and fine tune it on other reactions to extract a new rxnfp fingerprint.
Something like this:

model, tokenizer = get_default_model_and_tokenizer()

or

model = SmilesLanguageModelingModel(model_type='bert', model_name = 'bert_ft', args=args)
train_file = 'my_reactions_train.txt'
eval_file = 'my_reactions_test.txt'
model.train_model(train_file=train_file, eval_file=eval_file)

However this does not work. So far, I have only succeed in using "bert_mlm_1k_tpl":

model = SmilesLanguageModelingModel(model_type='bert', model_name = 'bert_mlm_1k_tpl', args=args)
train_file = 'my_reactions_train.txt'
eval_file = 'my_reactions_test.txt'
model.train_model(train_file=train_file, eval_file=eval_file)

Anyone to shed some light?

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

1 participant