We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Hi. I am following the workflow as shown in a blog that uses "keras" package for BERT: https://blogs.rstudio.com/ai/posts/2019-09-30-bert-r/
When compiling a model, I encountered the following error message:
model %>% compile( k_bert$AdamWarmup(decay_steps=1249, warmup_steps=124L, learning_rate=1e-4), loss = "mse", metrics = c("mae") )
Error in py_call_impl(callable, dots$args, dots$keywords) : AttributeError: 'AdamWarmup' object has no attribute '_set_hyper'
I cannot find which part of the code was wrong. I would appreciate your help. Thank you.
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Hi. I am following the workflow as shown in a blog that uses "keras" package for BERT:
https://blogs.rstudio.com/ai/posts/2019-09-30-bert-r/
When compiling a model, I encountered the following error message:
model %>% compile( k_bert$AdamWarmup(decay_steps=1249, warmup_steps=124L, learning_rate=1e-4), loss = "mse", metrics = c("mae") )Error in py_call_impl(callable, dots$args, dots$keywords) :
AttributeError: 'AdamWarmup' object has no attribute '_set_hyper'
I cannot find which part of the code was wrong. I would appreciate your help. Thank you.
The text was updated successfully, but these errors were encountered: