BookmarkSubscribeRSS Feed
Michal_S_00
Calcite | Level 5

Hi,

I'm working at Sequnce Labaling model for NLP task (dlpy.applications.SequenceLabeling) and while I was trying to fit the data, I came across an error "ERROR: A floating-point overflow exception occurred, halting the analysis. This condition is usually caused by improperly scaled inputs, a large learning rate, or exploding gradients.".

 

This is my code:

model.fit(data='train_data',
                 inputs=col_names[:10],
                 texts=col_names[:10],
                 target_sequence=col_names[10:],
                 nominals=col_names[10:],
                 text_parms=TextParms(init_input_embeddings='word_embeddings_100'),
                 mini_batch_size=10,
                 max_epochs=100,
                 lr=0.000000000000001,
                 log_level=2
                 )
 
Input consists of ten columns, there is one word in each column in each row, also the labels(varchar type) are represented in the same way.
 
I tried to run it with diffrent learning rate, but every time I get the same error, any ideas how to fix that?
2 REPLIES 2
joeFurbee
Community Manager

Hi @Michal_S_00,

This question is being worked on by the developer through the issue created on the DLPy GitHub repository. I will update this thread once a solution is posted there.


Join us for SAS Community Trivia
SAS Bowl XXXVI, Data Simulation
Wednesday, December 13, 2023, at 10 a.m. ET | #SASBowl

joeFurbee
Community Manager

Here's a copy of the response from @lipcai on GitHub:

 

If your model generates floating-point exception errors, you can consider specifying values for gradient clipping parameters (clip_grad_min and clip_grad_max). https://github.com/sassoftware/python-dlpy/blob/af4874e00edc7a4b7c31646e76057a76d566481c/dlpy/tests/...


Join us for SAS Community Trivia
SAS Bowl XXXVI, Data Simulation
Wednesday, December 13, 2023, at 10 a.m. ET | #SASBowl

SAS INNOVATE 2024

Innovate_SAS_Blue.png

Registration is open! SAS is returning to Vegas for an AI and analytics experience like no other! Whether you're an executive, manager, end user or SAS partner, SAS Innovate is designed for everyone on your team. Register for just $495 by 12/31/2023.

If you are interested in speaking, there is still time to submit a session idea. More details are posted on the website. 

Register now!

How to Concatenate Values

Learn how use the CAT functions in SAS to join values from multiple variables into a single value.

Find more tutorials on the SAS Users YouTube channel.

Get the $99 certification deal.jpg

 

 

Back in the Classroom!

Select SAS Training centers are offering in-person courses. View upcoming courses for:

View all other training opportunities.

Discussion stats
  • 2 replies
  • 658 views
  • 1 like
  • 2 in conversation