0

I am having the hardest of times getting my training session to use my gpu 0 which by every measure is present and correctly setup with cuda 12.2.

When I try to do python -m spacy train base_config.cfg --gpu-id 0

I get X Invalid config override '0': name should start with --.

It appears because - makes it a nogo.

I am running in Conda environment on Windows. I have spaCy 3.7.4

By the way, when I put gpu_id 0 under my system section in config file, spaCy appears not to be taking it but in the blue messages which appear when I do train say:

To switch to GPU, use the option --gpu-id 0

Improve this question
1
  • I can't see why this would not work, hopefully someone spots it. But just in case this is some weird cli parsing error, I would try: python -m spacy train base_config.cfg --gpu-id "0" . Commented Oct 8 at 8:10
Related questions
1
Why does Spacy 3 NER use different pipeline for GPU vs CPU?
0
Why token "less" has higher similarity with "more" in Spacy?
2
Installing Spacy for GPU training of Transformer
Load 7 more related questions Show fewer related questions

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.