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

Add larger GPT models #213

Merged
merged 1 commit into from
Jan 10, 2022
Merged

Conversation

jbloxham
Copy link
Contributor

Time to go bigger :)

Specs copied from https://arxiv.org/pdf/2005.14165.pdf. Only fields changed from the existing GPT models are:
model.gpt2.n_embd
model.gpt2.n_head
model.gpt2.n_inner
model.gpt2.n_layer
optimizer.adamw.lr
train_batch_size
grad_accum

@moinnadeem
Copy link
Contributor

What machine is grad_accum tuned for?

@jbloxham
Copy link
Contributor Author

What machine is grad_accum tuned for?

It's just assuming a microbatch size of 1 for any 8-GPU machine. I'm of the opinion that providing pre-tuned grad_accum is counterproductive.

Copy link
Member

@abhi-mosaic abhi-mosaic left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think these are fine for now for the purpose of performance benchmarking, in the near future we can update / replace them with GPT3 convergence run YAMLs.

@jbloxham jbloxham merged commit aad5330 into mosaicml:dev Jan 10, 2022
coryMosaicML pushed a commit to coryMosaicML/composer that referenced this pull request Feb 23, 2022
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

Successfully merging this pull request may close these issues.

3 participants