Skip to content

Length gen experiments#40

Merged
Benjamin-Walker merged 2 commits intomainfrom
length_gen
Oct 24, 2025
Merged

Length gen experiments#40
Benjamin-Walker merged 2 commits intomainfrom
length_gen

Conversation

@Benjamin-Walker
Copy link
Owner

Set checkpoint to only save for new best val acc

train.py Outdated
train_padding_length = 20
if model_name[:8] == "deltanet" or model_name == "deltaproduct":
train_padding_length = 65
elif model_name == "xlstm":
Copy link
Owner Author

Choose a reason for hiding this comment

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

Remove as don't perform mLSTM on length generalisation due to needing fixed input length

@Benjamin-Walker Benjamin-Walker merged commit ca6d55e into main Oct 24, 2025
1 check passed
@Benjamin-Walker Benjamin-Walker deleted the length_gen branch October 24, 2025 10:23
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.

1 participant