Skip to content

Some refactoring of methods to enable additional customization of BaseTrainer, including how input data to models are sharded. #345

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Some refactoring of methods to enable additional customization of BaseTrainer, including how input data to models are sharded. #345

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion examples/losses.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,7 @@ def sigmoid_cross_entropy(
register_loss: bool = True,
extra_registration_kwargs: dict[str, Any] | None = None,
registration_module: types.ModuleType = kfac_jax,
mask: Array | None = None,
) -> Array:
"""Sigmoid cross-entropy loss."""
extra_registration_kwargs = extra_registration_kwargs or {}
Expand All @@ -70,7 +71,12 @@ def sigmoid_cross_entropy(

log_1p = jnp.log1p(jnp.exp(neg_abs_logits))

return weight * jnp.add(relu_logits - logits * labels, log_1p)
if mask is None:
mask = 1.0
else:
assert mask.shape == labels.shape

return weight * mask * jnp.add(relu_logits - logits * labels, log_1p)


def softmax_cross_entropy(
Expand Down