Skip to content

Fix for setting adam_beta3 and adam_epsilon2 for CAME Optimizer #2654

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

Fix for setting adam_beta3 and adam_epsilon2 for CAME Optimizer #2654

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions docs/config.qmd
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -632,7 +632,9 @@ weight_decay:
# adamw hyperparams
adam_beta1:
adam_beta2:
adam_beta3:
adam_epsilon:
adam_epsilon2:
# Gradient clipping max norm
max_grad_norm:

Expand Down
6 changes: 5 additions & 1 deletion src/axolotl/core/trainer_builder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -387,8 +387,12 @@ def build(self, total_num_steps):
training_arguments_kwargs["adam_beta1"] = self.cfg.adam_beta1
if self.cfg.adam_beta2:
training_arguments_kwargs["adam_beta2"] = self.cfg.adam_beta2
if self.cfg.adam_beta3:
training_arguments_kwargs["adam_beta3"] = self.cfg.adam_beta3
if self.cfg.adam_epsilon:
training_arguments_kwargs["adam_epsilon"] = self.cfg.adam_epsilon
if self.cfg.adam_epsilon2:
training_arguments_kwargs["adam_epsilon2"] = self.cfg.adam_epsilon2
if self.cfg.max_grad_norm:
training_arguments_kwargs["max_grad_norm"] = self.cfg.max_grad_norm

Expand Down Expand Up @@ -715,7 +719,7 @@ def build(self, total_num_steps):

beta1 = training_arguments_kwargs.get("adam_beta1", 0.9)
beta2 = training_arguments_kwargs.get("adam_beta2", 0.999)
beta3 = training_arguments_kwargs.get("adam_beta2", 0.9999)
beta3 = training_arguments_kwargs.get("adam_beta3", 0.9999)
eps1 = training_arguments_kwargs.get("adam_epsilon", 1e-30)
eps2 = training_arguments_kwargs.get("adam_epsilon2", 1e-16)
adam_kwargs["betas"] = (beta1, beta2, beta3)
Expand Down
13 changes: 13 additions & 0 deletions src/axolotl/core/training_args.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,6 +227,19 @@ class AxolotlTrainingMixins:
},
)

adam_beta3: Optional[float] = field(
default=None,
metadata={
"help": "The beta3 hyperparameter used in some optimizers such as CAME"
},
)
adam_epsilon2: Optional[float] = field(
default=None,
metadata={
"help": "The epsilon2 hyperparameter used in some optimizers such as CAME"
},
)

# multi-modal section

image_size: int | tuple[int, int] | None = field(
Expand Down
Loading