Skip to content

fix label_names #3657

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

Merged
merged 1 commit into from
Mar 25, 2025
Merged

fix label_names #3657

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
1 change: 0 additions & 1 deletion examples/train/tuners/boft/train.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@ CUDA_VISIBLE_DEVICES=0 \
swift sft \
--model Qwen/Qwen2.5-7B-Instruct \
--train_type boft \
--label_names labels \
--dataset 'swift/self-cognition#1000' \
--num_train_epochs 1 \
--per_device_train_batch_size 1 \
Expand Down
1 change: 0 additions & 1 deletion examples/train/tuners/bone/train.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@ CUDA_VISIBLE_DEVICES=0 \
swift sft \
--model Qwen/Qwen2.5-7B-Instruct \
--train_type bone \
--label_names labels \
--dataset 'swift/self-cognition#1000' \
--num_train_epochs 1 \
--per_device_train_batch_size 1 \
Expand Down
3 changes: 2 additions & 1 deletion swift/trainers/mixin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,8 +94,9 @@ def __init__(self,

self.compute_loss_func = compute_loss_func
if get_function(model.__class__.forward) is not get_function(model.forward):
self.label_names = find_labels(model) or ['labels']
self.label_names = find_labels(model)
self.can_return_loss = can_return_loss(model)
self.label_names = self.label_names or ['labels']
self.start_time = time.time()

def _save_initial_model(self, output_dir):
Expand Down
Loading