Skip to content

fix ds z3 checkpointing when stage3_gather_16bit_weights_on_model_save=False #25817

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 2 commits into from
Aug 31, 2023
Merged

fix ds z3 checkpointing when stage3_gather_16bit_weights_on_model_save=False #25817

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cff6480
fix ds z3 checkpointing when `stage3_gather_16bit_weights_on_model_s…
pacman100 Aug 29, 2023
bf7cb03
refactoring
pacman100 Aug 30, 2023
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
12 changes: 6 additions & 6 deletions src/transformers/trainer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,6 +93,7 @@
nested_numpify,
nested_xla_mesh_reduce,
reissue_pt_warnings,
remove_dummy_checkpoint,
)
from .trainer_utils import (
PREFIX_CHECKPOINT_DIR,
Expand Down Expand Up @@ -2780,12 +2781,8 @@ def save_model(self, output_dir: Optional[str] = None, _internal_call: bool = Fa
if self.args.should_save:
self._save(output_dir, state_dict=state_dict)
if self.is_fsdp_enabled:
# remove the dummy state_dict saved above
if self.args.should_save:
for filename in [WEIGHTS_NAME, SAFE_WEIGHTS_NAME]:
file = os.path.join(output_dir, filename)
if os.path.isfile(file):
os.remove(file)
# remove the dummy state_dict
remove_dummy_checkpoint(self.args.should_save, output_dir, [WEIGHTS_NAME, SAFE_WEIGHTS_NAME])
save_fsdp_model(self.accelerator.state.fsdp_plugin, self.accelerator, self.model, output_dir)

elif self.is_deepspeed_enabled:
Expand All @@ -2801,6 +2798,9 @@ def save_model(self, output_dir: Optional[str] = None, _internal_call: bool = Fa
" stage3_gather_16bit_weights_on_model_save=false. Saving the full checkpoint instead, use"
" zero_to_fp32.py to recover weights"
)
self._save(output_dir, state_dict={})
# remove the dummy state_dict
remove_dummy_checkpoint(self.args.should_save, output_dir, [WEIGHTS_NAME, SAFE_WEIGHTS_NAME])
self.model_wrapped.save_checkpoint(output_dir)

elif self.args.should_save:
Expand Down
8 changes: 8 additions & 0 deletions src/transformers/trainer_pt_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1089,6 +1089,14 @@ def get_module_class_from_name(module, name):
return module_class


def remove_dummy_checkpoint(is_main_process, output_dir, filenames):
if is_main_process:
for filename in filenames:
file = os.path.join(output_dir, filename)
if os.path.isfile(file):
os.remove(file)


if is_sagemaker_mp_enabled():
import smdistributed.modelparallel.torch as smp

Expand Down