Skip to content
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

Jump to bottom

Fix dreambooth data sampler issue #8413

Merged
merged 1 commit into from
Feb 16, 2024
Merged

Fix dreambooth data sampler issue #8413

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: 1 addition & 1 deletion nemo/collections/multimodal/models/text_to_image/dreambooth/dreambooth.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -487,7 +487,7 @@ def setup_training_data(self, cfg):
global_batch_size=self.cfg.global_batch_size,
data_parallel_rank=parallel_state.get_data_parallel_rank(),
data_parallel_size=parallel_state.get_data_parallel_world_size(),
drop_last=False,
drop_last=True,
)

self._train_dl = torch.utils.data.DataLoader(
Expand Down
3 changes: 3 additions & 0 deletions nemo/collections/multimodal/parts/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,9 +22,11 @@
from pytorch_lightning.plugins.environments import TorchElasticEnvironment
from transformers import CLIPImageProcessor

from nemo.collections.nlp.modules.common.megatron.megatron_init import fake_initialize_model_parallel
from nemo.collections.nlp.parts.nlp_overrides import NLPDDPStrategy, NLPSaveRestoreConnector
from nemo.collections.nlp.parts.peft_config import PEFT_CONFIG_MAP
from nemo.utils import AppState, logging
from nemo.utils.model_utils import inject_model_parallel_rank

try:
from megatron.core import dist_checkpointing
Expand Down Expand Up @@ -361,6 +363,7 @@ def create_neva_model_and_processor(cfg):
neva_cfg.activations_checkpoint_method = None
neva_cfg.precision = trainer.precision
neva_cfg.mm_cfg.llm.from_pretrained = cfg.get('base_model_file', None)
neva_cfg.apply_rope_fusion = False
# neva_cfg.mm_cfg.vision_encoder.from_pretrained = None

model = MegatronNevaModel.restore_from(
Expand Down