Skip to content

Fix: Configure gradient accumulation and chunking collator for stable training #301

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
quangkmhd wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −3
Open

Fix: Configure gradient accumulation and chunking collator for stable training #301

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
7 changes: 4 additions & 3 deletions sam3/train/configs/roboflow_v100/roboflow_v100_full_ft_100_images.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,14 +227,15 @@ scratch:
dict_key: roboflow100
with_seg_masks: ${scratch.enable_segmentation} # Note: Set this to true if using segmentation masks!

gradient_accumulation_steps: 1
train_batch_size: 1
gradient_accumulation_steps: 16
train_batch_size: 16
collate_fn:
_target_: sam3.train.data.collator.collate_fn_api
_target_: sam3.train.data.collator.collate_fn_api_with_chunking
_partial_: true
repeats: ${scratch.hybrid_repeats}
dict_key: all
with_seg_masks: ${scratch.enable_segmentation} # Note: Set this to true if using segmentation masks!
num_chunks: ${scratch.gradient_accumulation_steps}

# ============================================================================
# Trainer Configuration
Expand Down