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] Fix batch-size setting of single-card LLaVA-Llama-3-8B configs #598

Merged
merged 2 commits into from
May 10, 2024
Merged

[Fix] Fix batch-size setting of single-card LLaVA-Llama-3-8B configs #598

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
fb81982
Update llava_llama3_8b_instruct_qlora_clip_vit_large_p14_336_e1_gpu1_…
LZHgrla Apr 23, 2024
5aa0bae
Update llava_llama3_8b_instruct_quant_clip_vit_large_p14_336_e1_gpu1_…
LZHgrla Apr 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion ...14_336/finetune/llava_llama3_8b_instruct_qlora_clip_vit_large_p14_336_e1_gpu1_finetune.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@

# Scheduler & Optimizer
batch_size = 1 # per_device
accumulative_counts = 16
accumulative_counts = 128
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这么夸张的数，有跑过吗？ loss 会下降不？

Copy link
Collaborator Author

@LZHgrla LZHgrla Apr 29, 2024 •
edited

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@hhaAndroid
测试了一下，是可以正常下降的。因为这是单卡的配置，这样设置来确保 global bs = 128

dataloader_num_workers = 0
max_epochs = 1
optim_type = AdamW
Expand Down
2 changes: 1 addition & 1 deletion ...14_336/pretrain/llava_llama3_8b_instruct_quant_clip_vit_large_p14_336_e1_gpu1_pretrain.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@

# Scheduler & Optimizer
batch_size = 1 # per_device
accumulative_counts = 32
accumulative_counts = 256
dataloader_num_workers = 0
max_epochs = 1
optim_type = AdamW
Expand Down