Fix InstructPix2Pix training in multi-GPU mode #2978
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The documentation is not available anymore as the PR was closed or merged. |
|
As pointed out by @whbzju here, we also need to do unwrapping while running validation inference. So, I fixed that and did the testing with the following command: accelerate launch --mixed_precision="fp16" --multi_gpu train_instruct_pix2pix.py \
--pretrained_model_name_or_path=runwayml/stable-diffusion-v1-5 \
--dataset_name=sayakpaul/instructpix2pix-1000-samples \
--use_ema \
--enable_xformers_memory_efficient_attention \
--resolution=512 --random_flip \
--train_batch_size=2 --gradient_accumulation_steps=4 --gradient_checkpointing \
--max_train_steps=20 \
--checkpointing_steps=10 --checkpoints_total_limit=1 \
--learning_rate=5e-05 --lr_warmup_steps=0 \
--conditioning_dropout_prob=0.05 \
--mixed_precision=fp16 \
--val_image_url="https://hf.co/datasets/diffusers/diffusers-images-docs/resolve/main/mountain.png" \
--validation_prompt="make the mountains snowy" \
--seed=42 \
--report_to=wandb@patrickvonplaten could you take a look again? |
williamberman
approved these changes
Apr 10, 2023
sayakpaul
force-pushed
the
fix/instructpix2pix-training
branch
from
9b6a6db to
91854ff
Compare
w4ffl35
pushed a commit
to w4ffl35/diffusers
that referenced
this pull request
Apr 14, 2023
* fix: norm group test for UNet3D. * fix: unet rejig. * fix: unwrapping when running validation inputs. * unwrapping the unet too. * fix: device. * better unwrapping. * unwrapping before ema. * unwrapping.
dg845
pushed a commit
to dg845/diffusers
that referenced
this pull request
May 6, 2023
* fix: norm group test for UNet3D. * fix: unet rejig. * fix: unwrapping when running validation inputs. * unwrapping the unet too. * fix: device. * better unwrapping. * unwrapping before ema. * unwrapping.
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
* fix: norm group test for UNet3D. * fix: unet rejig. * fix: unwrapping when running validation inputs. * unwrapping the unet too. * fix: device. * better unwrapping. * unwrapping before ema. * unwrapping.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Should close #2966.
Command used for testing:
accelerate launch --mixed_precision="fp16" --multi_gpu train_instruct_pix2pix.py \ --pretrained_model_name_or_path=runwayml/stable-diffusion-v1-5 \ --dataset_name=sayakpaul/instructpix2pix-1000-samples \ --use_ema \ --enable_xformers_memory_efficient_attention \ --resolution=512 --random_flip \ --train_batch_size=4 --gradient_accumulation_steps=4 --gradient_checkpointing \ --max_train_steps=100 \ --checkpointing_steps=10 --checkpoints_total_limit=1 \ --learning_rate=5e-05 --lr_warmup_steps=0 \ --conditioning_dropout_prob=0.05 \ --mixed_precision=fp16 \ --seed=42