when i run train_lcm_distill_lora_sdxl.py, it cause error:'DistributedDataParallel' object has no attribute 'disable_adapters' #6351
Description
Describe the bug
when i run train_lcm_distill_lora_sdxl.py, it cause error:'DistributedDataParallel' object has no attribute 'disable_adapters'
Reproduction
export MODEL_NAME="/home/kas/general_model/diffusers_workspace/text_to_image/cvitai/dreamshaper_xl1.0"
export OUTPUT_DIR="/home/kas/kas_workspace/cjt/save_lcm_sdxl_models"
DATA_DIR="/home/kas/kas_workspace/zijunhuang/other_data/coyo_part4"
VAE_NAME="/home/kas/general_model/diffusers_workspace/train_sd_xl/text2image/projects/llm_text_encoder/sdxl-vae-fp16-fix"
/home/kas/.conda/envs/torch2.0/bin/accelerate launch --mixed_precision="bf16" --multi_gpu --config_file="./distill.yaml" train_lcm_distill_lora_sdxl.py
--pretrained_teacher_model=$MODEL_NAME
--pretrained_vae_model_name_or_path=$VAE_NAME
--output_dir=$OUTPUT_DIR
--train_data_dir=$DATA_DIR
--mixed_precision=bf16
--cache_dir="./cache_dir"
--resolution=1024
--lora_rank=128
--learning_rate=1e-4 --loss_type="huber" --adam_weight_decay=0.0
--max_train_steps=1000000
--max_train_samples=1000000
--dataloader_num_workers=8
--checkpointing_steps=1000 --checkpoints_total_limit=10
--train_batch_size=12
--gradient_checkpointing --enable_xformers_memory_efficient_attention
--gradient_accumulation_steps=1
--use_8bit_adam
--resume_from_checkpoint=latest
Logs
No response
System Info
diffusersversion: 0.24.0- Platform: Linux-5.4.0-48-generic-x86_64-with-glibc2.27
- Python version: 3.9.17
- PyTorch version (GPU?): 2.0.1+cu118 (True)
- Huggingface_hub version: 0.20.1
- Transformers version: 4.33.0
- Accelerate version: 0.25.0
- xFormers version: 0.0.21
- Using GPU in script?:
- Using distributed or parallel set-up in script?:
Who can help?
No response