export MODEL_NAME="../CogVideoX-Fun-Github/models/Diffusion_Transformer/Lens"
export DATASET_NAME="datasets/X-Fun-Images-Demo"
export DATASET_META_NAME="datasets/X-Fun-Images-Demo/metadata_add_width_height.json"
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA. 
# export NCCL_IB_DISABLE=1
# export NCCL_P2P_DISABLE=1
NCCL_DEBUG=INFO

accelerate launch --mixed_precision="bf16" scripts/lens/train_lora.py \
  --pretrained_model_name_or_path=$MODEL_NAME \
  --train_data_dir=$DATASET_NAME \
  --train_data_meta=$DATASET_META_NAME \
  --train_batch_size=1 \
  --image_sample_size=1328 \
  --gradient_accumulation_steps=1 \
  --dataloader_num_workers=8 \
  --num_train_epochs=100 \
  --checkpointing_steps=100 \
  --learning_rate=1e-04 \
  --seed=42 \
  --output_dir="output_dir_lens_lora" \
  --gradient_checkpointing \
  --mixed_precision="bf16" \
  --adam_weight_decay=3e-2 \
  --adam_epsilon=1e-10 \
  --vae_mini_batch=1 \
  --max_grad_norm=0.05 \
  --enable_bucket \
  --low_vram \
  --uniform_sampling \
  --rank=64 \
  --network_alpha=32 \
  --target_name="img_qkv,txt_qkv,to_out.0,to_add_out,img_mod.1,txt_mod.1,img_mlp,txt_mlp"