export MODEL_NAME="models/Diffusion_Transformer/Wan2.1-T2V-1.3B"
export DATASET_NAME=""
export ODE_DATA_META="datasets/ode_pairs_output/outputs.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/wan2.1_self_forcing/train_ode.py \
  --config_path="config/wan2.1/wan_civitai.yaml" \
  --pretrained_model_name_or_path=$MODEL_NAME \
  --train_data_dir=$DATASET_NAME \
  --train_data_meta=$ODE_DATA_META \
  --train_batch_size=1 \
  --gradient_accumulation_steps=1 \
  --dataloader_num_workers=8 \
  --num_train_epochs=100 \
  --checkpointing_steps=500 \
  --learning_rate=2.0e-06 \
  --lr_scheduler="constant_with_warmup" \
  --lr_warmup_steps=100 \
  --seed=42 \
  --output_dir="output_dir_wan2.1_self_forcing_ode_regression" \
  --gradient_checkpointing \
  --mixed_precision="bf16" \
  --adam_weight_decay=3e-2 \
  --adam_epsilon=1e-10 \
  --max_grad_norm=0.05 \
  --num_frame_per_block=3 \
  --train_sampling_steps=1000 \
  --denoising_step_indices_list 1000 750 500 250 \
  --shift=8.0 \
  --resume_from_checkpoint="latest" \
  --trainable_modules "."