48 lines
1.7 KiB
Bash
48 lines
1.7 KiB
Bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.2-Fun-A14B-InP"
|
|
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
|
|
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
|
|
# NCCL_IB_DISABLE=1 与 NCCL_P2P_DISABLE=1 用于没有 RDMA 的多机环境。
|
|
# export NCCL_IB_DISABLE=1
|
|
# export NCCL_P2P_DISABLE=1
|
|
export NCCL_DEBUG=INFO
|
|
|
|
accelerate launch --mixed_precision="bf16" --use_fsdp --fsdp_auto_wrap_policy TRANSFORMER_BASED_WRAP \
|
|
--fsdp_transformer_layer_cls_to_wrap=WanAttentionBlock --fsdp_sharding_strategy "FULL_SHARD" \
|
|
--fsdp_state_dict_type=SHARDED_STATE_DICT --fsdp_backward_prefetch "BACKWARD_PRE" \
|
|
--fsdp_cpu_ram_efficient_loading False \
|
|
scripts/wan2.2_fun/train_reward_lora.py \
|
|
--config_path="config/wan2.2/wan_civitai_i2v.yaml" \
|
|
--pretrained_model_name_or_path=$MODEL_NAME \
|
|
--train_data_dir=$DATASET_NAME \
|
|
--train_data_meta=$DATASET_META_NAME \
|
|
--video_sample_size=640 \
|
|
--token_sample_size=640 \
|
|
--video_sample_stride=2 \
|
|
--video_sample_n_frames=81 \
|
|
--train_batch_size=1 \
|
|
--gradient_accumulation_steps=1 \
|
|
--dataloader_num_workers=8 \
|
|
--num_train_epochs=100 \
|
|
--checkpointing_steps=50 \
|
|
--learning_rate=1e-04 \
|
|
--seed=42 \
|
|
--output_dir="output_dir_wan2.2_fun_reward_lora" \
|
|
--gradient_checkpointing \
|
|
--mixed_precision="bf16" \
|
|
--adam_weight_decay=3e-2 \
|
|
--adam_epsilon=1e-10 \
|
|
--vae_mini_batch=1 \
|
|
--enable_bucket \
|
|
--boundary_type="low" \
|
|
--rank=128 \
|
|
--network_alpha=64 \
|
|
--target_name="q,k,v,ffn.0,ffn.2" \
|
|
--num_inference_steps=25 \
|
|
--num_decoded_latents=3 \
|
|
--reward_fn="HPSReward" \
|
|
--reward_fn_kwargs='{"version": "v2.1"}' \
|
|
--backprop \
|
|
--backprop_strategy="tail" \
|
|
--backprop_num_steps=1 \
|
|
--train_mode="inpaint" \
|
|
--low_vram |