35 lines
1.4 KiB
Bash
35 lines
1.4 KiB
Bash
export MODEL_NAME="models/Diffusion_Transformer/ERNIE-Image"
|
|
export DATASET_NAME="datasets/internal_datasets/"
|
|
export DATASET_META_NAME="datasets/internal_datasets/metadata.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" --use_fsdp --fsdp_auto_wrap_policy TRANSFORMER_BASED_WRAP \
|
|
--fsdp_transformer_layer_cls_to_wrap ErnieImageSharedAdaLNBlock --fsdp_sharding_strategy "FULL_SHARD" \
|
|
--fsdp_state_dict_type=SHARDED_STATE_DICT --fsdp_backward_prefetch "BACKWARD_PRE" --fsdp_cpu_ram_efficient_loading False \
|
|
scripts/ernie_image/train.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=2e-05 \
|
|
--lr_scheduler="constant_with_warmup" \
|
|
--lr_warmup_steps=100 \
|
|
--seed=42 \
|
|
--output_dir="output_dir_ernie_image" \
|
|
--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 \
|
|
--uniform_sampling \
|
|
--trainable_modules "." |