GitHub - huggingface/peft: 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

from transformers import AutoModelForSeq2SeqLM
from peft import get_peft_config, get_peft_model, LoraConfig, TaskType
model_name_or_path = "bigscience/mt0-large"
tokenizer_name_or_path = "bigscience/mt0-large"

peft_config = LoraConfig(
    task_type=TaskType.SEQ_2_SEQ_LM, inference_mode=False, r=8, lora_alpha=32, lora_dropout=0.1
)

model = AutoModelForSeq2SeqLM.from_pretrained(model_name_or_path)
model = get_peft_model(model, peft_config)
model.print_trainable_parameters()
# output: trainable params: 2359296 || all params: 1231940608 || trainable%: 0.19151053100118282

export MODEL_NAME= "CompVis/stable-diffusion-v1-4" #"stabilityai/stable-diffusion-2-1"
export INSTANCE_DIR="path-to-instance-images"
export CLASS_DIR="path-to-class-images"
export OUTPUT_DIR="path-to-save-model"

accelerate launch train_dreambooth.py \
  --pretrained_model_name_or_path=$MODEL_NAME  \
  --instance_data_dir=$INSTANCE_DIR \
  --class_data_dir=$CLASS_DIR \
  --output_dir=$OUTPUT_DIR \
  --train_text_encoder \
  --with_prior_preservation --prior_loss_weight=1.0 \
  --instance_prompt="a photo of sks dog" \
  --class_prompt="a photo of dog" \
  --resolution=512 \
  --train_batch_size=1 \
  --lr_scheduler="constant" \
  --lr_warmup_steps=0 \
  --num_class_images=200 \
  --use_lora \
  --lora_r 16 \
  --lora_alpha 27 \
  --lora_text_encoder_r 16 \
  --lora_text_encoder_alpha 17 \
  --learning_rate=1e-4 \
  --gradient_accumulation_steps=1 \
  --gradient_checkpointing \
  --max_train_steps=800

compute_environment: LOCAL_MACHINE
deepspeed_config:
  gradient_accumulation_steps: 1
  gradient_clipping: 1.0
  offload_optimizer_device: cpu
  offload_param_device: cpu
  zero3_init_flag: true
  zero3_save_16bit_model: true
  zero_stage: 3
distributed_type: DEEPSPEED
downcast_bf16: 'no'
dynamo_backend: 'NO'
fsdp_config: {}
machine_rank: 0
main_training_function: main
megatron_lm_config: {}
mixed_precision: 'no'
num_machines: 1
num_processes: 1
rdzv_backend: static
same_network: true
use_cpu: false

accelerate launch --config_file ds_zero3_cpu.yaml examples/peft_lora_seq2seq_accelerate_ds_zero3_offload.py

GPU Memory before entering the train : 1916
GPU Memory consumed at the end of the train (end-begin): 66
GPU Peak Memory consumed during the train (max-begin): 7488
GPU Total Peak Memory consumed during the train (max): 9404
CPU Memory before entering the train : 19411
CPU Memory consumed at the end of the train (end-begin): 0
CPU Peak Memory consumed during the train (max-begin): 0
CPU Total Peak Memory consumed during the train (max): 19411
epoch=4: train_ppl=tensor(1.0705, device='cuda:0') train_epoch_loss=tensor(0.0681, device='cuda:0')
100%|████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:27<00:00,  3.92s/it]
GPU Memory before entering the eval : 1982
GPU Memory consumed at the end of the eval (end-begin): -66
GPU Peak Memory consumed during the eval (max-begin): 672
GPU Total Peak Memory consumed during the eval (max): 2654
CPU Memory before entering the eval : 19411
CPU Memory consumed at the end of the eval (end-begin): 0
CPU Peak Memory consumed during the eval (max-begin): 0
CPU Total Peak Memory consumed during the eval (max): 19411
accuracy=100.0
eval_preds[:10]=['no complaint', 'no complaint', 'complaint', 'complaint', 'no complaint', 'no complaint', 'no complaint', 'complaint', 'complaint', 'no complaint']
dataset['train'][label_column][:10]=['no complaint', 'no complaint', 'complaint', 'complaint', 'no complaint', 'no complaint', 'no complaint', 'complaint', 'complaint', 'no complaint']

from peft.utils.other import fsdp_auto_wrap_policy

...

if os.environ.get("ACCELERATE_USE_FSDP", None) is not None:
    accelerator.state.fsdp_plugin.auto_wrap_policy = fsdp_auto_wrap_policy(model)

model = accelerator.prepare(model)

command_file: null
commands: null
compute_environment: LOCAL_MACHINE
deepspeed_config: {}
distributed_type: FSDP
downcast_bf16: 'no'
dynamo_backend: 'NO'
fsdp_config:
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_backward_prefetch_policy: BACKWARD_PRE
  fsdp_offload_params: true
  fsdp_sharding_strategy: 1
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_transformer_layer_cls_to_wrap: T5Block
gpu_ids: null
machine_rank: 0
main_process_ip: null
main_process_port: null
main_training_function: main
megatron_lm_config: {}
mixed_precision: 'no'
num_machines: 1
num_processes: 2
rdzv_backend: static
same_network: true
tpu_name: null
tpu_zone: null
use_cpu: false

accelerate launch --config_file fsdp_config.yaml examples/peft_lora_seq2seq_accelerate_fsdp.py