adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1.0e-08
adam_weight_decay: 0.01
allow_tf32: false
beta_dpo: 2500
cache_dir: null
checkpointing_steps: 2000
checkpoints_total_limit: null
dataloader_num_workers: 0
dataset_name: kashif/pickascore
dataset_split_name: validation
enable_xformers_memory_efficient_attention: false
gradient_accumulation_steps: 1
gradient_checkpointing: true
hub_model_id: null
hub_token: null
learning_rate: 1.0e-05
local_rank: -1
logging_dir: logs
loss_type: sigmoid
lr_num_cycles: 1
lr_power: 1.0
lr_scheduler: constant
lr_warmup_steps: 0
max_grad_norm: 1.0
max_train_samples: null
max_train_steps: 10000
mixed_precision: fp16
no_hflip: false
num_train_epochs: 20
output_dir: diffusion-dpo
pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
prior_generation_precision: null
push_to_hub: true
random_crop: false
rank: 8
report_to: tensorboard
resolution: 512
resume_from_checkpoint: null
revision: null
run_validation: true
scale_lr: false
seed: 0
tracker_name: diffusion-dpo-lora
train_batch_size: 1
use_8bit_adam: true
vae_encode_batch_size: 8
validation_steps: 200
variant: null