adam_beta1: 0.9 | |
adam_beta2: 0.999 | |
adam_epsilon: 1.0e-08 | |
adam_weight_decay: 0.01 | |
allow_tf32: false | |
cache_dir: null | |
center_crop: false | |
checkpointing_steps: 10000 | |
checkpoints_total_limit: 3 | |
conditioning_dropout_prob: 0.05 | |
dataloader_num_workers: 16 | |
dataset_config_name: null | |
dataset_name: pilancilab/Audio_inpainting_combined_data | |
edit_prompt_column: edit_prompt | |
edited_image_column: edited_image | |
enable_xformers_memory_efficient_attention: false | |
gradient_accumulation_steps: 1 | |
gradient_checkpointing: false | |
hub_model_id: null | |
hub_token: null | |
learning_rate: 1.0e-05 | |
local_rank: -1 | |
logging_dir: logs | |
lr_scheduler: constant | |
lr_warmup_steps: 500 | |
max_grad_norm: 1.0 | |
max_train_samples: null | |
max_train_steps: 150000 | |
mixed_precision: null | |
non_ema_revision: null | |
num_train_epochs: 15 | |
num_validation_images: 4 | |
original_image_column: original_image | |
output_dir: ./data/pix2pix-riff-ckpt | |
pretrained_model_name_or_path: riffusion/riffusion-model-v1 | |
push_to_hub: false | |
random_flip: false | |
report_to: tensorboard | |
resolution: 256 | |
resume_from_checkpoint: latest | |
revision: null | |
scale_lr: false | |
seed: 0 | |
train_batch_size: 4 | |
train_data_dir: null | |
use_8bit_adam: false | |
use_ema: false | |
val_image_url: null | |
validation_epochs: 1 | |
validation_prompt: null | |