Using seed: 40529315 Running with params: ['accelerate', 'launch', 'train_text_to_image_lora.py', '--pretrained_model_name_or_path', 'runwayml/stable-diffusion-v1-5', '--dataset_name', 'lambdalabs/naruto-blip-captions', '--dataloader_num_workers', '8', '--resolution', '512', '--center_crop', '--random_flip', '--train_batch_size', '1', '--num_train_epochs', '100', '--gradient_accumulation_steps', '4', '--max_train_steps', '1000', '--checkpointing_steps', '1001', '--learning_rate', '0.0001', '--max_grad_norm', '1.0', '--lr_scheduler', 'cosine', '--lr_warmup_steps', '0', '--output_dir', '/tmp/train-t2i-lora', '--validation_prompt', 'A naruto with blue eyes.', '--seed', '40529315'] The following values were not passed to `accelerate launch` and had defaults used instead: `--num_processes` was set to a value of `1` `--num_machines` was set to a value of `1` `--mixed_precision` was set to a value of `'no'` `--dynamo_backend` was set to a value of `'no'` To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`. /root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/accelerate/accelerator.py:406: UserWarning: `log_with=tensorboard` was passed but no supported trackers are currently installed. warnings.warn(f"`log_with={log_with}` was passed but no supported trackers are currently installed.") 07/28/2024 20:35:39 - INFO - __main__ - Distributed environment: NO Num processes: 1 Process index: 0 Local process index: 0 Device: cuda Mixed precision type: no {'thresholding', 'sample_max_value', 'prediction_type', 'rescale_betas_zero_snr', 'timestep_spacing', 'dynamic_thresholding_ratio', 'variance_type', 'clip_sample_range'} was not found in config. Values will be initialized to default values. {'force_upcast', 'scaling_factor', 'use_post_quant_conv', 'use_quant_conv', 'latents_mean', 'latents_std', 'shift_factor'} was not found in config. Values will be initialized to default values. {'encoder_hid_dim', 'conv_out_kernel', 'upcast_attention', 'num_attention_heads', 'mid_block_only_cross_attention', 'cross_attention_norm', 'conv_in_kernel', 'addition_embed_type', 'addition_time_embed_dim', 'num_class_embeds', 'mid_block_type', 'time_embedding_type', 'encoder_hid_dim_type', 'only_cross_attention', 'transformer_layers_per_block', 'dual_cross_attention', 'reverse_transformer_layers_per_block', 'attention_type', 'time_embedding_act_fn', 'class_embed_type', 'resnet_time_scale_shift', 'projection_class_embeddings_input_dim', 'time_cond_proj_dim', 'timestep_post_act', 'class_embeddings_concat', 'resnet_out_scale_factor', 'resnet_skip_time_act', 'use_linear_projection', 'addition_embed_type_num_heads', 'time_embedding_dim', 'dropout'} was not found in config. Values will be initialized to default values. Downloading readme: 0%| | 0.00/1.02k [00:00