OutOfMemoryError: CUDA out of memory (WHY?)

Why am I getting put of memory? I made a script.py that is a copy of the "dreambooth_joepenna.ipynb" Notebook and everything goes well until training is about to start, why? I am using it on 3090's instances created in vast.ai with pytorch:latest

I also modified download_model.py and setup_training.py to NOT work as a form and accept args prom my script.py as you can see in the fork I did

Any ideo on how to do this?

This is the ERROR/LOG:

gpu_vram: 23.69 GB { "class_word": "person", "config_date_time": "2023-07-26T18-37-45", "debug": false, "flip_percent": 0.0, "gpu": 0, "learning_rate": 1e-06, "max_training_steps": 4000, "model_path": "sd_v1-5_vae.ckpt", "model_repo_id": "panopstor/EveryDream", "project_config_filename": "2023-07-26T18-37-45-7777777-config.json", "project_name": "7777777", "regularization_images_folder_path": "Stable-Diffusion-Regularization-Images-person_ddim/person_ddim", "save_every_x_steps": 500, "schema": 1, "seed": 23, "token": "TMF", "token_only": false, "training_images": [ "00003.png", "00004.png", "00005.png", "00006.png", "00007.png", "00008.png", "00009.png", "00010.png", "00011.png", "00012.png", "00013.png", "00014.png", "00015.png", "00016.png", "00017.png", "00018.png", "00019.png", "00020.png", "00021.png", "00022.png" ], "training_images_count": 20, "training_images_folder_path": "./training_images" } ✅ 2023-07-26T18-37-45-7777777-config.json successfully generated. Proceed to training. entrenendo?????????????????????????????????????????? Global seed set to 23 gpu_vram: 23.69 GB Loading model from sd_v1-5_vae.ckpt

LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. making attention of type 'vanilla' with 512 in_channels Working with z of shape (1, 4, 64, 64) = 16384 dimensions. making attention of type 'vanilla' with 512 in_channels Some weights of the model checkpoint at openai/clip-vit-large-patch14 were not used when initializing CLIPTextModel: ['vision_model.embeddings.class_embedding', 'vision_model.encoder.layers.15.mlp.fc1.weight', 'vision_model.encoder.layers.9.layer_norm2.bias', 'vision_model.encoder.layers.0.self_attn.v_proj.bias', 'vision_model.encoder.layers.5.self_attn.v_proj.bias', 'vision_model.encoder.layers.21.mlp.fc2.weight', 'vision_model.encoder.layers.6.mlp.fc2.weight', 'vision_model.encoder.layers.6.layer_norm1.weight', 'vision_model.encoder.layers.3.mlp.fc2.bias', 'vision_model.encoder.layers.0.self_attn.q_proj.weight', 'vision_model.encoder.layers.4.self_attn.out_proj.bias', 'vision_model.encoder.layers.11.mlp.fc1.weight', 'vision_model.encoder.layers.15.mlp.fc2.bias', 'vision_model.encoder.layers.20.self_attn.out_proj.weight', 'vision_model.encoder.layers.11.self_attn.k_proj.weight', 'vision_model.encoder.layers.13.self_attn.v_proj.weight', 'vision_model.encoder.layers.12.self_attn.q_proj.bias', 'vision_model.encoder.layers.16.self_attn.q_proj.bias', 'vision_model.encoder.layers.17.self_attn.q_proj.bias', 'vision_model.encoder.layers.21.self_attn.v_proj.bias', 'vision_model.encoder.layers.19.self_attn.q_proj.bias', 'vision_model.encoder.layers.11.layer_norm1.weight', 'vision_model.encoder.layers.16.layer_norm1.weight', 'vision_model.encoder.layers.1.self_attn.out_proj.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.bias', 'vision_model.encoder.layers.3.self_attn.out_proj.bias', 'vision_model.encoder.layers.1.self_attn.v_proj.weight', 'vision_model.encoder.layers.18.self_attn.q_proj.bias', 'vision_model.encoder.layers.9.mlp.fc2.weight', 'vision_model.encoder.layers.16.self_attn.q_proj.weight', 'vision_model.encoder.layers.2.self_attn.q_proj.weight', 'vision_model.encoder.layers.2.layer_norm2.weight', 'logit_scale', 'vision_model.encoder.layers.1.self_attn.out_proj.bias', 'vision_model.encoder.layers.20.self_attn.out_proj.bias', 'vision_model.encoder.layers.23.self_attn.v_proj.weight', 'vision_model.encoder.layers.12.mlp.fc2.weight', 'vision_model.encoder.layers.5.self_attn.k_proj.bias', 'vision_model.encoder.layers.2.layer_norm1.weight', 'vision_model.encoder.layers.4.self_attn.v_proj.bias', 'vision_model.encoder.layers.13.layer_norm1.weight', 'vision_model.encoder.layers.14.mlp.fc1.bias', 'vision_model.encoder.layers.23.self_attn.out_proj.weight', 'vision_model.encoder.layers.17.layer_norm2.bias', 'vision_model.encoder.layers.9.self_attn.v_proj.weight', 'vision_model.encoder.layers.20.self_attn.v_proj.weight', 'vision_model.encoder.layers.8.self_attn.v_proj.bias', 'vision_model.encoder.layers.12.self_attn.v_proj.bias', 'vision_model.encoder.layers.8.layer_norm1.bias', 'vision_model.encoder.layers.9.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.mlp.fc1.bias', 'vision_model.encoder.layers.3.mlp.fc1.bias', 'vision_model.encoder.layers.7.self_attn.v_proj.weight', 'vision_model.encoder.layers.7.self_attn.out_proj.bias', 'vision_model.encoder.layers.7.self_attn.q_proj.weight', 'vision_model.encoder.layers.12.layer_norm1.bias', 'vision_model.encoder.layers.10.self_attn.v_proj.weight', 'vision_model.encoder.layers.15.mlp.fc1.bias', 'vision_model.encoder.layers.11.mlp.fc2.bias', 'vision_model.encoder.layers.20.self_attn.k_proj.bias', 'vision_model.encoder.layers.23.layer_norm1.weight', 'vision_model.encoder.layers.14.self_attn.v_proj.weight', 'vision_model.encoder.layers.22.layer_norm1.bias', 'vision_model.encoder.layers.17.self_attn.k_proj.bias', 'vision_model.encoder.layers.19.self_attn.k_proj.bias', 'vision_model.encoder.layers.21.self_attn.k_proj.bias', 'vision_model.encoder.layers.12.layer_norm2.weight', 'vision_model.encoder.layers.19.self_attn.v_proj.weight', 'vision_model.encoder.layers.18.self_attn.out_proj.weight', 'vision_model.encoder.layers.5.mlp.fc2.bias', 'vision_model.encoder.layers.2.mlp.fc1.weight', 'vision_model.encoder.layers.1.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.layer_norm2.weight', 'vision_model.encoder.layers.18.self_attn.v_proj.bias', 'vision_model.encoder.layers.18.self_attn.v_proj.weight', 'vision_model.encoder.layers.18.layer_norm1.weight', 'vision_model.encoder.layers.8.self_attn.q_proj.weight', 'vision_model.encoder.layers.14.layer_norm1.weight', 'vision_model.encoder.layers.10.layer_norm2.weight', 'vision_model.encoder.layers.10.self_attn.q_proj.weight', 'vision_model.encoder.layers.15.self_attn.q_proj.bias', 'vision_model.encoder.layers.4.layer_norm1.bias', 'vision_model.encoder.layers.7.layer_norm1.bias', 'vision_model.encoder.layers.6.mlp.fc2.bias', 'vision_model.encoder.layers.9.self_attn.q_proj.weight', 'vision_model.encoder.layers.21.layer_norm1.weight', 'vision_model.encoder.layers.12.mlp.fc2.bias', 'vision_model.encoder.layers.10.self_attn.k_proj.bias', 'vision_model.encoder.layers.5.mlp.fc1.bias', 'vision_model.encoder.layers.15.layer_norm1.bias', 'vision_model.encoder.layers.14.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.self_attn.k_proj.weight', 'vision_model.encoder.layers.16.mlp.fc2.bias', 'vision_model.encoder.layers.2.mlp.fc2.weight', 'vision_model.encoder.layers.2.layer_norm1.bias', 'vision_model.encoder.layers.18.self_attn.q_proj.weight', 'vision_model.encoder.layers.4.layer_norm2.bias', 'vision_model.encoder.layers.0.layer_norm2.weight', 'vision_model.encoder.layers.3.self_attn.q_proj.weight', 'vision_model.encoder.layers.18.mlp.fc1.weight', 'vision_model.post_layernorm.weight', 'vision_model.encoder.layers.2.layer_norm2.bias', 'vision_model.encoder.layers.5.mlp.fc2.weight', 'vision_model.encoder.layers.0.self_attn.v_proj.weight', 'vision_model.encoder.layers.3.self_attn.k_proj.weight', 'vision_model.encoder.layers.20.self_attn.q_proj.bias', 'vision_model.encoder.layers.8.self_attn.k_proj.bias', 'vision_model.encoder.layers.18.layer_norm2.weight', 'vision_model.encoder.layers.2.self_attn.k_proj.weight', 'vision_model.encoder.layers.2.mlp.fc1.bias', 'vision_model.encoder.layers.13.self_attn.v_proj.bias', 'vision_model.encoder.layers.4.mlp.fc1.weight', 'vision_model.encoder.layers.1.layer_norm1.weight', 'vision_model.encoder.layers.20.layer_norm2.weight', 'vision_model.encoder.layers.2.self_attn.q_proj.bias', 'vision_model.encoder.layers.8.self_attn.out_proj.bias', 'vision_model.encoder.layers.23.self_attn.out_proj.bias', 'vision_model.encoder.layers.16.mlp.fc2.weight', 'vision_model.encoder.layers.18.mlp.fc2.weight', 'vision_model.encoder.layers.21.self_attn.q_proj.weight', 'vision_model.encoder.layers.2.self_attn.out_proj.weight', 'vision_model.encoder.layers.20.self_attn.q_proj.weight', 'vision_model.encoder.layers.13.mlp.fc1.weight', 'vision_model.encoder.layers.10.self_attn.k_proj.weight', 'vision_model.encoder.layers.20.layer_norm1.bias', 'vision_model.encoder.layers.16.mlp.fc1.bias', 'vision_model.encoder.layers.0.self_attn.k_proj.weight', 'vision_model.encoder.layers.21.mlp.fc1.bias', 'vision_model.encoder.layers.19.self_attn.q_proj.weight', 'vision_model.encoder.layers.17.mlp.fc1.weight', 'vision_model.encoder.layers.4.mlp.fc2.bias', 'vision_model.encoder.layers.7.self_attn.k_proj.bias', 'vision_model.encoder.layers.10.mlp.fc1.bias', 'vision_model.pre_layrnorm.weight', 'vision_model.encoder.layers.13.mlp.fc1.bias', 'vision_model.encoder.layers.7.mlp.fc1.bias', 'vision_model.encoder.layers.8.self_attn.v_proj.weight', 'vision_model.encoder.layers.16.layer_norm2.weight', 'vision_model.encoder.layers.0.mlp.fc2.weight', 'vision_model.pre_layrnorm.bias', 'vision_model.encoder.layers.8.layer_norm2.bias', 'vision_model.encoder.layers.9.layer_norm1.weight', 'vision_model.encoder.layers.11.layer_norm2.bias', 'vision_model.post_layernorm.bias', 'vision_model.encoder.layers.15.self_attn.k_proj.weight', 'vision_model.encoder.layers.5.layer_norm2.weight', 'visual_projection.weight', 'vision_model.encoder.layers.1.mlp.fc2.weight', 'vision_model.encoder.layers.3.mlp.fc1.weight', 'vision_model.encoder.layers.5.layer_norm1.weight', 'vision_model.encoder.layers.7.layer_norm2.weight', 'vision_model.encoder.layers.23.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.self_attn.out_proj.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.weight', 'vision_model.embeddings.position_ids', 'vision_model.encoder.layers.7.mlp.fc1.weight', 'vision_model.encoder.layers.7.self_attn.q_proj.bias', 'vision_model.encoder.layers.6.self_attn.v_proj.bias', 'vision_model.encoder.layers.9.self_attn.k_proj.bias', 'vision_model.encoder.layers.12.layer_norm1.weight', 'vision_model.encoder.layers.21.self_attn.out_proj.bias', 'vision_model.encoder.layers.22.mlp.fc1.weight', 'vision_model.encoder.layers.3.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.self_attn.out_proj.weight', 'vision_model.encoder.layers.8.mlp.fc2.bias', 'vision_model.encoder.layers.17.self_attn.out_proj.bias', 'vision_model.encoder.layers.11.layer_norm2.weight', 'vision_model.encoder.layers.11.layer_norm1.bias', 'vision_model.encoder.layers.23.layer_norm1.bias', 'vision_model.encoder.layers.18.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.layer_norm2.bias', 'vision_model.encoder.layers.20.mlp.fc2.weight', 'vision_model.encoder.layers.1.layer_norm1.bias', 'vision_model.encoder.layers.14.self_attn.out_proj.bias', 'vision_model.encoder.layers.17.self_attn.v_proj.bias', 'vision_model.encoder.layers.9.self_attn.q_proj.bias', 'vision_model.encoder.layers.0.mlp.fc1.weight', 'vision_model.encoder.layers.18.mlp.fc2.bias', 'vision_model.encoder.layers.21.self_attn.out_proj.weight', 'vision_model.encoder.layers.15.self_attn.v_proj.bias', 'vision_model.encoder.layers.19.self_attn.v_proj.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.bias', 'vision_model.encoder.layers.16.layer_norm2.bias', 'vision_model.encoder.layers.19.self_attn.k_proj.weight', 'vision_model.encoder.layers.7.self_attn.v_proj.bias', 'vision_model.encoder.layers.23.self_attn.k_proj.weight', 'vision_model.encoder.layers.1.layer_norm2.weight', 'vision_model.encoder.layers.7.layer_norm2.bias', 'vision_model.encoder.layers.19.layer_norm1.weight', 'vision_model.encoder.layers.19.layer_norm1.bias', 'vision_model.encoder.layers.2.self_attn.v_proj.weight', 'vision_model.encoder.layers.5.mlp.fc1.weight', 'vision_model.encoder.layers.14.self_attn.k_proj.bias', 'vision_model.encoder.layers.8.layer_norm2.weight', 'vision_model.encoder.layers.19.mlp.fc2.weight', 'vision_model.encoder.layers.12.self_attn.v_proj.weight', 'vision_model.encoder.layers.23.self_attn.v_proj.bias', 'vision_model.encoder.layers.5.self_attn.k_proj.weight', 'vision_model.encoder.layers.21.self_attn.q_proj.bias', 'vision_model.encoder.layers.22.mlp.fc1.bias', 'vision_model.encoder.layers.1.mlp.fc1.bias', 'vision_model.encoder.layers.14.self_attn.q_proj.weight', 'vision_model.encoder.layers.10.mlp.fc2.weight', 'vision_model.encoder.layers.12.layer_norm2.bias', 'vision_model.encoder.layers.7.mlp.fc2.weight', 'vision_model.encoder.layers.16.self_attn.k_proj.bias', 'vision_model.encoder.layers.0.layer_norm2.bias', 'vision_model.encoder.layers.15.self_attn.out_proj.bias', 'vision_model.encoder.layers.7.layer_norm1.weight', 'text_projection.weight', 'vision_model.encoder.layers.1.self_attn.k_proj.bias', 'vision_model.encoder.layers.4.self_attn.k_proj.weight', 'vision_model.encoder.layers.13.layer_norm1.bias', 'vision_model.encoder.layers.5.self_attn.q_proj.bias', 'vision_model.encoder.layers.15.self_attn.q_proj.weight', 'vision_model.encoder.layers.6.self_attn.v_proj.weight', 'vision_model.encoder.layers.22.self_attn.q_proj.weight', 'vision_model.encoder.layers.13.self_attn.out_proj.weight', 'vision_model.encoder.layers.4.layer_norm2.weight', 'vision_model.encoder.layers.21.self_attn.v_proj.weight', 'vision_model.encoder.layers.13.mlp.fc2.weight', 'vision_model.encoder.layers.23.mlp.fc2.weight', 'vision_model.encoder.layers.11.self_attn.v_proj.bias', 'vision_model.encoder.layers.17.self_attn.q_proj.weight', 'vision_model.encoder.layers.20.layer_norm2.bias', 'vision_model.encoder.layers.17.mlp.fc2.weight', 'vision_model.encoder.layers.22.self_attn.out_proj.weight', 'vision_model.encoder.layers.22.self_attn.v_proj.weight', 'vision_model.encoder.layers.8.mlp.fc1.bias', 'vision_model.encoder.layers.9.mlp.fc1.weight', 'vision_model.encoder.layers.11.mlp.fc1.bias', 'vision_model.encoder.layers.6.self_attn.k_proj.bias', 'vision_model.encoder.layers.19.self_attn.out_proj.bias', 'vision_model.encoder.layers.22.mlp.fc2.weight', 'vision_model.encoder.layers.6.self_attn.q_proj.bias', 'vision_model.encoder.layers.9.layer_norm1.bias', 'vision_model.encoder.layers.4.layer_norm1.weight', 'vision_model.encoder.layers.3.self_attn.v_proj.bias', 'vision_model.encoder.layers.14.mlp.fc1.weight', 'vision_model.encoder.layers.6.layer_norm2.bias', 'vision_model.encoder.layers.17.self_attn.v_proj.weight', 'vision_model.encoder.layers.23.self_attn.k_proj.bias', 'vision_model.encoder.layers.20.mlp.fc1.weight', 'vision_model.encoder.layers.10.self_attn.out_proj.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.weight', 'vision_model.encoder.layers.1.layer_norm2.bias', 'vision_model.encoder.layers.14.self_attn.q_proj.bias', 'vision_model.encoder.layers.19.mlp.fc1.bias', 'vision_model.encoder.layers.14.layer_norm1.bias', 'vision_model.encoder.layers.15.self_attn.v_proj.weight', 'vision_model.encoder.layers.22.layer_norm2.weight', 'vision_model.encoder.layers.8.mlp.fc2.weight', 'vision_model.encoder.layers.11.mlp.fc2.weight', 'vision_model.encoder.layers.21.layer_norm2.weight', 'vision_model.encoder.layers.16.self_attn.v_proj.weight', 'vision_model.encoder.layers.16.self_attn.v_proj.bias', 'vision_model.encoder.layers.4.mlp.fc2.weight', 'vision_model.encoder.layers.11.self_attn.out_proj.bias', 'vision_model.encoder.layers.3.mlp.fc2.weight', 'vision_model.encoder.layers.4.self_attn.k_proj.bias', 'vision_model.encoder.layers.23.layer_norm2.weight', 'vision_model.encoder.layers.21.self_attn.k_proj.weight', 'vision_model.encoder.layers.3.layer_norm2.weight', 'vision_model.encoder.layers.13.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.k_proj.weight', 'vision_model.encoder.layers.15.layer_norm2.weight', 'vision_model.encoder.layers.5.layer_norm2.bias', 'vision_model.encoder.layers.14.self_attn.out_proj.weight', 'vision_model.encoder.layers.18.self_attn.out_proj.bias', 'vision_model.encoder.layers.1.self_attn.q_proj.bias', 'vision_model.encoder.layers.4.self_attn.q_proj.bias', 'vision_model.encoder.layers.21.mlp.fc1.weight', 'vision_model.encoder.layers.13.layer_norm2.weight', 'vision_model.encoder.layers.12.self_attn.out_proj.bias', 'vision_model.encoder.layers.16.self_attn.out_proj.bias', 'vision_model.encoder.layers.22.mlp.fc2.bias', 'vision_model.encoder.layers.23.layer_norm2.bias', 'vision_model.encoder.layers.6.mlp.fc1.weight', 'vision_model.encoder.layers.11.self_attn.v_proj.weight', 'vision_model.encoder.layers.19.layer_norm2.weight', 'vision_model.encoder.layers.17.layer_norm1.bias', 'vision_model.encoder.layers.21.layer_norm1.bias', 'vision_model.encoder.layers.10.mlp.fc1.weight', 'vision_model.encoder.layers.3.self_attn.v_proj.weight', 'vision_model.encoder.layers.1.mlp.fc1.weight', 'vision_model.encoder.layers.12.mlp.fc1.bias', 'vision_model.encoder.layers.13.layer_norm2.bias', 'vision_model.encoder.layers.3.layer_norm1.bias', 'vision_model.embeddings.patch_embedding.weight', 'vision_model.encoder.layers.16.self_attn.out_proj.weight', 'vision_model.encoder.layers.15.self_attn.out_proj.weight', 'vision_model.encoder.layers.11.self_attn.k_proj.bias', 'vision_model.encoder.layers.23.mlp.fc2.bias', 'vision_model.encoder.layers.0.layer_norm1.bias', 'vision_model.encoder.layers.7.self_attn.k_proj.weight', 'vision_model.encoder.layers.2.self_attn.out_proj.bias', 'vision_model.encoder.layers.17.mlp.fc2.bias', 'vision_model.encoder.layers.13.self_attn.k_proj.bias', 'vision_model.encoder.layers.19.mlp.fc1.weight', 'vision_model.encoder.layers.3.layer_norm2.bias', 'vision_model.encoder.layers.2.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.self_attn.k_proj.bias', 'vision_model.encoder.layers.20.layer_norm1.weight', 'vision_model.encoder.layers.3.self_attn.q_proj.bias', 'vision_model.encoder.layers.6.self_attn.q_proj.weight', 'vision_model.encoder.layers.8.mlp.fc1.weight', 'vision_model.encoder.layers.22.layer_norm2.bias', 'vision_model.encoder.layers.10.layer_norm1.weight', 'vision_model.encoder.layers.13.self_attn.out_proj.bias', 'vision_model.encoder.layers.9.mlp.fc2.bias', 'vision_model.encoder.layers.10.layer_norm2.bias', 'vision_model.encoder.layers.21.layer_norm2.bias', 'vision_model.encoder.layers.22.self_attn.q_proj.bias', 'vision_model.encoder.layers.14.mlp.fc2.bias', 'vision_model.encoder.layers.14.mlp.fc2.weight', 'vision_model.encoder.layers.22.self_attn.v_proj.bias', 'vision_model.encoder.layers.17.layer_norm1.weight', 'vision_model.encoder.layers.3.self_attn.k_proj.bias', 'vision_model.embeddings.position_embedding.weight', 'vision_model.encoder.layers.22.self_attn.out_proj.bias', 'vision_model.encoder.layers.23.self_attn.q_proj.bias', 'vision_model.encoder.layers.18.layer_norm2.bias', 'vision_model.encoder.layers.10.mlp.fc2.bias', 'vision_model.encoder.layers.20.mlp.fc1.bias', 'vision_model.encoder.layers.10.self_attn.v_proj.bias', 'vision_model.encoder.layers.11.self_attn.q_proj.weight', 'vision_model.encoder.layers.19.layer_norm2.bias', 'vision_model.encoder.layers.0.mlp.fc2.bias', 'vision_model.encoder.layers.12.self_attn.out_proj.weight', 'vision_model.encoder.layers.18.layer_norm1.bias', 'vision_model.encoder.layers.17.layer_norm2.weight', 'vision_model.encoder.layers.10.self_attn.out_proj.bias', 'vision_model.encoder.layers.9.mlp.fc1.bias', 'vision_model.encoder.layers.18.self_attn.k_proj.weight', 'vision_model.encoder.layers.1.mlp.fc2.bias', 'vision_model.encoder.layers.13.mlp.fc2.bias', 'vision_model.encoder.layers.8.self_attn.k_proj.weight', 'vision_model.encoder.layers.4.mlp.fc1.bias', 'vision_model.encoder.layers.16.layer_norm1.bias', 'vision_model.encoder.layers.14.layer_norm2.weight', 'vision_model.encoder.layers.0.mlp.fc1.bias', 'vision_model.encoder.layers.22.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.layer_norm1.weight', 'vision_model.encoder.layers.20.self_attn.v_proj.bias', 'vision_model.encoder.layers.20.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.mlp.fc1.bias', 'vision_model.encoder.layers.8.self_attn.q_proj.bias', 'vision_model.encoder.layers.18.mlp.fc1.bias', 'vision_model.encoder.layers.7.mlp.fc2.bias', 'vision_model.encoder.layers.2.mlp.fc2.bias', 'vision_model.encoder.layers.6.layer_norm2.weight', 'vision_model.encoder.layers.5.layer_norm1.bias', 'vision_model.encoder.layers.12.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.self_attn.v_proj.bias', 'vision_model.encoder.layers.19.mlp.fc2.bias', 'vision_model.encoder.layers.10.layer_norm1.bias', 'vision_model.encoder.layers.5.self_attn.v_proj.weight', 'vision_model.encoder.layers.8.layer_norm1.weight', 'vision_model.encoder.layers.5.self_attn.out_proj.bias', 'vision_model.encoder.layers.23.mlp.fc1.weight', 'vision_model.encoder.layers.10.self_attn.q_proj.bias', 'vision_model.encoder.layers.12.self_attn.k_proj.bias', 'vision_model.encoder.layers.12.mlp.fc1.weight', 'vision_model.encoder.layers.11.self_attn.q_proj.bias', 'vision_model.encoder.layers.6.self_attn.out_proj.bias', 'vision_model.encoder.layers.2.self_attn.v_proj.bias', 'vision_model.encoder.layers.22.self_attn.k_proj.weight', 'vision_model.encoder.layers.15.mlp.fc2.weight', 'vision_model.encoder.layers.16.mlp.fc1.weight', 'vision_model.encoder.layers.4.self_attn.v_proj.weight', 'vision_model.encoder.layers.8.self_attn.out_proj.weight', 'vision_model.encoder.layers.14.layer_norm2.bias', 'vision_model.encoder.layers.20.mlp.fc2.bias', 'vision_model.encoder.layers.19.self_attn.out_proj.weight', 'vision_model.encoder.layers.4.self_attn.q_proj.weight', 'vision_model.encoder.layers.3.layer_norm1.weight', 'vision_model.encoder.layers.16.self_attn.k_proj.weight', 'vision_model.encoder.layers.5.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.v_proj.bias', 'vision_model.encoder.layers.0.self_attn.k_proj.bias', 'vision_model.encoder.layers.11.self_attn.out_proj.weight', 'vision_model.encoder.layers.4.self_attn.out_proj.weight', 'vision_model.encoder.layers.17.self_attn.k_proj.weight', 'vision_model.encoder.layers.9.self_attn.out_proj.weight', 'vision_model.encoder.layers.0.layer_norm1.weight', 'vision_model.encoder.layers.23.mlp.fc1.bias', 'vision_model.encoder.layers.12.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.self_attn.out_proj.weight', 'vision_model.encoder.layers.14.self_attn.v_proj.bias', 'vision_model.encoder.layers.21.mlp.fc2.bias', 'vision_model.encoder.layers.0.self_attn.q_proj.bias', 'vision_model.encoder.layers.5.self_attn.q_proj.weight', 'vision_model.encoder.layers.22.layer_norm1.weight', 'vision_model.encoder.layers.6.layer_norm1.bias'] - This IS expected if you are initializing CLIPTextModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing CLIPTextModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). Restored from sd_v1-5_vae.ckpt with 12 missing and 0 unexpected keys Missing Keys: ['betas', 'alphas_cumprod', 'alphas_cumprod_prev', 'sqrt_alphas_cumprod', 'sqrt_one_minus_alphas_cumprod', 'log_one_minus_alphas_cumprod', 'sqrt_recip_alphas_cumprod', 'sqrt_recipm1_alphas_cumprod', 'posterior_variance', 'posterior_log_variance_clipped', 'posterior_mean_coef1', 'posterior_mean_coef2'] --------------------------- GPU available: True (cuda), used: True TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available: False, using: 0 HPUs LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0] LatentDiffusion: Also optimizing conditioner params! Project config model: base_learning_rate: 1.0e-06 target: ldm.models.diffusion.ddpm.LatentDiffusion params: reg_weight: 1.0 linear_start: 0.00085 linear_end: 0.012 num_timesteps_cond: 1 log_every_t: 200 timesteps: 1000 first_stage_key: image cond_stage_key: caption image_size: 64 channels: 4 cond_stage_trainable: true conditioning_key: crossattn monitor: val/loss_simple_ema scale_factor: 0.18215 use_ema: false embedding_reg_weight: 0.0 unfreeze_model: true model_lr: 1.0e-06 personalization_config: target: ldm.modules.embedding_manager.EmbeddingManager params: placeholder_strings: - '*' initializer_words: - sculpture per_image_tokens: false num_vectors_per_token: 1 progressive_words: false unet_config: target: ldm.modules.diffusionmodules.openaimodel.UNetModel params: image_size: 32 in_channels: 4 out_channels: 4 model_channels: 320 attention_resolutions: - 4 - 2 - 1 num_res_blocks: 2 channel_mult: - 1 - 2 - 4 - 4 num_heads: 8 use_spatial_transformer: true transformer_depth: 1 context_dim: 768 use_checkpoint: true legacy: false first_stage_config: target: ldm.models.autoencoder.AutoencoderKL params: embed_dim: 4 monitor: val/rec_loss ddconfig: double_z: true z_channels: 4 resolution: 512 in_channels: 3 out_ch: 3 ch: 128 ch_mult: - 1 - 2 - 4 - 4 num_res_blocks: 2 attn_resolutions: [] dropout: 0.0 lossconfig: target: torch.nn.Identity cond_stage_config: target: ldm.modules.encoders.modules.FrozenCLIPEmbedder ckpt_path: sd_v1-5_vae.ckpt data: target: main.DataModuleFromConfig params: batch_size: 1 num_workers: 1 wrap: false train: target: ldm.data.personalized.PersonalizedBase params: size: 512 set: train per_image_tokens: false repeats: 100 coarse_class_text: person data_root: ./training_images placeholder_token: TMF token_only: false flip_p: 0.0 reg: target: ldm.data.personalized.PersonalizedBase params: size: 512 set: train reg: true per_image_tokens: false repeats: 10 data_root: Stable-Diffusion-Regularization-Images-person_ddim/person_ddim coarse_class_text: person placeholder_token: TMF validation: target: ldm.data.personalized.PersonalizedBase params: size: 512 set: val per_image_tokens: false repeats: 10 coarse_class_text: person placeholder_token: TMF data_root: ./training_images lightning: modelcheckpoint: params: every_n_train_steps: 500 callbacks: image_logger: target: dreambooth_helpers.callback_helpers.ImageLogger params: batch_frequency: 500 max_images: 8 increase_log_steps: false metrics_over_trainsteps_checkpoint: target: pytorch_lightning.callbacks.ModelCheckpoint params: dirpath: logs/2023-07-26T18-37-45_7777777/ckpts/trainstep_ckpts filename: '{epoch:06}-{step:09}' verbose: true save_top_k: -1 every_n_train_steps: 500 save_weights_only: true trainer: accelerator: gpu devices: 0, benchmark: true accumulate_grad_batches: 1 max_steps: 4000 Lightning config modelcheckpoint: params: every_n_train_steps: 500 callbacks: image_logger: target: dreambooth_helpers.callback_helpers.ImageLogger params: batch_frequency: 500 max_images: 8 increase_log_steps: false metrics_over_trainsteps_checkpoint: target: pytorch_lightning.callbacks.ModelCheckpoint params: dirpath: logs/2023-07-26T18-37-45_7777777/ckpts/trainstep_ckpts filename: '{epoch:06}-{step:09}' verbose: true save_top_k: -1 every_n_train_steps: 500 save_weights_only: true trainer: accelerator: gpu devices: 0, benchmark: true accumulate_grad_batches: 1 max_steps: 4000 | Name | Type | Params --------------------------------------------------------- 0 | model | DiffusionWrapper | 859 M 1 | first_stage_model | AutoencoderKL | 83.7 M 2 | cond_stage_model | FrozenCLIPEmbedder | 123 M --------------------------------------------------------- 982 M Trainable params 83.7 M Non-trainable params 1.1 B Total params 4,264.941 Total estimated model params size (MB) Sanity Checking: 0it [00:00, ?it/s]/opt/conda/lib/python3.10/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:236: PossibleUserWarning: The dataloader, val_dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance. rank_zero_warn( /opt/conda/lib/python3.10/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:236: PossibleUserWarning: The dataloader, train_dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 16 which is the number of cpus on this machine) in the `DataLoader` init to improve performance. rank_zero_warn( Epoch 0: 0%| | 0/2020 [00:00> allocated memory try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF Error training at step 0 Traceback (most recent call last): File "/workspace/Dreambooth-Stable-Diffusion/main.py", line 226, in trainer.fit(model, data) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 696, in fit self._call_and_handle_interrupt( File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 650, in _call_and_handle_interrupt return trainer_fn(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 735, in _fit_impl results = self._run(model, ckpt_path=self.ckpt_path) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1166, in _run results = self._run_stage() File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1252, in _run_stage return self._run_train() File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1283, in _run_train self.fit_loop.run() File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/loop.py", line 200, in run self.advance(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/fit_loop.py", line 271, in advance self._outputs = self.epoch_loop.run(self._data_fetcher) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/loop.py", line 200, in run self.advance(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 203, in advance batch_output = self.batch_loop.run(kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/loop.py", line 200, in run self.advance(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/batch/training_batch_loop.py", line 87, in advance outputs = self.optimizer_loop.run(optimizers, kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/loop.py", line 200, in run self.advance(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 201, in advance result = self._run_optimization(kwargs, self._optimizers[self.optim_progress.optimizer_position]) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 248, in _run_optimization self._optimizer_step(optimizer, opt_idx, kwargs.get("batch_idx", 0), closure) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 358, in _optimizer_step self.trainer._call_lightning_module_hook( File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1550, in _call_lightning_module_hook output = fn(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/core/module.py", line 1705, in optimizer_step optimizer.step(closure=optimizer_closure) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/core/optimizer.py", line 168, in step step_output = self._strategy.optimizer_step(self._optimizer, self._optimizer_idx, closure, **kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/strategies/strategy.py", line 216, in optimizer_step return self.precision_plugin.optimizer_step(model, optimizer, opt_idx, closure, **kwargs) File "/opt/conda/lib/python3.10/site-packages/pytorch_lightning/plugins/precision/precision_plugin.py", line 153, in optimizer_step return optimizer.step(closure=closure, **kwargs) File "/opt/conda/lib/python3.10/site-packages/torch/optim/optimizer.py", line 280, in wrapper out = func(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/torch/optim/optimizer.py", line 33, in _use_grad ret = func(self, *args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/torch/optim/adamw.py", line 171, in step adamw( File "/opt/conda/lib/python3.10/site-packages/torch/optim/adamw.py", line 321, in adamw func( File "/opt/conda/lib/python3.10/site-packages/torch/optim/adamw.py", line 566, in _multi_tensor_adamw denom = torch._foreach_add(exp_avg_sq_sqrt, eps) torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 146.00 MiB (GPU 0; 23.69 GiB total capacity; 21.99 GiB already allocated; 108.94 MiB free; 22.22 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF

JoePenna / Dreambooth-Stable-Diffusion

OutOfMemoryError: CUDA out of memory (WHY?) #194