bmaltais
commented
1 year ago This error message is a Python traceback, which indicates that an error has occurred while executing a Python program. The error message suggests that there is a problem with loading PyTorch weights from a checkpoint file for the 'openai/clip-vit-large-patch14' model. Specifically, the error message suggests that the PyTorch checkpoint file is not in the expected format or is corrupted, which is preventing the weights from being loaded.
Sansblaze
mlsjla
Traceback (most recent call last): File "D:\code\test\kohya_ss\venv\lib\site-packages\transformers\modeling_utils.py", line 415, in load_state_dict return torch.load(checkpoint_file, map_location="cpu") File "D:\code\test\kohya_ss\venv\lib\site-packages\torch\serialization.py", line 705, in load with _open_zipfile_reader(opened_file) as opened_zipfile: File "D:\code\test\kohya_ss\venv\lib\site-packages\torch\serialization.py", line 242, in init super(_open_zipfile_reader, self).init(torch._C.PyTorchFileReader(name_or_buffer)) RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "D:\code\test\kohya_ss\venv\lib\site-packages\transformers\modeling_utils.py", line 419, in load_state_dict if f.read(7) == "version": UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 64: illegal multibyte sequence
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "D:\code\test\kohya_ss\train_network.py", line 724, in
train(args)
File "D:\code\test\kohya_ss\train_network.py", line 135, in train
textencoder, vae, unet, = train_util.load_target_model(
File "D:\code\test\kohya_ss\library\train_util.py", line 2649, in load_target_model
text_encoder, vae, unet = model_util.load_models_from_stable_diffusion_checkpoint(args.v2, name_or_path, device)
File "D:\code\test\kohya_ss\library\model_util.py", line 898, in load_models_from_stable_diffusion_checkpoint
text_model = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14").to(device)
File "D:\code\test\kohya_ss\venv\lib\site-packages\transformers\modeling_utils.py", line 2301, in from_pretrained
state_dict = load_state_dict(resolved_archive_file)
File "D:\code\test\kohya_ss\venv\lib\site-packages\transformers\modeling_utils.py", line 431, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for 'C:\Users\MJ/.cache\huggingface\hub\models--openai--clip-vit-large-patch14\snapshots\8d052a0f05efbaefbc9e8786ba291cfdf93e5bff\pytorch_model.bin' at 'C:\Users\MJ/.cache\huggingface\hub\models--openai--clip-vit-large-patch14\snapshots\8d052a0f05efbaefbc9e8786ba291cfdf93e5bff\pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
Traceback (most recent call last):
File "C:\Users\MJ\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\MJ\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "D:\code\test\kohya_ss\venv\Scripts\accelerate.exe__main__.py", line 7, in
File "D:\code\test\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
args.func(args)
File "D:\code\test\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command
simple_launcher(args)
File "D:\code\test\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 567, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['D:\code\test\kohya_ss\venv\Scripts\python.exe', 'train_network.py', '--pretrained_model_name_or_path=D:/code/novelai-webui-aki-v3/models/Stable-diffusion/CounterfeitV25_25.safetensors', '--train_data_dir=D:/code/test/train/image', '--resolution=512,512', '--output_dir=D:/code/test/train/model', '--logging_dir=D:/code/test/train/log', '--network_alpha=1', '--save_model_as=safetensors', '--network_module=networks.lora', '--text_encoder_lr=5e-5', '--unet_lr=0.0001', '--network_dim=8', '--output_name=last', '--lr_scheduler_num_cycles=1', '--learning_rate=0.0001', '--lr_scheduler=cosine', '--lr_warmup_steps=230', '--train_batch_size=1', '--max_train_steps=2300', '--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--cache_latents', '--optimizer_type=AdamW8bit', '--max_data_loader_n_workers=0', '--bucket_reso_steps=64', '--xformers', '--bucket_no_upscale']' returned non-zero exit status 1.