kohya_ss icon indicating copy to clipboard operation
kohya_ss copied to clipboard

无法训练模型

Open meijun1997 opened this issue 1 year ago • 3 comments

CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64... F:\stable\kohya\kohya_ss\venv\lib\site-packages\bitsandbytes\cuda_setup\paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')} warn( WARNING: No libcudart.so found! Install CUDA or the cudatoolkit package (anaconda)! CUDA SETUP: Loading binary F:\stable\kohya\kohya_ss\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cpu.so... Traceback (most recent call last): File "F:\stable\kohya\kohya_ss\train_network.py", line 659, in train(args) File "F:\stable\kohya\kohya_ss\train_network.py", line 171, in train optimizer_name, optimizer_args, optimizer = train_util.get_optimizer(args, trainable_params) File "F:\stable\kohya\kohya_ss\library\train_util.py", line 1719, in get_optimizer import bitsandbytes as bnb File "F:\stable\kohya\kohya_ss\venv\lib\site-packages\bitsandbytes_init_.py", line 6, in from .autograd._functions import ( File "F:\stable\kohya\kohya_ss\venv\lib\site-packages\bitsandbytes\autograd_functions.py", line 5, in import bitsandbytes.functional as F File "F:\stable\kohya\kohya_ss\venv\lib\site-packages\bitsandbytes\functional.py", line 13, in from .cextension import COMPILED_WITH_CUDA, lib File "F:\stable\kohya\kohya_ss\venv\lib\site-packages\bitsandbytes\cextension.py", line 41, in lib = CUDALibrary_Singleton.get_instance().lib File "F:\stable\kohya\kohya_ss\venv\lib\site-packages\bitsandbytes\cextension.py", line 37, in get_instance cls.instance.initialize() File "F:\stable\kohya\kohya_ss\venv\lib\site-packages\bitsandbytes\cextension.py", line 31, in initialize self.lib = ct.cdll.LoadLibrary(binary_path) File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\ctypes_init.py", line 452, in LoadLibrary return self.dlltype(name) File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\ctypes_init.py", line 364, in init if '/' in name or '\' in name: TypeError: argument of type 'WindowsPath' is not iterable Traceback (most recent call last): File "C:\Users\Administrator\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\Administrator\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in run_code exec(code, run_globals) File "F:\stable\kohya\kohya_ss\venv\Scripts\accelerate.exe_main.py", line 7, in File "F:\stable\kohya\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main args.func(args) File "F:\stable\kohya\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command simple_launcher(args) File "F:\stable\kohya\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 '['F:\stable\kohya\kohya_ss\venv\Scripts\python.exe', 'train_network.py', '--pretrained_model_name_or_path=runwayml/stable-diffusion-v1-5', '--train_data_dir=F:/stable/train/catmodel/image', '--resolution=512,512', '--output_dir=F:/stable/train/catmodel/model', '--logging_dir=F:/stable/train/catmodel/log', '--network_alpha=128', '--save_model_as=safetensors', '--network_module=networks.lora', '--text_encoder_lr=5e-5', '--unet_lr=0.0001', '--network_dim=128', '--output_name=Addams', '--lr_scheduler_num_cycles=1', '--learning_rate=0.0001', '--lr_scheduler=constant', '--train_batch_size=1', '--max_train_steps=1500', '--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=1234', '--caption_extension=.txt', '--cache_latents', '--optimizer_type=AdamW8bit', '--max_data_loader_n_workers=1', '--clip_skip=2', '--bucket_reso_steps=64', '--mem_eff_attn', '--gradient_checkpointing', '--xformers', '--bucket_no_upscale']' returned non-zero exit status 1.

meijun1997 avatar Mar 15 '23 01:03 meijun1997

一摸一样的情况,估计是新版本的问题

yifenglv46 avatar Mar 15 '23 10:03 yifenglv46

各位我找到好消息了,他們使用的顯卡30系或40系lora訓練是沒問題的,他們更不知道10系或16系還有人在用,所以作者呢把kohya_ss設定為30系或40系的設定,所以我們沒有辦法訓練lora。

來首先點擊Dreambooth LoRA點擊Training parameters 然後你會看到AdamW8bit設定選擇AdamW 還有你會看到Gradient checkpointing和Memory efficient attention跟它打√就對了。

希望這個設定對你們有幫助。

FinaBro69 avatar Mar 17 '23 17:03 FinaBro69

各位我找到好消息了,他們使用的顯卡30系或40系lora訓練是沒問題的,他們更不知道10系或16系還有人在用,所以作者呢把kohya_ss設定為30系或40系的設定,所以我們沒有辦法訓練lora。

來首先點擊Dreambooth LoRA點擊Training parameters 然後你會看到AdamW8bit設定選擇AdamW 還有你會看到Gradient checkpointing和Memory efficient attention跟它打√就對了。

希望這個設定對你們有幫助。

It doesn't work~BRO~

Big-ANGELO avatar Mar 25 '23 10:03 Big-ANGELO

@FinaBro69 worked for me

Chasexj avatar Mar 27 '23 18:03 Chasexj

各位我找到好消息了,他們使用的顯卡30系或40系lora訓練是沒問題的,他們更不知道10系或16系還有人在用,所以作者呢把kohya_ss設定為30系或40系的設定,所以我們沒有辦法訓練lora。

來首先點擊Dreambooth LoRA點擊Training parameters 然後你會看到AdamW8bit設定選擇AdamW 還有你會看到Gradient checkpointing和Memory efficient attention跟它打√就對了。

希望這個設定對你們有幫助。

解决了我的问题,终于开始训练了

lamboJw avatar Apr 02 '23 09:04 lamboJw