bmaltais / kohya_ss

Apache License 2.0
9.38k stars 1.21k forks source link

cant start training File "D:\KohyaNew\kohya_ss\kohya_gui\lora_gui.py", line 994, in train_model if max_train_steps > 0 and stop_text_encoder_training > 0: TypeError: '>' not supported between instances of 'NoneType' and 'int' #2817

Open DarkViewAI opened 1 week ago

DarkViewAI commented 1 week ago

12:08:38-630149 INFO Dataset config TOML file used; skipping calculations for total_steps, train_batch_size, gradient_accumulation_steps, epoch, reg_factor, and max_train_steps. Traceback (most recent call last): File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\queueing.py", line 536, in process_events response = await route_utils.call_process_api( File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\route_utils.py", line 321, in call_process_api output = await app.get_blocks().process_api( File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\blocks.py", line 1935, in process_api result = await self.call_function( File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\blocks.py", line 1520, in call_function prediction = await anyio.to_thread.run_sync( # type: ignore File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\anyio_backends_asyncio.py", line 2177, in run_sync_in_worker_thread return await future File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\anyio_backends_asyncio.py", line 859, in run result = context.run(func, args) File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\utils.py", line 826, in wrapper response = f(args, **kwargs) File "D:\KohyaNew\kohya_ss\kohya_gui\lora_gui.py", line 994, in train_model if max_train_steps > 0 and stop_text_encoder_training > 0: TypeError: '>' not supported between instances of 'NoneType' and 'int'

DarkViewAI commented 1 week ago

works on this commit 7531b36cbde9bd152c45d877a459437c6c82d5f0

not sure what has changed

bmaltais commented 1 week ago

I pushed a fix for it. Give it a try

DarkViewAI commented 1 week ago

@bmaltais

seem to be getting this now

Traceback (most recent call last): File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\queueing.py", line 536, in process_events response = await route_utils.call_process_api( File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\route_utils.py", line 321, in call_process_api output = await app.get_blocks().process_api( File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\blocks.py", line 1935, in process_api result = await self.call_function( File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\blocks.py", line 1520, in call_function prediction = await anyio.to_thread.run_sync( # type: ignore File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\anyio_backends_asyncio.py", line 2177, in run_sync_in_worker_thread return await future File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\anyio_backends_asyncio.py", line 859, in run result = context.run(func, args) File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\utils.py", line 826, in wrapper response = f(args, **kwargs) File "D:\KohyaNew\kohya_ss\kohya_gui\lora_gui.py", line 1014, in train_model log.info(max_train_steps_info) UnboundLocalError: local variable 'max_train_steps_info' referenced before assignment

bmaltais commented 1 week ago

OK, I have reverted a bunch of updates. Give it a try now.

DarkViewAI commented 1 week ago

@bmaltais thank you very much! works now :)