Software Engineering Courses (SECourses)•6mo ago

Anyone know what would cause my training to just stop randomly? This has happened numerous times sin

Anyone know what would cause my training to just stop randomly? This has happened numerous times since I upgraded to a 5090 a few weeks back. No errors are displayed and there seems to be nothing in particular triggering the event. I reinstalled everything and it runs smoothly...until it just stops and gpu utilization drops to zero. Once this occurs I'm unable to create a backup and have to restart onetrainer and resume from backup. Very frustrating because I have to keep restarting the training and can't leave and let it cook

KKat-e Anyone know what would cause my training to just stop randomly? This has happene...

Furkan Gözükara SECourses•6/29/25, 12:36 AM

yes out of RAM

Furkan Gözükara SECourses•6/29/25, 12:36 AM

it can cause crash

Kat-eOP•6/29/25, 12:40 AM

I just restarted a training and RAM (while it's working is only at 22 (I have 64). VRAM however is at 31.5

KKat-e I just restarted a training and RAM (while it's working is only at 22 (I have 64...

Furkan Gözükara SECourses•6/29/25, 12:50 AM

how much watt you using?

Furkan Gözükara SECourses•6/29/25, 12:50 AM

by the way normally it uses around 28.5gb vram

Furkan Gözükara SECourses•6/29/25, 12:50 AM

if all 1024x1024px

Kat-eOP•6/29/25, 12:59 AM

Watt- fluctuating between 350-500 approximately if I'm looking at it right. I'm doing an SDXL training btw. All 1024x1024, batch size 2, accumulation steps 3 just experimenting. But ever since I installed 5090 Onetrainer just randomly stops responding.

KKat-e Watt- fluctuating between 350-500 approximately if I'm looking at it right. I'm ...

Furkan Gözükara SECourses•6/29/25, 1:02 AM

ah ye that is why

Furkan Gözükara SECourses•6/29/25, 1:02 AM

i really recommend use kohya and our config

Kat-eOP•6/29/25, 1:04 AM

I much prefer onetrainer personally. Which setting is likely tripping it off? I haven't tried your new config yet so maybe that is next

KKat-e I much prefer onetrainer personally. Which setting is likely tripping it off? I ...

Furkan Gözükara SECourses•6/29/25, 1:13 AM

my new config for SDXL though. for FLUX on onetrainer i didnt do much research

Kat-eOP•6/29/25, 1:15 AM

Yea, I do use kohya for FLUX, but recently got back into SDXL. And yes, your new config for SDXL is what I meant. I'm wondering if one of my settings is wonky.

KKat-e Yea, I do use kohya for FLUX, but recently got back into SDXL. And yes, your new...

Furkan Gözükara SECourses•6/29/25, 1:17 AM

ah yes SDXL config is up to date

Furkan Gözükara SECourses•6/29/25, 1:17 AM

but my config is batch size 1

Furkan Gözükara SECourses•6/29/25, 1:17 AM

more batch size and accumulation steps (fake batch size) changes learning rate

Furkan Gözükara SECourses•6/29/25, 1:17 AM

singificantly

Furkan Gözükara SECourses•6/29/25, 1:17 AM

and reduces quality

Kat-eOP•6/29/25, 1:19 AM

So to confirm, with a 5090 you recommend keeping batch size 1 and acc. steps 1 as well correct? I didn't know it reduced quality

KKat-e So to confirm, with a 5090 you recommend keeping batch size 1 and acc. steps 1 a...

Furkan Gözükara SECourses•6/29/25, 1:20 AM

yes

Furkan Gözükara SECourses•6/29/25, 1:20 AM

all 1

Furkan Gözükara SECourses•6/29/25, 1:20 AM

also use newest tier

Furkan Gözükara SECourses•6/29/25, 1:20 AM

tier1_17_GB_fast_v4.json

Kat-eOP•6/29/25, 1:20 AM

Will give it a shot and let you know if perhaps that resolves it! Thanks

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•6/29/25, 7:34 AM

on windows when i run kohya installer, i hit option 1 to install, once i press ENTER, the terminal just closes

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭•6/29/25, 7:38 AM

installation was complete in like 15 seconds, obviously it did not install

Flame火•6/29/25, 5:22 PM

how to change lr_shceduler to cosine in fluxgym? its default to constant with warmup

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭on windows when i run kohya installer, i hit option 1 to install, once i press E...

Furkan Gözükara SECourses•6/29/25, 10:24 PM

you are lacking python

Furkan Gözükara SECourses•6/29/25, 10:25 PM

please follow requirements : https://youtu.be/DrhUHnYfwC0

YouTubeSECourses

How to Install Python, CUDA, cuDNN, C++ Build Tools, FFMPEG & Git T...

If you are interested in using AI, generative AI applications, open source applications in your computer, than this is the most fundamental and important tutorial that you need. In this tutorial I show and explain how to properly install appropriate Python versions accurately, how to switch between different Python versions, how to install diffe...

FFlame火 how to change lr_shceduler to cosine in fluxgym? its default to constant with wa...

Furkan Gözükara SECourses•6/29/25, 10:25 PM

i never used fluxgym

FFurkan Gözükara SECourses i never used fluxgym

Flame火•6/30/25, 8:15 PM

what do you suggest using?

Flame火•6/30/25, 8:16 PM

for lora training

Flame火•6/30/25, 8:16 PM

ive 48gb vram but with fluxgym im unable to fully utilize it. its only using 20gb vram

FFlame火 what do you suggest using?

Furkan Gözükara SECourses•7/1/25, 12:12 AM

kohya

FFlame火 ive 48gb vram but with fluxgym im unable to fully utilize it. its only using 20g...

Furkan Gözükara SECourses•7/1/25, 12:12 AM

for 48 gb we have batch size 7 dreambooth config

Furkan Gözükara SECourses•7/1/25, 12:12 AM

fully utilizes the GPU

Furkan Gözükara SECourses•7/1/25, 12:13 AM

https://youtu.be/FvpWy1x5etM

YouTubeSECourses

FLUX Full Fine-Tuning / DreamBooth Training Master Tutorial for Win...

If you want to train FLUX with maximum possible quality, this is the tutorial looking for. In this comprehensive tutorial, you will learn how to install Kohya GUI and use it to fully Fine-Tune / DreamBooth FLUX model. After that how to use SwarmUI to compare generated checkpoints / models and find the very best one to generate most amazing image...

Furkan Gözükara SECourses•7/1/25, 12:13 AM

if you want lora it is here https://youtu.be/nySGu12Y05k

YouTubeSECourses

FLUX LoRA Training Simplified: From Zero to Hero with Kohya SS GUI ...

Ultimate Kohya GUI FLUX LoRA training tutorial. This tutorial is product of non-stop 9 days research and training. I have trained over 73 FLUX LoRA models and analyzed all to prepare this tutorial video. The research still going on and hopefully the results will be significantly improved and latest configs and findings will be shared. Please wat...

ghstoic•7/1/25, 8:10 AM

Have an 3090 and recently did a fresh install of Kohya, followed by 'Windows_RTX5000_Series_Upgrade_Run_After_Install_Finished.bat', and previously my speed was ~8s/it but now its ~11s/it. Tried reverting and doing fresh installs again but the same issue. Any idea on what's the best way to debug what's causing this?