Software Engineering Courses (SECourses)•15mo ago

if my computer unexpectedly reboots while training, is there a possibillity to resume process or do

if my computer unexpectedly reboots while training, is there a possibillity to resume process or do i jave to start over?

Ddeepblue_1337 if my computer unexpectedly reboots while training, is there a possibillity to r...

Furkan Gözükara SECourses•10/13/24, 10:41 AM

you have to restart

Furkan Gözükara SECourses•10/13/24, 10:41 AM

you can use latest fine tuning checkpoint

Furkan Gözükara SECourses•10/13/24, 10:41 AM

for lora there is lora weights but i dont know if working

Furkan Gözükara SECourses•10/13/24, 10:42 AM

if it is running on massed cokmpute or runpod, you can even close your computer

Furkan Gözükara SECourses•10/13/24, 10:42 AM

they run on cloud

deepblue_1337OP•10/13/24, 10:48 AM

you mention somewhere that you have a discount on massed compute, is that right? if yes how/where?

thanks

Ddeepblue_1337 you mention somewhere that you have a discount on massed compute, is that right?...

Furkan Gözükara SECourses•10/13/24, 10:49 AM

select A6000 GPU

Furkan Gözükara SECourses•10/13/24, 10:49 AM

use SECourses coupon

deepblue_1337OP•10/13/24, 10:56 AM

did you ever use fluxgym? As far as I understand it does also use Kohya, but has a (more or less) one-klick setup?

deepblue_1337OP•10/13/24, 10:58 AM

or any thoughts on providing a script that installs all dependencies and starts the program by yourself? I am a computer engineer (by training) myself, though out of the industry for >20years, and the setup usage could be made massively easier (especially for non-technical people)

deepblue_1337OP•10/13/24, 10:58 AM

just as suggestions, otherwise your content is great

FFurkan Gözükara SECourses 0.004 is 1000 times bigger LR

druhl•10/13/24, 11:48 AM

I associated bigger with faster. He said his checkpoint was taking too much time to train, but I assumed if I use 0.0004 instead of 0.000004, I train faster.

druhl•10/13/24, 11:49 AM

But then he mentioned it also has something to do with his lora rank selection of 128.

Ddeepblue_1337 did you ever use fluxgym? As far as I understand it does also use Kohya, but has...

Furkan Gözükara SECourses•10/13/24, 11:53 AM

we are already 1 click setup you just set your folder paths

Ddruhl I associated bigger with faster. He said his checkpoint was taking too much time...

Furkan Gözükara SECourses•10/13/24, 11:54 AM

ye when you change lora alpha you pratically changes your LR

Charkel•10/13/24, 12:36 PM

Hi @Dr. Furkan Gözükara
running massed compute instance
ran the swarmUI updater
Ran the install Flux models script from forge_installer_v2
Now when i try to load a model and generate a image it fails the backend.

Here is log https://paste.denizenscript.com/View/127224

SwarmUI v0.9.3.1 Server Log - 2024-10-13 12:34:24 | Paste #127224 |...

Content of Swarm Debug Log Paste #127224: SwarmUI v0.9.3.1 Server Log - 2024-10-13 12:34:24SwarmUI v0.9.3.1 Server Log - 2024-10-13 12:34:24... pasted 2024/10/13 05:34:24 UTC-07:002024/10/13 05:34:24 UTC-07:00, Paste length: 32083 characters across 281 lines32083 characters across 281 lines, Content: 2024-10-13 12:26:52.083 [Init] === SwarmUI v0.9.3.1 Starting at 2024-10-13 12:26:52 ===2024-10-13 12...2024-10-13 12:26:52.083 [Init] === SwarmUI v0.9.3.1 Starting at 2024-10-13 12:26:52 ===2024-10-13 12...