Mirrors
/
EveryDream2trainer
mirror of https://github.com/victorchall/EveryDream2trainer.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update OPTIMIZER.md

This commit is contained in:
Victor Hall 2023-05-06 00:54:47 -04:00 committed by GitHub
parent cb511025ed
commit 4c5ce81b31
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
doc/OPTIMIZER.md
View File

@ -16,7 +16,7 @@ If you do not set `optimizer_config` at all or set it to `null` in train.json, t
## Optimizers
In `optimizer.json` the you can set independent optimizer settings for both the text encoder and unet. If you want shared settings, just fill out the `unet` section and leave `text_encoder` properties null an they will be copied from the `unet` section, only respecting `text_encoder_lr_scale` if set.
In `optimizer.json` the you can set independent optimizer settings for both the text encoder and unet. If you want shared settings, just fill out the `base` section and leave `text_encoder_overrides` properties null an they will be copied from the `base` section.
If you set the `text_encder_lr_scale` property, the text encoder will be trained with a multiple of the Unet learning rate if it the LR is being copied. If you explicitly set the text encoder LR, the `text_encder_lr_scale` is ignored. `text_encder_lr_scale` is likely to be deprecated in the future, but now is left for backwards compatibility.