fix

README.md

@@ -153,18 +153,18 @@ VAE: Changed, new VAE - [EQB7](https://huggingface.co/Anzhc/MS-LC-EQ-D-VR_VAE) w
 (Base / quality-tuned)
 
 **Samples seen**(unbatched steps): ~2kk / ~400k  
-**Learning Rate**: 2e-5 / 2e-5
-**Effective Batch size**: 1280 (40 real * 4 accum * 8 devices) / 1280 (40 * 4 * 8)
-**Precision**: Full BF16
-**Optimizer**: AdamW8bit with Kahan Summation
+**Learning Rate**: 2e-5 / 2e-5  
+**Effective Batch size**: 1280 (40 real * 4 accum * 8 devices) / 1280 (40 * 4 * 8)  
+**Precision**: Full BF16  
+**Optimizer**: AdamW8bit with Kahan Summation  
 **Weight Decay**: 0.01  
-**Schedule**: Constant with warmup
+**Schedule**: Constant with warmup  
 **Timestep Sampling Strategy**: Logit-Normal (sometimes referred to as Lognorm), Shift 2.5  
-**Text Encoders**: Frozen
+**Text Encoders**: Frozen  
 **Keep Token**: False (Used "Protected Tags" instead), all tags are shuffled.  
-**Tag Dropout**: 10%
+**Tag Dropout**: 10%  
 **Uncond Dropout**: 10%  
-**Optimal Transport**: True
+**Optimal Transport**: True  
 
 
 
@@ -193,13 +193,13 @@ My current style training settings (Anzhc):
 **Schedule**: ReREX (Use REX for simplicity)  
 **Precision**: Full BF16  
 **Weight Decay**: 0.02  
-**Timestep Sampling Strategy**: Logit-Normal, Shift 2.5 (Closest to what i use result-wise)
+**Timestep Sampling Strategy**: Logit-Normal, Shift 2.5 (Closest to what i use result-wise)  
 
-**Dim/Alpha/Conv/Alpha**: 24/24/24/24 (Lycoris/Locon)
+**Dim/Alpha/Conv/Alpha**: 24/24/24/24 (Lycoris/Locon)  
 
-**Text Encoders**: Frozen
+**Text Encoders**: Frozen  
 
-**Optimal Transport**: True
+**Optimal Transport**: True  
 
 **Expected Dataset Size**: 100 images (Can be even 10, but balance with repeats to roughly this target.)  
 **Epochs**: 50 (Yes, even with 10 repeats. 500 effective epochs works just fine and doesn't break from my tests.)