Update README.md

README.md

@@ -121,3 +121,24 @@ body {
   2. Source Code Accessibility: If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.
   3. Distribution Terms: Any distribution must be under this license or another with similar rules.
 
+
+## とれーにんぐ Training  
+
+These are the key hyperparameters used during training:
+
+  | Feature                       | FT             |
+|-------------------------------|----------------------------|
+| **Hardware**                  | 4090 24GB PCIe          |
+| **Batch Size**                | 12                         |
+| **Gradient Accumulation Steps** | 1                        |
+| **Noise Offset**              | 0.035                       |
+| **Epochs**                    | 10                         |
+| **UNet Learning Rate**        | 2.1e-6                       |
+| **Text Encoder Learning Rate** | 1.5e-7                   |
+| **Optimizer**                 | Adafactor                  |
+| **Optimizer Args**            | Scale Parameter: False, Relative Step: False, Warmup Init: False |
+| **Scheduler**                 | Constant with Warmups      |
+| **image**              | 6300image                       |
+
+
+