Update README.md

README.md

@@ -40,7 +40,7 @@ This model is still in its infancy and it's meant to be constantly updated and t
   - #### Stable:
     - No stable version available right now.
   - #### Beta:
-    - [vae.2700500.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.2700500.pt): Trained from scratch for 2.70M steps
+    - [vae.2731500.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.2731500.pt): Trained from scratch for 2.73M steps
     - [maskgit.1206000.p](https://huggingface.co/Sygil/Sygil-Muse/blob/main/maskgit.1206000.pt): Maskgit trained from the VAE for 1.20M steps
   
   Note: Checkpoints under the Beta section are updated daily or at least 3-4 times a week. While the beta checkpoints can be used as they are only the latest version is kept on the repo and the older checkpoints are removed when a new one
@@ -55,14 +55,17 @@ The model was trained on the following dataset:
 **Hardware and others**
 - **Hardware:** 1 x Nvidia RTX 3050 GPU
 - **Hours Trained:** NaN.
-- **Gradient Accumulations**: 10
+- **Gradient Accumulations**: 1
 - **Batch:** 1
-- **Learning Rate:** 7e-08
+- **Learning Rate:** 7e-04
+- **Learning Rate Scheduler:** `cosine_with_restarts`
+- **Optimizer:** Lion
+- **Weight Decay:** 1e-2
 - **Warmup Steps:** 10,000
 - **Resolution/Image Size**: First trained at a resolution of 64x64, then increased to 256x256 and then to 512x512. Check the notes down below for more details on this.
 - **Dimension:** 128
 - **vq_codebook_size:** 256
-- **Total Training Steps:** 2,700,500
+- **Total Training Steps:** 2,731,500
 
   Note: On Muse we can change the image_size or resolution at any time without having to train the model from scratch again, this allows us to first train the model at low resolution using the same `dim` and `vq_codebook_size` to train faster and then we can increase the `image_size` and use a higher resolution once the model has trained enough.