Update README.md

README.md

@@ -41,7 +41,7 @@ This model is still in its infancy and it's meant to be constantly updated and t
     - [vae.sygil_muse_v0.1.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.sygil_muse_v0.1.pt): Trained from scratch for 3.0M steps with **dim: 128** and **vq_codebook_size: 256**.
     - [maskgit.sygil_muse_v0.1.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/maskgit.sygil_muse_v0.1.pt): Maskgit trained from the VAE for 3.46M steps
   - #### Beta:
-    - [vae.932300.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.932300.pt): Trained from scratch for 932K steps and higher **vq_codebook_size** than before.
+    - [vae.1245400.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.1245400.pt): Trained from scratch for 1.24M steps and higher **vq_codebook_size** than before.
     - [maskgit.10000.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/maskgit.10000.pt): Maskgit trained from the VAE for 10K 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
@@ -56,25 +56,21 @@ The model was trained on the following dataset:
 **Hardware and others**
 - **Hardware:** 1 x Nvidia RTX 3050 GPU
 - **Hours Trained:** NaN.
-- **Gradient Accumulations**: 1
+- **Gradient Accumulations**: 5
 - **Batch:** 1
-- **Learning Rate:** 1e-04
-- **Learning Rate Scheduler:** `cosine_with_restarts`
+- **Learning Rate:** 1e-4
+- **Learning Rate Scheduler:** `constant_with_warmup`
 - **Optimizer:** Adam
-- **Weight Decay:** 1e-4
 - **Warmup Steps:** 10,000
 - **Number of Cycles:** 100
 - **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:** 8192
-- **Total Training Steps:** 932,300
+- **Total Training Steps:** 1,245,400
 
   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.
 
 Developed by: [ZeroCool](https://github.com/ZeroCool940711) at [Sygil-Dev](https://github.com/Sygil-Dev/)
 
-## Community Contributions:
-  - [Chad Kensington (isamu isozaki)](https://github.com/isamu-isozaki/muse-maskgit-pytorch): Thanks for helping with the training scripts and improving the code for Muse.
-
 # License
 This model is open access and available to all, with a CreativeML Open RAIL++-M License further specifying rights and usage.