Update README.md

README.md

@@ -20,10 +20,10 @@ This model is the primary output of the paper: **"Visual Reasoning Transfer: Lev
 
 The model does not generate images. Instead, it acts as a dynamics engine in latent space. When given a latent representation of a physical state (encoded as a "spatial field image"), it predicts the latent representation of the next physical state.
 
-This LoRA (final) was trained for 15,000 steps on a synthetic dataset of 10,000 N-body trajectories.
+This LoRA was trained for 15,000 steps on a synthetic dataset of 10,000 N-body trajectories.
 
 *   **Research Project Repository:** [https://github.com/sandner-art/SC-Visual-Reasoning](https://github.com/sandner-art/SC-Visual-Reasoning)
-*   **Training Dataset:** [huggingface.co/datasets/sandner/n-body-trajectories-for-vrlora](https://huggingface.co/datasets/YourUsername/n-body-trajectories-for-vrlora) (Replace with your link)
+*   **Training Dataset:** [huggingface.co/datasets/YourUsername/n-body-trajectories-for-vrlora](https://huggingface.co/datasets/YourUsername/n-body-trajectories-for-vrlora) (Replace with your link)
 
 ## How to Use
 
@@ -42,4 +42,19 @@ pipeline.to("cuda")
 
 # Now the `pipeline.unet` component is ready for physics simulation.
 unet = pipeline.unet
-# ...
+# ...
+```
+
+## Training Procedure
+
+The model was trained using the `train_vr_lora.py` script from the project repository. Key hyperparameters:
+
+*   **Learning Rate:** 1e-4
+*   **Batch Size:** 32
+*   **Max Steps:** 15,000
+*   **Optimizer:** AdamW
+*   **Scheduler:** Cosine
+
+## Citing this Work
+
+If you use this model in your research, please cite our paper (BibTeX entry coming soon).