Update README.md

README.md

@@ -1,15 +1,27 @@
-This model was trained as part of a series of experiments testing the performance of pure DPO vs SFT vs ORPO, all supported by Unsloth/Huggingface TRL.
+*This model was trained as part of a series of experiments testing the performance of pure DPO vs SFT vs ORPO, all supported by Unsloth/Huggingface TRL.*
+
+**Training Details**
 
 Dataset: https://huggingface.co/datasets/argilla/dpo-mix-7k 
+
 Rank: 8 
+
 Alpha: 16 
+
 Learning rate: 5e-6 
+
 Beta: 0.1 
+
 Batch size: 8 
+
 Epochs: 1
+
 Learning rate scheduler: Linear
+
 Prompt Format: ```You are a helpful assistant.<s>[INST] PROMPT [/INST]RESPONSE</s>```
 
+
+**WanDB Reports**
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65a5c0e82823ba72ed2cee7d/Tg3dknWsTvfqM96Fab2YJ.png)
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65a5c0e82823ba72ed2cee7d/8DQ0WiypkVIJeK_Y18Wv0.png)