Update README.md

README.md

@@ -33,7 +33,7 @@ This model was developed using [Self-Play Preference Optimization](https://arxiv
 |-------------------------------------------|:------------:|:--------:|:-----------:|
 |[Llama-3-8B-SPPO Iter1](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter1) |31.73 |31.74 | 1962
 |[Llama-3-8B-SPPO Iter2](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2) |35.15 |35.98 | 2021
-|[Llama-3-8B-SPPO Iter3](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3) |38.77 |39.85 | 2066
+|[Llama-3-8B-SPPO Iter3](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3) |**38.77** |**39.85** | 2066
 
 
 
@@ -45,7 +45,7 @@ Results are reported by using [lm-evaluation-harness](https://github.com/Eleuthe
 |--------|---------------|----------------|------------|-------|-----------|-------|---------|
 |[Llama-3-8B-SPPO Iter1](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter1) | 63.82 | 54.96 | 76.40 | 75.44 | 79.80 | 65.65 | 69.35
 |[Llama-3-8B-SPPO Iter2](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter2) | 64.93 | 56.48 | 76.87 | 75.13 | 80.39 | 65.67 | 69.91
-|[Llama-3-8B-SPPO Iter3](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3) | 65.19 | 58.04 | 77.11 | 74.91 | 80.86 | 65.60 | 70.29
+|[Llama-3-8B-SPPO Iter3](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3) | 65.19 | 58.04 | 77.11 | 74.91 | 80.86 | 65.60 | **70.29**
 
 ### Training hyperparameters
 The following hyperparameters were used during training: