Update README.md

README.md

@@ -19,6 +19,20 @@ Built on top of the **OmniSQL-7B** base model and finetuned on the **BIRD** data
 - **Enhancing Text-to-SQL Pipelines:** Integrate as a reward or reranking model to improve execution accuracy and semantic fidelity in Text-to-SQL systems.
 - **Evaluation and Research:** Analyze the semantic alignment of SQL queries with natural language questions to identify and mitigate errors.
 
+## Finetuning Configuration
+
+The following **LoRA configuration** was used to train this model:
+
+- **R**: `16` (rank of the low-rank matrices)  
+- **Lora Alpha**: `64` (scaling factor for the low-rank update)  
+- **Target Modules**: `{q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj}`  
+- **Lora Dropout**: `0.05`  
+- **Bias**: `"none"` (bias terms are frozen)  
+- **FP16**: `True` (half-precision training)  
+- **Learning Rate**: `7e-5`  
+- **Train Batch Size**: `5`  
+- **Num. Train Epochs**: `50`
+  
 ## Usage Example
 
 ```python