Update README.md

README.md

@@ -75,18 +75,19 @@ Built using efficient fine-tuning with Unsloth + LoRA, this model focuses on imp
 
 ---
 
-## 🧪 Evaluation
 
-Human evaluation on test prompts:
+## Evaluation Results (Automated)
 
-| Metric | Score |
-| :--- | :--- |
-| **Fluency** | 8.7 / 10 |
-| **Human-likeness** | 8.5 / 10 |
-| **Meaning Preservation** | 9.2 / 10 |
+The model was evaluated using a professional suite at temperature 0.7.
 
-> *Note: Scores are based on qualitative evaluation.*
+| Metric | Value | Interpretation |
+| :--- | :--- | :--- |
+| **BERTScore F1** | 0.8424 | Semantic Similarity to Prompts |
+| **ROUGE-L** | 0.0908 | Low overlap indicates original generation |
+| **Perplexity** | 1.5242 | Confidence/Coherence (Lower is better) |
+| **Text Overlap** | 0.0528 | Lexical similarity to input |
 
+*Results generated and uploaded via Colab automated pipeline.*
 ---
 
 ## 💻 Usage
@@ -106,15 +107,4 @@ outputs = model.generate(**inputs, max_new_tokens=120)
 
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
-## Evaluation Results (Automated)
 
-The model was evaluated using a professional suite at temperature 0.7.
-
-| Metric | Value | Interpretation |
-| :--- | :--- | :--- |
-| **BERTScore F1** | 0.8424 | Semantic Similarity to Prompts |
-| **ROUGE-L** | 0.0908 | Low overlap indicates original generation |
-| **Perplexity** | 1.5242 | Confidence/Coherence (Lower is better) |
-| **Text Overlap** | 0.0528 | Lexical similarity to input |
-
-*Results generated and uploaded via Colab automated pipeline.*