Update README.md

README.md

@@ -14,6 +14,7 @@ license: apache-2.0
 ### Finetuning Overview:
 
 **Model Used:** HuggingFaceH4/zephyr-7b-alpha
+
 **Dataset:** HuggingFaceH4/no_robots  
 
 #### Dataset Insights:
@@ -35,21 +36,17 @@ With the utilization of [MonsterAPI](https://monsterapi.ai)'s [LLM finetuner](ht
 - **Total Finetuning Cost:** $1.212
 - **Model Path:** HuggingFaceH4/zephyr-7b-alpha
 - **Learning Rate:** 0.0002
-- **Data Split:** 99% train 1% validation
+- **Data Split:** 100% train
 - **Gradient Accumulation Steps:** 4
 - **lora r:** 32
 - **lora alpha:** 64
 
 ---
-Prompt Structure
+#### Prompt Structure
 ```
-### INSTRUCTION:
-[instruction]
-
-### RESPONSE:
-[text]
+<|system|> <|endoftext|> <|user|> [USER PROMPT]<|endoftext|> <|assistant|> [ASSISTANT ANSWER] <|endoftext|>
 ```
-Train loss :
+#### Train loss :
 
 ![training loss](https://cdn-uploads.huggingface.co/production/uploads/63ba46aa0a9866b28cb19a14/7sEdsTGZhlAYTJqOKzbVo.png)