Update README.md

README.md

@@ -18,19 +18,19 @@ Cakrawala-70B is a fine-tuned variant of the Llama-3.1-70B-Instruct model, speci
 ## 🧪 The Secret Sauce
 
 ### Training Diet:
-- Fed with 5,867 conversation pairs
+- Fed with 13,000 conversation pairs
 - Each conversation is a minimum 12-13 turns long
 - Focused heavily details like facial expressions, environmental descriptions, and character reactions that are focused a lot on **keeping the model in character.**
 
 ### Tech Wizardry:
-- Trained on the mighty Llama-3.1-70B-Instruct
+- Trained on Llama-3.1-70B-Instruct
 - Fine-tuned using QLoRA 
-- Trained over 3 epochs
+- Trained over 2 epochs
 
 ## Training Parameters
-- Gradient Accumulation Steps: 16
+- Gradient Accumulation Steps: 1
 - Micro Batch Size: 4
-- Learning Rate: 0.0003
+- Learning Rate: 0.0002
 - Optimizer: AdamW
 - Scheduler: Cosine
 - Mixed Precision: BF16 & FP16 with TF32 support