Update README.md

README.md

@@ -57,21 +57,21 @@ Only the solution portion of each example was used for loss computation through
 
 ## Training Configuration  
 
-Method: QLoRA (4-bit)  
-Quantization: NF4 with float16 compute  
-LoRA rank: 16  
-LoRA alpha: 32  
-LoRA dropout: 0.05  
-Target modules: q_proj, k_proj, v_proj, o_proj  
-Max sequence length: 1024  
-Batch size: 1  
-Gradient accumulation: 16  
-Effective batch size: 16  
-Learning rate: 1e-4  
-Optimizer: paged_adamw_8bit  
-Scheduler: cosine  
-Warmup: 5 percent  
-Epochs: 6  
+Method: LoRA (full precision, bfloat16)
+Precision: bfloat16 (no 4-bit quantization)
+LoRA rank: 16
+LoRA alpha: 32
+LoRA dropout: 0.05
+Target modules: q_proj, k_proj, v_proj, o_proj
+Max sequence length: 1024
+Batch size: 2
+Gradient accumulation: 8
+Effective batch size: 16
+Learning rate: 1e-4
+Optimizer: adamw_torch
+Scheduler: cosine
+Warmup: 5 percent
+Epochs: 3
 
 ---