Update README.md

README.md

@@ -31,9 +31,9 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float16
 
 ### LOSS
-Step	           Training Loss     Eval Loss
-1550 (Epoch:1)       0.4295           0.4367
-3110 (Epoch:2)       0.4057           0.4217
+Step	           Training Loss     Eval Loss    
+1550 (Epoch:1)       0.4295           0.4367    
+3110 (Epoch:2)       0.4057           0.4217    
 
 ### Framework versions