Update README.md

README.md

@@ -125,6 +125,7 @@ Please see the graph below:
 
 The final evaluation cross-entropy ended around 0.4 for this model.
 
+The table below shows the cross-entropies for each technique applied when the embedding training was present. Without the embedding, the results were usually worse for up to 0.1.
 
 
 |  | Loss on Llama 3.1 fine tuning | Notice |
@@ -132,7 +133,7 @@ The final evaluation cross-entropy ended around 0.4 for this model.
 | **LORA**     | 0.4603                  | |
 | **LORA+** | 0.4011    |  The model uploaded here |
 | **DORA**|  0.4182         | |
-| **qLORA (for 70b model)**| 0.3694          | The model with best evaluation, was too big to optimize it further with with my budget|
+| **qLORA (for 70b model)**| 0.3694          | The model with best evaluation, was too big to optimize it further with my budget|
 | **qLORA (for 8b model)**| 0.5471         |  |
 | **(LO)ReFT**| 0.4824         |  |