update model card README.md

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [AI-Lab-Makerere/lg_en](https://huggingface.co/AI-Lab-Makerere/lg_en) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0710
-- Bleu: 14.7729
+- Loss: 1.1615
+- Bleu: 28.3855
 
 ## Model description
 
@@ -48,8 +48,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| No log        | 1.0   | 26   | 2.1577          | 14.6173 |
-| No log        | 2.0   | 52   | 2.0710          | 14.7729 |
+| No log        | 1.0   | 26   | 1.2704          | 25.9847 |
+| No log        | 2.0   | 52   | 1.1615          | 28.3855 |
 
 
 ### Framework versions