update model card README.md

README.md

@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7781
-- Rouge1: 10.6291
-- Rouge2: 4.8145
-- Rougel: 8.5806
-- Rougelsum: 9.9062
+- Loss: 1.6732
+- Rouge1: 10.3791
+- Rouge2: 4.7637
+- Rougel: 8.4427
+- Rougelsum: 9.6953
 - Gen Len: 20.0
 
 ## Model description
@@ -53,7 +53,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
-| 1.6643        | 1.0   | 6188 | 1.7781          | 10.6291 | 4.8145 | 8.5806 | 9.9062    | 20.0    |
+| 1.5316        | 1.0   | 6188 | 1.6732          | 10.3791 | 4.7637 | 8.4427 | 9.6953    | 20.0    |
 
 
 ### Framework versions