End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1083
+- Loss: 0.0001
 
 ## Model description
 
@@ -46,16 +46,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 18   | 0.1065          |
-| No log        | 2.0   | 36   | 0.1076          |
-| No log        | 3.0   | 54   | 0.1076          |
-| No log        | 4.0   | 72   | 0.1078          |
-| No log        | 5.0   | 90   | 0.1077          |
-| No log        | 6.0   | 108  | 0.1079          |
-| No log        | 7.0   | 126  | 0.1080          |
-| No log        | 8.0   | 144  | 0.1081          |
-| No log        | 9.0   | 162  | 0.1083          |
-| No log        | 10.0  | 180  | 0.1083          |
+| No log        | 1.0   | 18   | 0.0004          |
+| No log        | 2.0   | 36   | 0.0002          |
+| No log        | 3.0   | 54   | 0.0002          |
+| No log        | 4.0   | 72   | 0.0001          |
+| No log        | 5.0   | 90   | 0.0002          |
+| No log        | 6.0   | 108  | 0.0002          |
+| No log        | 7.0   | 126  | 0.0001          |
+| No log        | 8.0   | 144  | 0.0001          |
+| No log        | 9.0   | 162  | 0.0001          |
+| No log        | 10.0  | 180  | 0.0001          |
 
 
 ### Framework versions