update model card README.md

README.md

@@ -29,7 +29,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ar-en](https://huggingface.co/Helsinki-NLP/opus-mt-ar-en) on the news_commentary dataset.
 It achieves the following results on the evaluation set:
-- Loss: 9.7617
+- Loss: 9.7675
 - Bleu: 36.3138
 - Gen Len: 57.0
 
@@ -50,7 +50,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-08
+- learning_rate: 2e-09
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -62,9 +62,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 4    | 9.7645          | 36.3138 | 57.0    |
-| No log        | 2.0   | 8    | 9.7624          | 36.3138 | 57.0    |
-| No log        | 3.0   | 12   | 9.7617          | 36.3138 | 57.0    |
+| No log        | 1.0   | 4    | 9.7676          | 36.3138 | 57.0    |
+| No log        | 2.0   | 8    | 9.7675          | 36.3138 | 57.0    |
+| No log        | 3.0   | 12   | 9.7675          | 36.3138 | 57.0    |
 
 
 ### Framework versions