update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Bleu
       type: bleu
-      value: 32.7441
+      value: 32.8872
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,9 +29,9 @@ 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: 8.4415
-- Bleu: 32.7441
-- Gen Len: 57.02
+- Loss: 0.6933
+- Bleu: 32.8872
+- Gen Len: 56.084
 
 ## Model description
 
@@ -50,21 +50,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-09
+- learning_rate: 3e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 4    | 8.4416          | 32.7441 | 57.02   |
-| No log        | 2.0   | 8    | 8.4415          | 32.7441 | 57.02   |
-| No log        | 3.0   | 12   | 8.4415          | 32.7441 | 57.02   |
+| No log        | 1.0   | 188  | 0.7407          | 30.7259 | 56.296  |
+| No log        | 2.0   | 376  | 0.6927          | 32.2038 | 58.602  |
+| 0.8066        | 3.0   | 564  | 0.6898          | 33.1091 | 57.72   |
+| 0.8066        | 4.0   | 752  | 0.6925          | 33.0842 | 56.574  |
+| 0.8066        | 5.0   | 940  | 0.6933          | 32.8872 | 56.084  |
 
 
 ### Framework versions