update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Bleu
       type: bleu
-      value: 36.3549
+      value: 35.7129
 ---
 
 <!-- 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: 9.1296
-- Bleu: 36.3549
-- Gen Len: 56.48
+- Loss: 8.7990
+- Bleu: 35.7129
+- Gen Len: 56.52
 
 ## Model description
 
@@ -50,7 +50,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-06
+- learning_rate: 3e-06
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -62,14 +62,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 4    | 9.4200          | 36.1989 | 56.48   |
-| No log        | 2.0   | 8    | 9.2108          | 36.3549 | 56.48   |
-| No log        | 3.0   | 12   | 9.1296          | 36.3549 | 56.48   |
+| No log        | 1.0   | 4    | 9.2430          | 36.2707 | 56.46   |
+| No log        | 2.0   | 8    | 8.9239          | 36.0358 | 56.56   |
+| No log        | 3.0   | 12   | 8.7990          | 35.7129 | 56.52   |
 
 
 ### Framework versions
 
 - Transformers 4.19.4
 - Pytorch 1.11.0+cu113
-- Datasets 2.3.0
+- Datasets 2.3.1
 - Tokenizers 0.12.1