lachkarsalim/DarijaTransliteration_to_English

README.md

@@ -17,8 +17,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6158
-- Bleu: 24.2746
+- Loss: 1.6140
+- Bleu: 39.7635
 
 ## Model description
 
@@ -44,16 +44,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 5
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 2.2719        | 1.0   | 1507 | 2.0346          | 25.4066 |
-| 1.8542        | 2.0   | 3014 | 1.7879          | 20.5567 |
-| 1.6428        | 3.0   | 4521 | 1.6770          | 24.2746 |
-| 1.5083        | 4.0   | 6028 | 1.6303          | 20.5567 |
-| 1.4477        | 5.0   | 7535 | 1.6158          | 24.2746 |
+| 2.2767        | 1.0   | 1507 | 2.0376          | 0.0     |
+| 1.8477        | 2.0   | 3014 | 1.7873          | 0.0     |
+| 1.644         | 3.0   | 4521 | 1.6827          | 39.7635 |
+| 1.5109        | 4.0   | 6028 | 1.6299          | 39.7635 |
+| 1.4356        | 5.0   | 7535 | 1.6140          | 39.7635 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ee83ebfa745c412952700a498e1e1eeeab64eb185b273ed77044a41f2174ef
+oid sha256:bfb6e96afd97975889db61f955689a3839eb0a10aaa548056f9bb236572b90e0
 size 305518408

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98585823a631de3c74dd366e2722ba614a76a5dd6b2f8333ba71e47c29091d24
+oid sha256:927aad6e08bbeb2a34f4af9d9809ec04b6774eb349878aa658e52f6612f7c2e1
 size 4984