Update README.md

README.md

@@ -6,9 +6,17 @@ tags:
 - generated_from_trainer
 metrics:
 - bleu
+- chrf
+- ter
 model-index:
 - name: Terjman-Large-v2.2
   results: []
+datasets:
+- BounharAbdelaziz/Terjman-v2-English-Darija-Dataset-350K
+language:
+- ar
+- en
+pipeline_tag: translation
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,8 +24,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Terjman-Large-v2.2
 
-This model is a fine-tuned version of [atlasia/Terjman-Large-v1.2](https://huggingface.co/atlasia/Terjman-Large-v1.2) on an unknown dataset.
-It achieves the following results on the evaluation set:
+This model is a fine-tuned version of [atlasia/Terjman-Large-v1.2](https://huggingface.co/atlasia/Terjman-Large-v1.2) on [BounharAbdelaziz/Terjman-v2-English-Darija-Dataset-350K](https://huggingface.co/datasets/BounharAbdelaziz/Terjman-v2-English-Darija-Dataset-350K).
+It achieves the following results on [atlasia/TerjamaBench](https://huggingface.co/datasets/atlasia/TerjamaBench) set:
 - Loss: 2.8068
 - Bleu: 20.1692
 - Chrf: 41.5829
@@ -201,4 +209,4 @@ The following hyperparameters were used during training:
 - Transformers 4.47.1
 - Pytorch 2.5.1+cu124
 - Datasets 3.1.0
-- Tokenizers 0.21.0
+- Tokenizers 0.21.0