Update README.md

README.md

@@ -88,7 +88,6 @@ Fine-tuned exclusively on the **Egyptian Arabic** [Omar-youssef/English-Egyptian
 - **Weight decay:** 0.01
 - **Optimizer:** AdamW
 - **Evaluation strategy:** steps (every 50 steps)
-- **Best model selection:** highest BLEU score on validation set
 
 ---
 
@@ -119,7 +118,7 @@ Fine-tuned exclusively on the **Egyptian Arabic** [Omar-youssef/English-Egyptian
 
 - **Architecture:** MarianMT (Encoder-Decoder Transformer)
 - **Base:** Helsinki-NLP/opus-mt-tc-big-en-ar
-- **Parameters:** ~600M
+- **Parameters:** ~500M
 - **Task:** Sequence-to-Sequence Translation
 
 ### Compute Infrastructure
@@ -138,7 +137,7 @@ If you use this model, please cite the base model and dataset:
 @misc{omar-youssef-egyptian-translation,
   author    = {Omar Youssef},
   title     = {English to Egyptian Arabic Translation Model},
-  year      = {2024},
+  year      = {2026},
   publisher = {Hugging Face},
   url       = {https://huggingface.co/Omar-youssef/english-egyptian-arabic-translation-v1}
 }