Simplify README phrasing around training data

README.md

@@ -18,7 +18,7 @@ FinTurkBERT Sentiment is a Turkish financial sentiment model for sentence-level
 
 The model is built on top of a Turkish BERT backbone that was continued-pretrained on approximately 1 GB of cleaned Turkish financial text. After domain-adaptive pretraining, the model was further improved with task-adaptive pretraining (TAPT) and then fine-tuned for 3-class sentiment classification.
 
-The final released checkpoint was selected from our agreement-level experiments on Turkish Financial PhraseBank-style data. Among the tested variants, the best held-out test performance came from training on the `66%+` agreement subset, which gave the best balance between label quality and data coverage.
+The final released checkpoint was trained for Turkish financial sentiment classification using a Turkish version of Financial PhraseBank.
 
 ## Labels