Fix eval dataset typo in README.

README.md

@@ -90,7 +90,7 @@ trainer = Trainer(
     model=model,                         # the instantiated model to be trained
     args=training_args,                  # training arguments, defined above
     train_dataset=train_dataset,         # training dataset
-    eval_dataset=val_dataset             # evaluation dataset
+    eval_dataset=eval_dataset            # evaluation dataset
 )
 
 trainer.train()