Example NER script predicts on tokenized dataset (#8468)

The new run_ner.py script tries to run prediction on the input
test set `datasets["test"]`, but it should be the tokenized set
`tokenized_datasets["test"]`

examples/token-classification/run_ner.py

@@ -344,7 +344,7 @@ def main():
     if training_args.do_predict:
         logger.info("*** Predict ***")
 
-        test_dataset = datasets["test"]
+        test_dataset = tokenized_datasets["test"]
         predictions, labels, metrics = trainer.predict(test_dataset)
         predictions = np.argmax(predictions, axis=2)