Fix ROUGE add example check and update README (#18398)

* Fix ROUGE add example check and update README

* Stay consistent in values

examples/flax/summarization/requirements.txt

@@ -3,3 +3,4 @@ jax>=0.2.8
 jaxlib>=0.1.59
 flax>=0.3.5
 optax>=0.0.8
+evaluate>=0.2.0

examples/flax/summarization/run_summarization_flax.py

@@ -680,12 +680,9 @@ def main():
         decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels)
 
         result = metric.compute(predictions=decoded_preds, references=decoded_labels, use_stemmer=True)
-        # Extract a few results from ROUGE
-        result = {key: value.mid.fmeasure * 100 for key, value in result.items()}
-
+        result = {k: round(v * 100, 4) for k, v in result.items()}
         prediction_lens = [np.count_nonzero(pred != tokenizer.pad_token_id) for pred in preds]
         result["gen_len"] = np.mean(prediction_lens)
-        result = {k: round(v, 4) for k, v in result.items()}
         return result
 
     # Enable tensorboard only on the master node