script with errors

run_translation_t5_flax.py

@@ -131,6 +131,7 @@ class DataTrainingArguments:
         metadata={"help": "The name of the column in the datasets containing the summaries (for summarization)."},
     )
     train_file: Optional[str] = field(default=None, metadata={"help": "The input training data file (a text file)."})
+    test_file: Optional[str] = field(default=None, metadata={"help": "The input test data file (a text file)."})
     validation_file: Optional[str] = field(
         default=None,
         metadata={"help": "An optional input evaluation data file to evaluate the perplexity on (a text file)."},
@@ -498,7 +499,7 @@ def main():
         )
 
     # Metric
-    metric = load_metric("rouge")
+    metric = load_metric("bleu")
 
     def postprocess_text(preds, labels):
         preds = [pred.strip() for pred in preds]
@@ -515,9 +516,11 @@ def main():
         decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)
 
         # Some simple post-processing
-        decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels)
-
-        result = metric.compute(predictions=decoded_preds, references=decoded_labels, use_stemmer=True)
+        #Probably not needed for bleu - pere
+        #decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels)
+        
+        breakpoint()
+        result = metric.compute(predictions=decoded_preds, references=decoded_labels)
         # Extract a few results from ROUGE
         result = {key: value.mid.fmeasure * 100 for key, value in result.items()}