Set output-ngrams to default to true and update README (stanford-crfm…

…#1776)

Co-authored-by: Andy Z <[email protected]>

scripts/data_overlap/README.md

@@ -32,6 +32,7 @@ For instance, you can call this with The Pile, e.g. have:
     output_stats = arbitrary output file name, e.g. "output_stats"
     input_format = the_pile
 
+If you don't want to output the ngrams that are overlapping in test set to a separate "{output_stats}_ngrams" file, you can pass --no-output-ngrams.
 
 There are additional optional args:
 --normalization default 

scripts/data_overlap/common/arguments.py

@@ -13,7 +13,7 @@ def get_data_overlap_args() -> Any:
         required=True,
         help="The format of your input file for your training data, e.g. raw, custom, the_pile",
     )
-    parser.add_argument("--output-ngrams", type=bool, default=False, help="Whether to output ngrams")
+    parser.add_argument("--no-output-ngrams", type=bool, default=False, help="Pass to not output ngrams")
     parser.add_argument(
         "--tags",
         type=str,

scripts/data_overlap/compute_data_overlap_metrics.py

@@ -233,10 +233,10 @@ def compute_document_data_overlap(
                 stats_key_to_input_ids=stats_key_to_input_ids,
                 stats_key_to_reference_ids=stats_key_to_reference_ids,
                 entry_overlap_key_to_ngram_counts=entry_overlap_key_to_ngram_counts,
-                output_ngrams=args.output_ngrams,
+                output_ngrams=not args.no_output_ngrams,
             )
 
-    if args.output_ngrams:
+    if not args.no_output_ngrams:
         all_entry_overlap_ngrams = []
         with open(f"{args.output_stats}_ngrams", "w") as f:
             for entry_overlap_key in entry_overlap_key_to_ngram_counts: