drop empty tokenized rows too (#509)

2023-08-30 06:55:26 -07:00
parent 1e07c162f1
commit c56b450cf5
1 changed files with 1 additions and 1 deletions
--- a/src/axolotl/utils/trainer.py
+++ b/src/axolotl/utils/trainer.py
@@ -361,7 +361,7 @@ def add_position_ids(sample):


 def drop_long_seq(sample, sequence_len=2048):
-    return len(sample["input_ids"]) <= sequence_len
+    return len(sample["input_ids"]) <= sequence_len and len(sample["input_ids"]) > 0


@contextmanager