From 7406d27f6a629c7592abf5c9df02a4305a837d5d Mon Sep 17 00:00:00 2001
From: Wing Lian <wing.lian@gmail.com>
Date: Wed, 13 Sep 2023 11:23:30 -0400
Subject: [PATCH] gracefully handle length feature used for group by (#565)

---
 src/axolotl/utils/dataloader.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/axolotl/utils/dataloader.py b/src/axolotl/utils/dataloader.py
index 6d5505baa2..d659c3d334 100644
--- a/src/axolotl/utils/dataloader.py
+++ b/src/axolotl/utils/dataloader.py
@@ -223,6 +223,8 @@ def __iter__(self):
                 concatenated = {}
                 batched_data = [self.dataset[batch_idx] for batch_idx in batch]
                 for feature in features:
+                    if feature == "length":
+                        continue
                     if feature == "attention_mask":
                         arrays = [
                             (attn_mask_cum_idx + idx + 1) * np.array(item[feature])