From 24f2887e871b63bfaea24df0c276b936f37366e3 Mon Sep 17 00:00:00 2001
From: Wing Lian <wing@axolotl.ai>
Date: Fri, 27 Jun 2025 10:37:53 -0400
Subject: [PATCH] don't fail during preprocess for sampling from iterable
 dataset (#2825) [skip ci]

---
 src/axolotl/common/datasets.py | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/src/axolotl/common/datasets.py b/src/axolotl/common/datasets.py
index 96af84c1e..a9b4c0f0f 100644
--- a/src/axolotl/common/datasets.py
+++ b/src/axolotl/common/datasets.py
@@ -75,13 +75,17 @@ def load_datasets(
 
         num_examples = cli_args.debug_num_examples if cli_args else 1
         text_only = cli_args.debug_text_only if cli_args else False
-        train_samples = sample_dataset(train_dataset, num_examples)
-        check_dataset_labels(
-            train_samples,
-            tokenizer,
-            num_examples=num_examples,
-            text_only=text_only,
-        )
+        try:
+            train_samples = sample_dataset(train_dataset, num_examples)
+            check_dataset_labels(
+                train_samples,
+                tokenizer,
+                num_examples=num_examples,
+                text_only=text_only,
+            )
+        except AttributeError:
+            # can't sample iterable datasets
+            pass
 
         LOG.info("printing prompters...")
         for prompter in prompters: