diff --git a/scripts/chat_sft.py b/scripts/chat_sft.py
index f31a2d3..cb9e078 100644
--- a/scripts/chat_sft.py
+++ b/scripts/chat_sft.py
@@ -282,8 +282,8 @@ def sft_data_generator_bos_bestfit(split, buffer_size=100):
         # Build tensors
         use_cuda = device_type == "cuda"
         batch_tensor = torch.tensor(rows, dtype=torch.long, pin_memory=use_cuda)
-        inputs = batch_tensor[:, :-1].to(device=device, dtype=torch.int32, non_blocking=use_cuda)
-        targets = batch_tensor[:, 1:].to(device=device, dtype=torch.int64, non_blocking=use_cuda)
+        inputs = batch_tensor[:, :-1].to(device=device, dtype=torch.int32, non_blocking=use_cuda).contiguous()
+        targets = batch_tensor[:, 1:].to(device=device, dtype=torch.int64, non_blocking=use_cuda).contiguous()
 
         # Apply the loss mask from render_conversation (mask=1 for assistant completions,
         # mask=0 for user prompts, BOS, special tokens, tool outputs). mask[1:] aligns