diff --git a/assets/docs/preprocessing.md b/assets/docs/preprocessing.md
index 6246ea4..15afd5c 100644
--- a/assets/docs/preprocessing.md
+++ b/assets/docs/preprocessing.md
@@ -268,7 +268,7 @@ When `sources` is set, `sections` is ignored.
 | `storage_format` | str | `"bin"` | `"bin"` (mmap) or `"h5"` |
 | `max_tokens_per_shard` | int | `100000000` | Flush threshold in cumulative tokens |
 | `dtype` | dict[str, str] | `{}` | Per-key tensor dtype override (e.g. `{"loss_mask": "bool"}`) |
-| `position_ids_mode` | str | `"none"` | How to compute position_ids: `"none"`, `"doc_reset"`, `"continuous"` |
+| `position_ids_mode` | str | `"doc_reset"` | How to compute position_ids: `"none"`, `"doc_reset"`, `"continuous"` |
 
 ---
 
diff --git a/astrai/config/preprocess_config.py b/astrai/config/preprocess_config.py
index 608747f..f10070c 100644
--- a/astrai/config/preprocess_config.py
+++ b/astrai/config/preprocess_config.py
@@ -96,7 +96,7 @@ class OutputConfig(BaseConfig):
     storage_format: str = "bin"
     max_tokens_per_shard: int = 100_000_000
     dtype: Dict[str, str] = field(default_factory=dict)
-    position_ids_mode: str = "none"
+    position_ids_mode: str = "doc_reset"
 
 
 @dataclass
diff --git a/astrai/preprocessing/pipeline.py b/astrai/preprocessing/pipeline.py
index e970cb9..5168802 100644
--- a/astrai/preprocessing/pipeline.py
+++ b/astrai/preprocessing/pipeline.py
@@ -144,7 +144,7 @@ class Pipeline:
         for key in list(bucket.keys()):
             if key in result:
                 continue
-            bucket[key].append([1] * len(ids))
+            bucket[key].append([0] * len(ids))
 
     def _iter_items(self):
         for path in self.paths:
@@ -160,6 +160,12 @@ class Pipeline:
             idx = shard_idx[domain]
 
             pp = self.config.preprocessing
+            original_sequences = keys.get("sequence", [])
+            mode = self.config.output.position_ids_mode
+
+            if mode == "doc_reset" and original_sequences:
+                keys["position_ids"] = [list(range(len(s))) for s in original_sequences]
+
             keys = self._packer.apply(dict(keys), pp.max_packed_len, pp.truncation_mode)
 
             tensors: Dict[str, List[torch.Tensor]] = {}
@@ -171,9 +177,10 @@ class Pipeline:
                     torch.tensor(list(chain.from_iterable(ids_list)), dtype=dt)
                 ]
 
-            pos_ids = self._position_id.generate(keys.get("sequence", []))
-            if pos_ids:
-                tensors["position_ids"] = [torch.tensor(pos_ids, dtype=torch.int32)]
+            if mode == "continuous" and original_sequences:
+                pos_ids = self._position_id.generate(keys.get("sequence", []))
+                if pos_ids:
+                    tensors["position_ids"] = [torch.tensor(pos_ids, dtype=torch.int32)]
 
             self._writer.save(self.output_dir, domain, idx, tensors)
             shard_idx[domain] = idx + 1