diff --git a/docs/config.qmd b/docs/config.qmd
index 6414b63a5..e58ad5bc0 100644
--- a/docs/config.qmd
+++ b/docs/config.qmd
@@ -109,7 +109,7 @@ datasets:
     preprocess_shards: # Optional[int] process dataset in N sequential chunks for memory efficiency (exclusive with `shards`)
 
     name: # Optional[str] name of dataset configuration to load
-    train_on_split: train # Optional[str] name of dataset split to load from
+    split: train # Optional[str] name of dataset split to load from
     revision: # Optional[str] The specific revision of the dataset to use when loading from the Hugging Face Hub. This can be a commit hash, tag, or branch name. If not specified, the latest version will be used. This parameter is ignored for local datasets.
     trust_remote_code: # Optional[bool] Trust remote code for untrusted source
 
diff --git a/src/axolotl/utils/schemas/datasets.py b/src/axolotl/utils/schemas/datasets.py
index 57de71da2..f9b694da1 100644
--- a/src/axolotl/utils/schemas/datasets.py
+++ b/src/axolotl/utils/schemas/datasets.py
@@ -39,7 +39,6 @@ class SFTDataset(BaseModel):
     input_format: str | None = None
     name: str | None = None
     ds_type: str | None = None
-    train_on_split: str | None = None
     field: str | None = None
     field_human: str | None = None
     field_model: str | None = None