Update README.md

README.md

@@ -28,8 +28,8 @@ The base model must be loaded separately.
 This adapter is trained to improve **structured output accuracy**
 (JSON / YAML / XML / TOML / CSV).
 
-Loss is applied only to the final assistant output,
-while intermediate reasoning (Chain-of-Thought) is masked.
+Chain-of-Thought reasoning was removed from training data, 
+and loss is applied directly to the final structured output.
 
 ## Training Configuration
 
@@ -63,5 +63,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 Training data: u-10bei/structured_data_with_cot_dataset_512_v2, u-10bei/structured_data_with_cot_dataset_512_v4, u-10bei/structured_data_with_cot_dataset_512_v5
 
+Data preprocessing: Combined the above three versions with removal of unparseable outputs, deduplication, and removal of Chain-of-Thought reasoning from assistant responses.
+
 Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
 Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.