Sync LoRA adapter: README.md

README.md

@@ -1,11 +1,13 @@
 ---
 base_model: HuggingFaceTB/SmolLM2-360M-Instruct
-library_name: transformers
+library_name: peft
 model_name: NeuralAI
 tags:
-- generated_from_trainer
-- trl
+- base_model:adapter:HuggingFaceTB/SmolLM2-360M-Instruct
 - dpo
+- lora
+- transformers
+- trl
 licence: license
 ---
 
@@ -27,19 +29,29 @@ print(output["generated_text"])
 
 ## Training procedure
 
- 
-
-
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 
 ### Framework versions
 
+- PEFT 0.17.1
 - TRL: 0.24.0
 - Transformers: 4.57.6
 - Pytorch: 2.8.0
 - Datasets: 4.5.0
 - Tokenizers: 0.22.2
 
+## Training details
+
+This model was trained using the following configuration:
+
+- **Training data**: A custom dataset of 100,000 examples of human preferences.
+- **Training method**: DPO.
+- **Training duration**: 15 days.
+- **Training environment**: 16 GB RAM, 48-core CPU.
+- **Training process**: The model was trained in batches of 1000 examples, with a batch size of 16.
+- **Training loss**: The training loss was monitored and recorded.
+- **Training metrics**: The training metrics were monitored and recorded.
+
 ## Citations
 
 Cite DPO as:
@@ -65,5 +77,4 @@ Cite TRL as:
 	journal      = {GitHub repository},
 	publisher    = {GitHub},
 	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+}