Update README.md

README.md

@@ -7,6 +7,8 @@ language:
 library_name: transformers
 ---
 
+An instruction-tuned LoRA model of https://huggingface.co/baichuan-inc/baichuan-7B
+
 This checkpoint is trained with: https://github.com/hiyouga/LLaMA-Efficient-Tuning
 
 Usage:
@@ -35,3 +37,9 @@ python src/cli_demo.py \
     --checkpoint_dir hiyouga/baichuan-7b-sft \
     --prompt_template ziya
 ```
+
+Loss curve on training set:
+![train](training_loss.svg)
+
+Loss curve on evaluation set:
+![eval](eval_loss.svg)