Is the uploaded code the final version? #1

Thank you very much for sharing this excellent work.
I tried running the program under the condition of Qwen2.5-7B-Instruct + Graph-Based Text Retriever, but the accuracy of the model after reinforcement learning (HippoRAG2_average_f1) does not exceed that of the model before reinforcement learning.
I was able to confirm that the model you uploaded to Hugging Face, “gzone0111/AutoGraphR1-musique_hotpotqa_train-qwen2.5-7b-text-retriever-grpo,” achieves higher accuracy than the original “Qwen2.5-7B-Instruct.”

There is a possibility that I may have made a mistake in my verification, but if the code currently uploaded is not the final version, I would greatly appreciate it if you could upload the final version.