Is the precision of fine-tuning with Lora the same as that of full-parameter fine-tuning on Libero

[helloworld13138]

I performed Lora fine-tuning according to the parameters provided in the code, but I couldn't get similar results, achieving only 90.6 on libero_spatial.

[lab-bj]

Hello, the result I obtained is 92.4%. May I ask what your loss value is?