lab-bj

Results 4 comments of


                                            lab-bj

运行 python run.py --agent Single_Agent/oculist_agent/config.json 运行成功，但是一提问就出现一下问题。

![Uploading 微信图片_20231208111810.png…](https://bearmall-hello.oss-cn-beijing.aliyuncs.com/%E5%BE%AE%E4%BF%A1%E5%9B%BE%E7%89%87_20231208111810.png)

运行 python run.py --agent Single_Agent/oculist_agent/config.json 运行成功，但是一提问就出现一下问题。

没有

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

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

When the training reaches 1000 steps, the training program automatically stops and exits

At what point does the loss converge to yield the best model performance?