Xiangdong Zhang comments

Repositories
Issues
Comments

Results 4 comments of


                                            Xiangdong Zhang

LR Scheduler Bugs in Finetuning Code

Thank you for your response. My questions are resolved. I will submit a PR in the next few days.

Questions about lora training setting for CogVideoX 5B

Additionally, I tried learning rates of 1e-3, 1e-4, 1e-5, 1e-6, and 1e-7, with a weight decay of 1e-3. Only the results for 1e-6 and 1e-7 were normal, but these values...

Questions about lora training setting for CogVideoX 5B

> Hi, when I finetune the CogVideo T2V 5B mode using LoRA, my loss turns to nan after 1-2 steps. Have you faced this issue ? I have tried reducing...

Questions about lora training setting for CogVideoX 5B

> > Hi, > > When I trained CogVideoX **2B** on 10,000 videos with a batch size of 16 (approximately 2k steps), using a **learning rate of 1e-5** and a...