Closed aoji0606 closed 2 weeks ago
No response
- OS: - Python: - Transformers: - PyTorch: - CUDA (`python -c 'import torch; print(torch.version.cuda)'`):
我用自己的数据去ft,执行的finetune_ds.sh,设置的总bs=8*16,lr=1e-6,训完loss在0.8713,最后测试mme效果非常差,这是什么原因呢
您的数据集和mme的差别有多大呢,您有测试过其他indomain数据集吗?我这里用单卡 batch为16,在refcoco上训练,最起码是有效果的。
是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?
该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?
当前行为 | Current Behavior
No response
期望行为 | Expected Behavior
No response
复现方法 | Steps To Reproduce
No response
运行环境 | Environment
备注 | Anything else?
No response