Open MichealZhangxa opened 2 months ago
您好,请问可以看一下您的实验脚本/配置吗?
Please provide your training script and any modified code (if applicable) so that we can better identify the issues in the code.
You might try using the two encoders separately to train the whole model, ensuring that each individual encoder can properly train the whole model.
And you can adjust the model training length by modifying the num_train_epochs
parameter.
你好,我在你的代码的基础上训练,前期的损失一直在3到4之间正常吗,训练的也是llava的预训练数据集