Strange issue with model.eval()

I find strange issue as never before .Adding model.eval( ) makes predictions worst compared to without it . I have been doing all this earlier with no issue ,as it is way as well when u have batch norm in place .
I dont know what unknown mistake i could be making
Here is how i save the model,‘model_eval.pth’ )

gpu = torch.device("cuda:0")
state_dict = torch.load('../work/model_eval.pth',map_location=gpu)
model.load_state_dict(state_dict   )

here is model head

 (head): Sequential(
    (0): AdaptiveConcatPool2d(
      (ap): AdaptiveAvgPool2d(output_size=1)
      (mp): AdaptiveMaxPool2d(output_size=1)
    (1): Flatten()
    (2): Linear(in_features=4096, out_features=512, bias=True)
    (3): Mish()
    (4): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (5): Dropout(p=0.5, inplace=False)
    (6): Linear(in_features=512, out_features=1, bias=True)