Hi,
I’m running a time series problem on fastai v1 using Training, Validation, Test set.
procs=[Normalize]
pth=Path(’.’)
test = TabularList.from_df(test_df, path=pth, cont_names=cont_cols, procs=procs)
data = (TabularList.from_df(train_df, path=pth, cont_names=cont_cols, procs=procs)
.split_by_idx(range(int(len(train_df)*.75),len(train_df)))
.label_from_df(cols=dep_var, label_cls=FloatList)
.add_test(test)
.databunch())
learn.fit_one_cycle(5)
epoch | train_loss | valid_loss | exp_rmspe |
---|---|---|---|
1 | 0.000010 | 0.000007 | 0.002616 |
2 | 0.000014 | 0.000034 | 0.004621 |
3 | 0.000011 | 0.000007 | 0.002567 |
4 | 0.000011 | 0.000009 | 0.002592 |
5 | 0.000007 | 0.000007 | 0.002167 |
The output of the train and validation loss are good.
When I run learn.get_preds(DatasetType.Valid) and learn.get_preds(DatasetType.Test), I get decent results, however when I run learn.get_preds(DatasetType.Train), I get poor results.
Am I doing something wrong? I would think I should get really good results.
Thanks for your help.