Lorenzo Stella

Hi @Riofd. Indeed, the model internally limits the context length (currently happens [here](https://github.com/amazon-science/chronos-forecasting/blob/9500eefd47b27120ce5a531b6f896f03221c11e2/src/chronos/chronos.py#L149-L150)). You **can** increase the model context length after loading it, as in the example below. **However** the...

Yes, fine-tuning may be the best way to go. We added code and some instructions [here](https://github.com/amazon-science/chronos-forecasting/tree/main/scripts#pretraining-and-fine-tuning-chronos-models), let me know if you run into any issue

Leaving open as FAQ

@yeongnamtan there's no need to use `ListDataset`, you can just use a list: ``` dataset = [ { "start": pd.Period(df.index[0], freq=freq), "target": df["DO"].values } ] ``` then you can apply...

@yeongnamtan you should do ``` split(dataset, offset=...) ``` and not ``` split(dataset.test, offset=...) ``` Also, if you wrap your code snippets between triple-backticks, the code will display with a better...

@mshooter could you include a self-contained snippet that reproduces the issue?

[This](https://docs.python.org/2/library/multiprocessing.html#windows) seems relevant, see also the first answer [here](https://stackoverflow.com/questions/24374288/where-to-put-freeze-support-in-a-python-script). TLDR: we probably need to add `freeze_support()` after `if __name__ == "__main__":` in the training script

@AvisP could you check if the fix proposed in #156 makes it work for you?

> What does this mean? > > > The `freeze_support()` line can be omitted if the program will be run normally instead of frozen. > > https://docs.python.org/2/library/multiprocessing.html#windows From what I...

@AlvinLok any update on this?