Allow for more forcast step embeddings

[sophie-xhonneux]

Description

allow more choices when embedding the forecast step

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update

Issue Number

None

Code Compatibility

• I have performed a self-review of my code

Code Performance and Testing

• I ran the uv run train and (if necessary) uv run evaluate on a least one GPU node and it works
• If the new feature introduces modifications at the config level, I have made sure to have notified the other software developers through Mattermost and updated the paths in the $WEATHER_GENERATOR_PRIVATE directory

I tested with --options forecast_offset=1 training_mode='forecast' istep=0 num_epochs=8 forecast_policy=fixed forecast_steps=2 fe_num_blocks=8

Dependencies

• I have ensured that the code is still pip-installable after the changes and runs
• I have tested that new dependencies themselves are pip-installable.
• I have not introduced new dependencies in the inference portion of the pipeline

Documentation

• My code follows the style guidelines of this project
• I have updated the documentation and docstrings to reflect the changes
• I have added comments to my code, particularly in hard-to-understand areas

Additional Notes

[clessig]

@sophie-xhonneux : what are we going to do with this? Do we want to rework this into a proper PR? The positional encodings need to be reworked in general, though (e.g. what is in ModelParams).

[sophie-xhonneux]

I think it would be good to have these options in the model, no? I guess this can stay a small PR, we can update the current one to be mergeable and then create a new larger DRAFT PR for the model params?

[clessig]

I think it would be good to have these options in the model, no? I guess this can stay a small PR, we can update the current one to be mergeable and then create a new larger DRAFT PR for the model params?

Sounds good.