google-research/timesfm

fine-tuned

Opened this issue · 1 comments

In the fine-tuned code, covariates were mentioned, but they were not actually used in the training. Why is this the case? Additionally, various time features were processed during data handling, but they were not utilized when actually feeding data into the training process.

Could you please provide some guidance or examples on how to include covariates in the fine-tuning phase?