Simon Sefcik

Could you explain to me please, when you mean multivariate, you still have only one target variable that you are predicting but just want to have other independent variables (features)...

> You can load a dataframe in long format with the column "item_id" as shown in the [Colab Demo 1](https://colab.research.google.com/drive/1DRAzLUPxsd-0r8b-o4nlyFXrjw_ZajJJ?usp=sharing#scrollTo=vT93Ks5tSvzq) > > ``` > import pandas as pd > from...

> > > You can load a dataframe in long format with the column "item_id" as shown in the [Colab Demo 1](https://colab.research.google.com/drive/1DRAzLUPxsd-0r8b-o4nlyFXrjw_ZajJJ?usp=sharing#scrollTo=vT93Ks5tSvzq) > > > ``` > > > import...

> So you can pretrain with covariates if you have a large pretraining set, and then finetune with the same covariates. If you have a large enough pretraining set where...

> > > You can load a dataframe in long format with the column "item_id" as shown in the [Colab Demo 1](https://colab.research.google.com/drive/1DRAzLUPxsd-0r8b-o4nlyFXrjw_ZajJJ?usp=sharing#scrollTo=vT93Ks5tSvzq) > > > ``` > > > import...

Same even with num_samples=5 it takes at least 30 seconds to conver with batch size of 4 and each sequence of lenght 1024 with pred len 512 if i set...

So this code ``` log_info("Starting inference...") check_memory_usage() forecast_it, ts_it = make_evaluation_predictions( dataset=batch, predictor=predictor, num_samples=num_samples ) log_info("Inference completed, converting to list...") ``` is almost instant, however this part ``` forecasts =...

> @CoCoNuTeK The models were trained with `tf32` (a 19-bit CUDA floating point format that's a replacement for `fp32`). We recommend `bf16` for inference, especially if your machine supports that....

> For fine-tuning, the recommended settings are in the [training script](https://github.com/amazon-science/chronos-forecasting/blob/main/scripts/training/train.py) which uses `tf32` for training. Of course, you're free to experiment with other dtypes and hyperparameters. > > P.S.:...

its not supported, i believe currently its only univariate time series with no covariates