search

time-series-foundation-models / lag-llama

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Apache License 2.0
1.09k stars 121 forks source link

Getting LightningModule error during fine-tuning #25

Closed shahrokhvahabi closed 3 months ago

shahrokhvahabi commented 3 months ago

When I run the fine-tuning code on my dataset I get this error:

TypeError: model must be a LightningModule or torch._dynamo.OptimizedModule, got LagLlamaLightningModule

But the zero-shot works perfectly.

kashif commented 3 months ago

can you kindly paste in the output of:

!pip list | grep -i lightning
shahrokhvahabi commented 3 months ago

can you kindly paste in the output of:

!pip list | grep -i lightning

lightning 2.1.4 lightning-utilities 0.10.1 pytorch-lightning 2.1.4

kashif commented 3 months ago

and in your notebook if you do:

import lightning

lightning.__version__

is it the same?

shahrokhvahabi commented 3 months ago

Dear @kashif thank you very much for your time. Eventually, I deleted the whole lag llama and installed it again. Now, it works perfectly. Thank you very much for this nice fine-tuning code.

sudongwang-upc commented 3 months ago

Can you explain the reason for the error and what is the difference between reinstalling it or not