Tracy Teal
07/05/2024, 6:14 PMTracy Teal
07/05/2024, 6:15 PM"Franco, Joao Vitor" <joao.vitor.franco@effem.com>
Hello, I hope you're doing well.
Can you please share a cost calculation example using the TimeGPT model in the Azure environment?
Iโm particularly interested to understand how the cost works when finetuning it.
How `finetune_steps`parameter impact cost? Should I consider all 4 types of costs when performing a finetuning?
Please share a detailed example covering all possible scenarios, with finetuning or not.
Max
07/05/2024, 6:19 PMMax
07/07/2024, 4:31 AMCristian Challu
07/08/2024, 11:22 AMTracy Teal
07/11/2024, 10:04 PMMax
07/12/2024, 1:13 AMCristian Challu
07/16/2024, 4:56 PMCristian Challu
07/16/2024, 4:59 PMThe finetune steps determine the type of token you will be charged. If you are finetuning the model, then only the finetuned type of tokens apply.
Tracy Teal
07/16/2024, 4:59 PMTracy Teal
07/16/2024, 5:45 PMlevel
parameter impacts the cost when using it. For example, letโs assume a confidence interval of 80%"Cristian Challu
07/16/2024, 5:46 PMoutput_tokens=num_series*h*(1+2*num_levels)
Tracy Teal
07/16/2024, 5:51 PM