samlhuillier / code-llama-fine-tune-notebook

Fine-tune Code Llama to generate SQL queries from text
32 stars 6 forks source link

Why is split the same at .1 #9

Open brian-methodical opened 4 weeks ago

brian-methodical commented 4 weeks ago

https://github.com/samlhuillier/code-llama-fine-tune-notebook/blob/5848de4f26922453f7e75bf8c2e61e72bf4be55c/fine-tune-code-llama.ipynb#L180

Confused slightly about this split. wouldn't it be .9 and .1 to be normal test train split?