Dataset?

#6
by Nekochu - opened

what dataset was it train? is openly available?

Apparently (not so sure but based on the paper) they finetuned based on ada-instruct, they have a dataset on their repo.

Check this
https://github.com/wangitu/Ada-Instruct/tree/main/data%2Fada-instruct

NousResearch org
β€’
edited Mar 10

We did not use the Ada-instruct dataset

I hand-wrote 21 examples, and also used 500 examples from ROPES augmented with reasoning from GPT-4

euclaise changed discussion status to closed

I hand-wrote 21 examples, and also used 500 examples from ROPES augmented with reasoning from GPT-4

Looking forward to being shared.

We did not use the Ada-instruct dataset

I hand-wrote 21 examples, and also used 500 examples from ROPES augmented with reasoning from GPT-4

was the dataset really that small? @euclaise , kind of suprising considering the size of some STF datasets these days.

NousResearch org
β€’
edited Mar 12

We did not use the Ada-instruct dataset

I hand-wrote 21 examples, and also used 500 examples from ROPES augmented with reasoning from GPT-4

was the dataset really that small? @euclaise , kind of suprising considering the size of some STF datasets these days.

Yes. The original Ada-instruct even used only 10 examples

I trained for dozens of epochs though

Sign up or log in to comment