Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
arkmm
37 days ago
|
parent
|
context
|
favorite
| on:
Show HN: I trained a 125M model to autocomplete pi...
Very cool! Can you say a little bit about the size of the DPO training examples and how long training took?
simedw
37 days ago
[–]
For DPO I only had around 700 preference examples, so not much data at all. That took about 12 minutes to train on a single GPU.
Pretraining was obviously a a lot slower, the 125M model took roughly half a day.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
