Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
p1esk
on Aug 23, 2019
|
parent
|
context
|
favorite
| on:
OpenGPT-2: We Replicated GPT-2 Because You Can Too
It's $50k per
training run
. Their main contribution has been finding the optimal hyperparameters, not described in the OpenAI paper. Obviously you need more than one training run to to that.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
