mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-25 17:10:51 +00:00
impl conditional reward
This commit is contained in:
parent
450d3dcfa4
commit
830ac3e10a
13 changed files with 52 additions and 24 deletions
|
|
@ -37,6 +37,7 @@ curriculum:
|
|||
word_len: 0
|
||||
reward:
|
||||
use_accuracy: True
|
||||
conditional_reward: False
|
||||
secondary_rewards:
|
||||
- name: cosine
|
||||
scaling_factor: 0.3
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue