Commit History

Added optimizer.zero_grad(), loss.backward(), and optimizer.step() properly
6eb22ad
verified

Bhavibond commited on

Minor updates to SCST RL
9bf77ba
verified

Bhavibond commited on

fix linebreaks :-)
a44d9ff
verified

Bhavibond commited on

Use SCST RLAI and check
94e54fd
verified

Bhavibond commited on

remove ppo training for now
dceaa5a
verified

Bhavibond commited on

use steps and check
25f3d38
verified

Bhavibond commited on

pass total_ppo_epochs and check
5c74aae
verified

Bhavibond commited on

remove ppo_epochs
a90581c
verified

Bhavibond commited on

pass set_seed through transformers
2402587
verified

Bhavibond commited on

cosmetic changes for PPO Model
a7c91cb
verified

Bhavibond commited on

AI legal assistant for disabilities
b383fb3
verified

Bhavibond commited on