Hugging Face's logo

espnet
/
multi_turn_SDS_RLAIF

Model card Files
xet
 Community
“siddhu001” commited on
Commit
6422686
·
1 Parent(s): b509110

Add model files

Browse files
Files changed (15) hide show
  1. 2epoch.pth +3 -0
  2. config.yaml +0 -0
  3. images/equal_rate.png +0 -0
  4. images/gpu_max_cached_mem_GB.png +0 -0
  5. images/grad_norm.png +0 -0
  6. images/iter_time.png +0 -0
  7. images/learning_rate.png +0 -0
  8. images/loss_dpo.png +0 -0
  9. images/loss_rate.png +0 -0
  10. images/loss_scale.png +0 -0
  11. images/neg_reward.png +0 -0
  12. images/pos_reward.png +0 -0
  13. images/reward_gap.png +0 -0
  14. images/step_time.png +0 -0
  15. images/win_rate.png +0 -0
2epoch.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f602b54b5680b57cb5dceceb2d7184630f086d7d85b58e7cfbbf882f509bc332
3
+ size 7469766446
config.yaml ADDED
The diff for this file is too large to render. See raw diff
 
images/equal_rate.png ADDED
images/gpu_max_cached_mem_GB.png ADDED
images/grad_norm.png ADDED
images/iter_time.png ADDED
images/learning_rate.png ADDED
images/loss_dpo.png ADDED
images/loss_rate.png ADDED
images/loss_scale.png ADDED
images/neg_reward.png ADDED
images/pos_reward.png ADDED
images/reward_gap.png ADDED
images/step_time.png ADDED
images/win_rate.png ADDED