Hugging Face's logo

espnet
/
multi_turn_SDS_RLAIF

Model card Files
xet
 Community
“siddhu001” commited on
Commit
a784cde
·
1 Parent(s): 6422686

Add model files

Browse files
Files changed (13) hide show
  1. images/equal_rate.png +0 -0
  2. images/gpu_max_cached_mem_GB.png +0 -0
  3. images/grad_norm.png +0 -0
  4. images/iter_time.png +0 -0
  5. images/learning_rate.png +0 -0
  6. images/loss_dpo.png +0 -0
  7. images/loss_rate.png +0 -0
  8. images/loss_scale.png +0 -0
  9. images/neg_reward.png +0 -0
  10. images/pos_reward.png +0 -0
  11. images/reward_gap.png +0 -0
  12. images/step_time.png +0 -0
  13. images/win_rate.png +0 -0
images/equal_rate.png DELETED
Binary file (33.1 kB)
 
images/gpu_max_cached_mem_GB.png DELETED
Binary file (31.2 kB)
 
images/grad_norm.png DELETED
Binary file (25.4 kB)
 
images/iter_time.png DELETED
Binary file (30.3 kB)
 
images/learning_rate.png DELETED
Binary file (24.4 kB)
 
images/loss_dpo.png DELETED
Binary file (25.9 kB)
 
images/loss_rate.png DELETED
Binary file (31.1 kB)
 
images/loss_scale.png DELETED
Binary file (15.2 kB)
 
images/neg_reward.png DELETED
Binary file (30.4 kB)
 
images/pos_reward.png DELETED
Binary file (24.7 kB)
 
images/reward_gap.png DELETED
Binary file (29.5 kB)
 
images/step_time.png DELETED
Binary file (28.3 kB)
 
images/win_rate.png DELETED
Binary file (30 kB)