SnakyMcSnekFace
/

Psyfighter2-13B-vore

Text Generation

Not-For-All-Audiences

text-generation-inference

Model card Files Files and versions Community

SnakyMcSnekFace commited on Sep 15

Commit

1211f0a

•

1 Parent(s): f19846b

Add plots for KTO training

Files changed (6) hide show

img/kto_grad_norm.png +0 -0
img/kto_learning_rate.png +0 -0
img/kto_loss.png +0 -0
img/kto_train_kl_divergence.png +0 -0
img/kto_train_logps.png +0 -0
img/kto_train_rewards.png +0 -0

img/kto_grad_norm.png ADDED Viewed

img/kto_learning_rate.png ADDED Viewed

img/kto_loss.png ADDED Viewed

img/kto_train_kl_divergence.png ADDED Viewed

img/kto_train_logps.png ADDED Viewed

img/kto_train_rewards.png ADDED Viewed