Training in progress, step 105000

logs/attn_loss_fn=kl, attn_norm=None, attn_projector=None, per_device_train_batch_size=8/events.out.tfevents.1726045328.d46c49212534

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784e6e287372478dc0aaae8ea7bb1e6bf345fdbd3c888a232cc0d7cae254f874
-size 3197117
+oid sha256:8776f691cdeaea0af487af1327add2c673304a5b9ceee831c5ca01dcc95844e2
+size 3356903

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa69728014d6b03cf033cd9f72ac8b8e2bc4e89d8714ad2350faa4fa350c091d
+oid sha256:5a0d713d37a4f94990dd4955b52413dff12d3391c13e4172a67552f2f4a1dd0f
 size 163832792