Training in progress, step 100000

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 sha256:2cd3e0bb9293074cadaea0351ac0c1c457cb9e1836b7e52e874f83c80890fc6e
-size 3036822
+oid sha256:784e6e287372478dc0aaae8ea7bb1e6bf345fdbd3c888a232cc0d7cae254f874
+size 3197117

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ddb99d0a95de774abf018725dc4c57b062bc0fe60f01f9c99f149c366f323f6
+oid sha256:fa69728014d6b03cf033cd9f72ac8b8e2bc4e89d8714ad2350faa4fa350c091d
 size 163832792