Training in progress, step 90000

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:d5806c227e6c6e6b970be44a8f9861ac0302947c457a1d17293b2b598519e7b6
-size 2716741
+oid sha256:644575a971cfdb6e92667dbac50ad2caefda4971d9742fff029a6e59d1f52267
+size 2877036

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaeed3c9288a009a0be8382b0b7db35cdd84b4df54da7775d1529f5ee9c8cb20
+oid sha256:fedbca6ff9af8101e6d12d511c82f363811d9e7df10a6548fb438f22cf8fd088
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e267464fb2ecd0ee5067719c791d6b4b96545b3a881c2ef71be3edd08bcfd30
-size 5304
+oid sha256:9ae883b3b464d3c815409ee2c492f2b8fdc1d7ff5b65cf0b942c59541166be8b
+size 5432