Training in progress, step 95000

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 sha256:644575a971cfdb6e92667dbac50ad2caefda4971d9742fff029a6e59d1f52267
-size 2877036
+oid sha256:2cd3e0bb9293074cadaea0351ac0c1c457cb9e1836b7e52e874f83c80890fc6e
+size 3036822

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612d631c044f37770017adfd26869e1260bc9df34b14c783f81780187f77bf0f
+oid sha256:8ddb99d0a95de774abf018725dc4c57b062bc0fe60f01f9c99f149c366f323f6
 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