Attempt #2 at Context obedient for 128k context model, trained longer at lower LR.

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f2b5337a72bf9ea6a13ec5af03c6b22cdaf20b05f0e99f253f5e45f3bbcfd2
+oid sha256:d90798ab939085488d815765203720caf7e86851aa88c071ade790a7c26d4339
 size 4972489200

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b439fb9e156b35935c3612baa4f45ef01ddbd919db5ab098401cc41ad414ff14
+oid sha256:a55e690763747f25da96435e7f4d81827b68e1438e3e1d7e03c0be224adf4c45
 size 2669692488