Merge other branch that was trained the longest

events.out.tfevents.1625416555.t1v-n-416475e4-w-0.250164.3.v2 → events.out.tfevents.1626277192.t1v-n-19ae6aab-w-0.394803.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad445ecd6d109520083c9efa0a35a59b33db9e87acd8084f173b5f95ab3592ab
-size 1361
+oid sha256:8f66884ba4af20d3c7e3f06cc3abc61b30a9cd9cd6f7680c45da66f169c3322f
+size 20033824

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c44cfab0c177dba64a78924e2aae587dc6a9a41c20cee3bf7bea6a3c386eac0
+oid sha256:34c099110802292b88e007fa9b34a86f5686e4498dd1f4a75500c4e38d5fa8c4
 size 500812408

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae4052178f4c51012eb97a4fde84eab198c9505e3969bf344c452db340dd0405
-size 526027101
+oid sha256:be3f3b784259f0f51391969be9556efdcc19273f8d4f8f4650dc260fb1107685
+size 526037233