diff --git a/.gitattributes b/.gitattributes
index 52373fe24473b1aa44333d318f578ae6bf04b49b..93701b33c5701a061a1935b67f6a134952d2b74c 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -34,3 +34,37 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__10_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__10_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
diff --git a/last-checkpoint/optimizer_0/.metadata b/last-checkpoint/optimizer_0/.metadata
new file mode 100644
index 0000000000000000000000000000000000000000..6e84d0be9e5d00972331538ee344d331ef1ec4bb
--- /dev/null
+++ b/last-checkpoint/optimizer_0/.metadata
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b234d441ca37bd17c52b1ca5b9bb096182950f6e9f3a4249ca29daaa41bd3134
+size 2341124
diff --git a/last-checkpoint/optimizer_0/__0_0.distcp b/last-checkpoint/optimizer_0/__0_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..d64c54cf0ca058103f51b1a9850e4d51cb04364a
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__0_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b775dea05086885cd2c6fca752a4b1867b9b4002ce03ac9866aba10bea975580
+size 500739836
diff --git a/last-checkpoint/optimizer_0/__10_0.distcp b/last-checkpoint/optimizer_0/__10_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..5e0b941f8b903574f4c3842532e78c2fc45251c5
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__10_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a88476b2faef510b55e43eccf178cca0c566d62dd6dff93cf5cbc16b22c088
+size 500768072
diff --git a/last-checkpoint/optimizer_0/__11_0.distcp b/last-checkpoint/optimizer_0/__11_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..70987cc0dd25a7e6b80af9590b7eeddf375209e8
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__11_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dfd61df2aa7f5133c113a4882b52a3dcde358378a18b9a6d4ee01df59c30034
+size 500768072
diff --git a/last-checkpoint/optimizer_0/__12_0.distcp b/last-checkpoint/optimizer_0/__12_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..6803e7ed17db66d7db49b953352181e3fdd3fdcd
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__12_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:298ea2c5bd52c1fbfa842831e035e23d692caca694bd998960d76c5571281b2e
+size 500768072
diff --git a/last-checkpoint/optimizer_0/__13_0.distcp b/last-checkpoint/optimizer_0/__13_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..9ab75e2202bd241c3a0ef7220907fa97bbd6320b
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__13_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4bdc88a586cec45fe7b60718f44a635aecebb19129283c78f8fb50cb1781741
+size 500768072
diff --git a/last-checkpoint/optimizer_0/__14_0.distcp b/last-checkpoint/optimizer_0/__14_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..bd76f55772a3d3663176265da94d4ad1c758f0ed
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__14_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c73b3b47de5a5cc1797eba6d565e9fe1936d11bb27dfab994570f48403099c2
+size 500768072
diff --git a/last-checkpoint/optimizer_0/__15_0.distcp b/last-checkpoint/optimizer_0/__15_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..935f162073c2980d579bd46e13044c1e51c29edd
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__15_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ee9043094ab8167115a03695ec11b1d403dc8972019d2db8f7ff744522a4f7
+size 500783880
diff --git a/last-checkpoint/optimizer_0/__1_0.distcp b/last-checkpoint/optimizer_0/__1_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..d2bfb0ea6f9bbffd89fe62b9ad6ccc8f22673482
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__1_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4a712e3f46fc46bcec1828b7085f4daa6426bedf3bd13f671a02ec7dec087d
+size 500765796
diff --git a/last-checkpoint/optimizer_0/__2_0.distcp b/last-checkpoint/optimizer_0/__2_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..4651a5bf4c0efefe1b667fb657700cd5f1f8846c
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__2_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a980f9552514589d810351294ab3a0e2da9fc1ecbdfbd05a3256a5fbef3f1d11
+size 500765796
diff --git a/last-checkpoint/optimizer_0/__3_0.distcp b/last-checkpoint/optimizer_0/__3_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..65a5ff14fc6b786533132acdb48b79746d4527a4
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__3_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e2a5dcb3498cd93754c0e79d44defc54d98f23a128c718726ba057602d59b6
+size 500765796
diff --git a/last-checkpoint/optimizer_0/__4_0.distcp b/last-checkpoint/optimizer_0/__4_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..f583d5bbb8a5e86f544e410719046dbb8b3b8baf
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__4_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1207decf490a676fba89edf950b7d12f1feaa8e01705fa6e0b3d453f336e2e6
+size 500765796
diff --git a/last-checkpoint/optimizer_0/__5_0.distcp b/last-checkpoint/optimizer_0/__5_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..1f83b6e00f533f77f9b30984a1731525fc114c42
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__5_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a5261d5dd82c709543d14c68c624915d8bb026685b43351345058aaace1307f
+size 500765796
diff --git a/last-checkpoint/optimizer_0/__6_0.distcp b/last-checkpoint/optimizer_0/__6_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..1835c457e675348af0937df1a0846acc57bfa611
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__6_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1614ada2eb2e8c4061058c29cd0ec62e452732ae7fde369da1bbc678be6f6df
+size 500765796
diff --git a/last-checkpoint/optimizer_0/__7_0.distcp b/last-checkpoint/optimizer_0/__7_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..163be0a9aaade12678c11719db7d894b25a4ab58
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__7_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5795da86056f316501c020e6b1e6f8327a986d99f82f85beea74d5213514bb8
+size 500765796
diff --git a/last-checkpoint/optimizer_0/__8_0.distcp b/last-checkpoint/optimizer_0/__8_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..1ecc6436ec463eaf95234a7ec75325d3cdcdc91b
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__8_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ab9c5000c3d63d1021016f7f7be003e38e131049adfd7fc772619cd6d0e3e0
+size 500765796
diff --git a/last-checkpoint/optimizer_0/__9_0.distcp b/last-checkpoint/optimizer_0/__9_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..6054e30c415f834f1b90e5ce4180791c0a3ccec3
--- /dev/null
+++ b/last-checkpoint/optimizer_0/__9_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d516c3851a3e86866783a2f215da7ed338ea75089f5e78299724ae828e37b5
+size 500765796
diff --git a/last-checkpoint/pytorch_model_fsdp_0/.metadata b/last-checkpoint/pytorch_model_fsdp_0/.metadata
new file mode 100644
index 0000000000000000000000000000000000000000..fc9562d366f54715decc5c660d64e08af813d551
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/.metadata
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c15d407bccb56bc44c87071192597ef8cab56756b0eb8ad4e3998c8c565307
+size 992294
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..a4893396c501705d7006871de38c389e73bc1fd7
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f757526e1ead0a79bb91fa196241e18a391ec8fb97ad37e14633fae6de6021
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__10_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__10_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..af8a086f7fa84f8deaf0ed3f1f0a18eb416d617c
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__10_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0416e09d29894c3bb365aeafa7e9d4cd22f2f9de84f8a67937c24c686f1b294f
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__11_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__11_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..48ea402f2c9cf45c61576f02ef0934bb64e43670
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__11_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa69027b7cfd90f942c69e4038df0ddcdd6e95fb2e0fe8c14802216a76fb086
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__12_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__12_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..fd0c73797d490fd22d2cdcfaa220da49f5019287
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__12_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b830cf0f8ffb9a448d9788b9395cc54bb056718466729c4d786687cc425170ea
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__13_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__13_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..29f28a82f375a518a6aca84107bbe7ebee31c568
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__13_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c9fd92e6e2788867775461133a07129b517bff458d7e2eadd93390876cf5d9
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__14_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__14_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..956cbcbb91a8cc3ef93ada7a152a7f1755020bc1
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__14_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3029fba8074e67ae0c222f4c8e52ece3f3c83f83ebb1d53e6a5e1d2265f703b2
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__15_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__15_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..7c55ce431d1f048aac6a5f91b68398834a527255
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__15_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283db2f4e5c59276827f363cd9d11c0d607d232fc695904e93a9f00acf5a9572
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..bc0ac169e957f4b9422df0169f6482066b2c7bf7
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9644933f20fc0beaa32c4960c2cac0182ce9f86110c25424ba7f72179d6765
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..bce5af77e276e9c57974187f37fe91ec298651ad
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdaa76df8911fc060420414ce6ea0ad99c95c8fe5d209a759859855745219afd
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..0e7aa59c1e04d6dd9b3a64ad70461c5590ca07e5
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b49c4264ae50f3ab061de657f9c5b39dcf9b0604891bce8b1df02697155448
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__4_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__4_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..796a90daed57923dc36d4f9c58a482dbf9157269
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__4_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8479f6217e244d81724143951b19713e1a3313b6601166c70b540867b85cdd2
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__5_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__5_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..347df2f681b3f05f3e4611e2042ee9bb78d46ba2
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__5_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4930c7600ab50a883846acee9c858484b3425e54cf772c682ce37969fb511db
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__6_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__6_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..883e73d8b63fc7b9e4533c303c64693758c45c08
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__6_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c167da6ad80e0326b7d5a0634bc523b3acfe36f862883ad1d0f4f61bbe3321
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__7_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__7_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..53e36dbbc42fbaf32d07937cbaa8327484a7eb66
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__7_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e40734e81083dd9e876d5f2ed18bfa0e52448ac9c83d783bdd71de6c80f9f35
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__8_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__8_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..09dfe7b2b4095e70d2ddea91c81d93776374564c
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__8_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c6d84b6f120d2f758497f9c756eff483da56a9b443535a69536f70614957aa
+size 325867980
diff --git a/last-checkpoint/pytorch_model_fsdp_0/__9_0.distcp b/last-checkpoint/pytorch_model_fsdp_0/__9_0.distcp
new file mode 100644
index 0000000000000000000000000000000000000000..25f028adef87ddb8fa1144c6b7a093313ad4e780
--- /dev/null
+++ b/last-checkpoint/pytorch_model_fsdp_0/__9_0.distcp
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810d09f4f4f59d8913fd6e0aacc806a4b63d163ea9f0a610a78b08cb9270cc2f
+size 325867980
diff --git a/last-checkpoint/rng_state_0.pth b/last-checkpoint/rng_state_0.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8be4da50e08ef9215e5f46f9cc7ebcb8fd4593eb
--- /dev/null
+++ b/last-checkpoint/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955b895101e13c81ba510512313a06782795770a0bf998c90f718166d25f1664
+size 15984
diff --git a/last-checkpoint/rng_state_1.pth b/last-checkpoint/rng_state_1.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3450e76a148654c7a712cc0f7f4fbfb8af73468e
--- /dev/null
+++ b/last-checkpoint/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096e351ace65ff91008be171a45173ed6369cc639fce73a288f671041e24b0ec
+size 15984
diff --git a/last-checkpoint/rng_state_10.pth b/last-checkpoint/rng_state_10.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c5cac5ff960c4504532780a9137eaa7166130a26
--- /dev/null
+++ b/last-checkpoint/rng_state_10.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d4ccf5bcdf5478695218ce9cac9d67bf8376f96f26acb4bc3b6a83253d7f03
+size 15997
diff --git a/last-checkpoint/rng_state_11.pth b/last-checkpoint/rng_state_11.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ba021f2b82cbda0618405cf68e638e8565b376e9
--- /dev/null
+++ b/last-checkpoint/rng_state_11.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ba7f3baea2e63bccfac7e530dc439874245b4cced6c3f1501ce779af02c195
+size 15997
diff --git a/last-checkpoint/rng_state_12.pth b/last-checkpoint/rng_state_12.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c274bbd7259c10f5893cd107194f9d422409fec7
--- /dev/null
+++ b/last-checkpoint/rng_state_12.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddcec8df6cf92d3e330f8a110aaac985a87813bb588d23c47bcd15f7c59a252
+size 15997
diff --git a/last-checkpoint/rng_state_13.pth b/last-checkpoint/rng_state_13.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2d2c97483502dfc542aa857e1c254dd05c37368c
--- /dev/null
+++ b/last-checkpoint/rng_state_13.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e84103490e5a16344f55fd7605a30dac6030bf3142b7d6b7d06c54c04875a4
+size 15997
diff --git a/last-checkpoint/rng_state_14.pth b/last-checkpoint/rng_state_14.pth
new file mode 100644
index 0000000000000000000000000000000000000000..79009482c5dd11c165832357730f649e1f5cfb18
--- /dev/null
+++ b/last-checkpoint/rng_state_14.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522c01c77754e44cd335b9bf502c0157dfb071a4916b475a7b3cbc76dded9e12
+size 15997
diff --git a/last-checkpoint/rng_state_15.pth b/last-checkpoint/rng_state_15.pth
new file mode 100644
index 0000000000000000000000000000000000000000..75c455fbc9a74c84f4c7e8c79cbe0f68c6803912
--- /dev/null
+++ b/last-checkpoint/rng_state_15.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd5abbaf634edfaa411a3bc4a9c764d09d8043f95b0892bb73c3d6e08f9e648
+size 15997
diff --git a/last-checkpoint/rng_state_2.pth b/last-checkpoint/rng_state_2.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9b3bdae1f6c60868005426daf443380b27066cba
--- /dev/null
+++ b/last-checkpoint/rng_state_2.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21c61b1a7e793bbdec183de3b52da90042305234bc7e5887986655cd3fc2192
+size 15984
diff --git a/last-checkpoint/rng_state_3.pth b/last-checkpoint/rng_state_3.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b05597dd523f7c9a629beaa525e6ad7122b018f9
--- /dev/null
+++ b/last-checkpoint/rng_state_3.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348742498d81780506d9760c655a7a7555185b5fbd70a7ae296d88fd9aeecd84
+size 15984
diff --git a/last-checkpoint/rng_state_4.pth b/last-checkpoint/rng_state_4.pth
new file mode 100644
index 0000000000000000000000000000000000000000..28f7e8868fd4df63a6756b111fe1ea4a8e7eb6e2
--- /dev/null
+++ b/last-checkpoint/rng_state_4.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399c4700dab9ae7b754110ce307fb7e26e22cb49b5bb233c435f0f12b77c202f
+size 15984
diff --git a/last-checkpoint/rng_state_5.pth b/last-checkpoint/rng_state_5.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b81cf1f9e78f606b05125af5ec552416d94116f4
--- /dev/null
+++ b/last-checkpoint/rng_state_5.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864ea2379cc907eb4189c52706cb978150d9c26e18abf74679590729a8f0c8e8
+size 15984
diff --git a/last-checkpoint/rng_state_6.pth b/last-checkpoint/rng_state_6.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d9cc9104b41c399577a5b19f280ae6ba448edc4f
--- /dev/null
+++ b/last-checkpoint/rng_state_6.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25755ba07299ee6ff45936dd04df329596319c9f8095af71e6f3a219e7543e26
+size 15984
diff --git a/last-checkpoint/rng_state_7.pth b/last-checkpoint/rng_state_7.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7736ce8fe27978c921d21f9fd6d1cda8c15a03f9
--- /dev/null
+++ b/last-checkpoint/rng_state_7.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908f018cd701ed629c41299726da4a25f202f20a1d4bc2075a2266ed4013db3a
+size 15984
diff --git a/last-checkpoint/rng_state_8.pth b/last-checkpoint/rng_state_8.pth
new file mode 100644
index 0000000000000000000000000000000000000000..58c3af89ecdb49354941bfc5c075974ec2ef8e00
--- /dev/null
+++ b/last-checkpoint/rng_state_8.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca0c0ac219cd2ca2a18d8a57b0e88c5e780eceed5e286e166cd56d65379268e
+size 15984
diff --git a/last-checkpoint/rng_state_9.pth b/last-checkpoint/rng_state_9.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ebfb36995bd19404a6570c8f920695c98d2dc705
--- /dev/null
+++ b/last-checkpoint/rng_state_9.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7285e50c3ac3dd7c6b2a0fce2426e160a499100149eeb22168e36bf4aeba4f3f
+size 15984
diff --git a/last-checkpoint/scheduler.pt b/last-checkpoint/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..62483a94ac3f287b7a340c57f038439fa17e5701
--- /dev/null
+++ b/last-checkpoint/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fd674a2f040b8480f1192e3fa4ec1131dbc43297e15a8144fda84f3eba5749
+size 1064
diff --git a/last-checkpoint/trainer_state.json b/last-checkpoint/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..057ca5a4b9ed8a6bb134fcccc3207ba073c4fe7e
--- /dev/null
+++ b/last-checkpoint/trainer_state.json
@@ -0,0 +1,33 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1000,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 10,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 45608903639040.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}