siddharthmb commited on
Commit
489026b
·
verified ·
1 Parent(s): 656bac2

Add full training checkpoints (FSDP model + optimizer state) for sft_ifp

Browse files
.gitattributes CHANGED
@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoints/step_1000/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
37
+ checkpoints/step_1000/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
38
+ checkpoints/step_1000/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
39
+ checkpoints/step_1000/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
40
+ checkpoints/step_1000/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
41
+ checkpoints/step_1000/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
42
+ checkpoints/step_1000/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
43
+ checkpoints/step_1000/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
44
+ checkpoints/step_1000/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
checkpoints/step_1000/pytorch_model_fsdp_0/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03111b3a55866dd94d7c3fdea1eb113b9a43d503870c688feab62385ebd01458
3
+ size 1181263
checkpoints/step_1000/pytorch_model_fsdp_0/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123359fca8d4f10b35d3c82b1aa219fe58c1ad41e4d175b038a36bf5b69130e2
3
+ size 986738817
checkpoints/step_1000/pytorch_model_fsdp_0/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981e37205b259b42a226fff0da1d495da676f4c2fa15e376be4d3e374eeb7929
3
+ size 986738817
checkpoints/step_1000/pytorch_model_fsdp_0/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2be3bab45ccf92e9ac629ec489cd98e282f4f468be8a81450d6e6bb4c70a33e
3
+ size 986738817
checkpoints/step_1000/pytorch_model_fsdp_0/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc77fb5f26b789deedcf23387a5497521360560e5d979650a31477c43a63fcb9
3
+ size 986738817
checkpoints/step_1000/pytorch_model_fsdp_0/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0dda1b55d154941fb7320d8a8443b34afb3e3501a105d1260d08964c398674
3
+ size 986738817
checkpoints/step_1000/pytorch_model_fsdp_0/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae69fc94e69f31bd1356c809f172fabed57e40a8a5796909cd7e3fc060a4290a
3
+ size 986738817
checkpoints/step_1000/pytorch_model_fsdp_0/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a600d1c7c069883bb09f5d32f7fb8d6f07f2afb554a5b92021d60c89be413d
3
+ size 986738817
checkpoints/step_1000/pytorch_model_fsdp_0/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3af962d9969db28b67c65c6400b0c7daf09946037bd2f92691cdbb4defa1d03
3
+ size 986738817