Add final checkpoint: g2_ffn_attn_kd_code_init_loadfix_v3
Browse files- .gitattributes +9 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/.metadata +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__0_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__0_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__1_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__1_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__2_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__2_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__3_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__3_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/common.pt +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/metadata.json +1 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/latest_checkpointed_iteration.txt +1 -0
.gitattributes
CHANGED
|
@@ -58,3 +58,12 @@ g2_wiki_code_conversation/sources/ffn_attn_shared_router/wiki/iter_0001800/__0_0
|
|
| 58 |
g2_wiki_code_conversation/sources/ffn_attn_shared_router/wiki/iter_0001800/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 59 |
g2_wiki_code_conversation/sources/ffn_attn_shared_router/wiki/iter_0001800/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 60 |
g2_wiki_code_conversation/sources/ffn_attn_shared_router/wiki/iter_0001800/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
g2_wiki_code_conversation/sources/ffn_attn_shared_router/wiki/iter_0001800/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 59 |
g2_wiki_code_conversation/sources/ffn_attn_shared_router/wiki/iter_0001800/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 60 |
g2_wiki_code_conversation/sources/ffn_attn_shared_router/wiki/iter_0001800/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eca1fc1b49bfbc108c0ca7c656cb2ccd1690590f2f226fc0d03d6fec2e03cd6f
|
| 3 |
+
size 227281
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06a156da34212fa3dbc3369cadac45df00199c08a6608fdd42cf3090b511ac18
|
| 3 |
+
size 124218772
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__0_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8adee13ca4710eecc1fb6e743638e8becce7cb280c92213bc0ccb79295679c16
|
| 3 |
+
size 124744724
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca18cd495d7729bfa305c1f261a04a309dffaa52a79509054b1f1621929cbadc
|
| 3 |
+
size 124162768
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__1_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a11471202b614a3fc4d41d0f12501827e37df337dbdc64f5dd457a220d6521f9
|
| 3 |
+
size 124543724
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a8c4bbf4fde0824a000e3b469dc593eac3fb244ff6157b750713abc466c79b4
|
| 3 |
+
size 124192444
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__2_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a10779c5b43dd82716367f7697f54f01344e7f33dad7525d1487a3ad348d36
|
| 3 |
+
size 124845444
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07f02af2548ed43c731c87818bcc369368b21d39935869705fa6ab48799532bd
|
| 3 |
+
size 124192444
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/__3_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02975dc38e9ea783f78f6723992cc9dbe04d90dba989f839cf3e4638bb46c4cb
|
| 3 |
+
size 124845444
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/common.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60f4b0fbaa9229ac430465c68b396d1d2729ea8970ec2205a4e0a64c513a7c28
|
| 3 |
+
size 22108
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_0000600/metadata.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"sharded_backend": "torch_dist", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1}
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/latest_checkpointed_iteration.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
600
|