Add final checkpoint: g2_ffn_attn_kd_conversation_init_loadfix_v3
Browse files- .gitattributes +9 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/.metadata +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__0_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__0_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__1_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__1_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__2_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__2_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/common.pt +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/metadata.json +1 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/latest_checkpointed_iteration.txt +1 -0
.gitattributes
CHANGED
|
@@ -76,3 +76,12 @@ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0
|
|
| 76 |
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 77 |
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 78 |
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 77 |
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 78 |
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c084f783e91403af5931b8ef22b6e0d5954eff7e668051265845c1e0e92087d
|
| 3 |
+
size 315208
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:700919ddc6ecfdd4026cec7a8aa104b025964a2c140f6b9825d33bce96395b4e
|
| 3 |
+
size 167052408
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__0_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc8d174b2874335bd79c27df4c5f0ee1ae01f2aa14540fbdf60931d2ebd6e153
|
| 3 |
+
size 167086772
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:289196143b198a628ed8265b5656944e717bef924ae618ca55c6283f0ed2c2bb
|
| 3 |
+
size 166878800
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__1_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cd84a9769f1d27616a5dffaf82c08c479e1881d21aa15146461d84cb9c9ac20
|
| 3 |
+
size 166876264
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:949b8b737452d74a8f04ecdd60521bc9c699d36295840620376b99eb89354476
|
| 3 |
+
size 166685732
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__2_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8518f29b01434d2bd02eab3ee63d91d0836282b79a4bddf41426d3f98345bb3
|
| 3 |
+
size 167343452
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1912ab9ae47f6a0c70a0c2d83cdbddf94f078fa4e6cc1589d47c12b12cbd373
|
| 3 |
+
size 166685732
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58c3c0ddfc09a9557539dbd3515cdf8c8535f75f4a1f817844a70be223268976
|
| 3 |
+
size 167343452
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/common.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc3a0df47d07bd3dfc37f97d06e8d4669d7b054079f091e59b45093341b577dd
|
| 3 |
+
size 22684
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/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/conversation/kd_init/latest_checkpointed_iteration.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
600
|