Add final checkpoint: g2_ffn_attn_1phase_code_loadfix_v3
Browse files- .gitattributes +9 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/.metadata +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__0_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__0_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__1_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__1_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__2_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__2_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__3_0.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__3_1.distcp +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/common.pt +3 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/metadata.json +1 -0
- g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/latest_checkpointed_iteration.txt +1 -0
.gitattributes
CHANGED
|
@@ -67,3 +67,12 @@ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/kd_init/iter_000
|
|
| 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 70 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__2_0.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
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82b6a42e808214514fd1abfc67a35f2db0b851ad2a417e9c43d11b8f357fda1a
|
| 3 |
+
size 227253
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9315598be63ca65e01e955d58ad2a69dc6064005a6f1700eca01bd1750b6f876
|
| 3 |
+
size 124218772
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__0_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d9108013e9efa6c93c1ff91a4f79cb4a1e0c5286b98b5df034ec5a3446913fa
|
| 3 |
+
size 124744724
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c7683ffce34077d0ba86302f1b6ce3901fa409c2d4ea304b51e26fa53c55e72
|
| 3 |
+
size 124162768
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__1_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d3caa75599d0821581e26c6bb154e3c72b1f6d2f60fe93128a0be62be644ce9
|
| 3 |
+
size 124543724
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76ecfbd6747afdc3ba3b19158e9dbe4f9f2d7c93a9dc670bb63f1f6663abe8dc
|
| 3 |
+
size 124192444
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__2_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ba9d2b576fca357904bab0c7c4c3ee06b206ecb721105b4fa779ff90b53834b
|
| 3 |
+
size 124845444
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:437464d713c83d465b9b62cb695b8db49f5069f327348508e37eca101ebb8b5a
|
| 3 |
+
size 124192444
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/__3_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4bc0ab12efbbbbff5cd292caff454317b3d272bbbe36f02047b76c40170ac98
|
| 3 |
+
size 124845444
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/common.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0e12c6a1439c40077fc73d1d0c5dd34cbcff5887f3693a0108f0050066f649f
|
| 3 |
+
size 22044
|
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/code/one_phase/iter_0001800/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/one_phase/latest_checkpointed_iteration.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
1800
|