Upload folder using huggingface_hub
Browse files- .gitattributes +17 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/common.pt +3 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/metadata.json +1 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/latest_checkpointed_iteration.txt +1 -0
- model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/linked_runs.txt +1 -0
.gitattributes
CHANGED
|
@@ -678,3 +678,20 @@ model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep
|
|
| 678 |
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 679 |
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 680 |
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 678 |
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 679 |
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 680 |
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 681 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 682 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 683 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 684 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 685 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 686 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 687 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 688 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 689 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 690 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 691 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 692 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 693 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 694 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 695 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 696 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 697 |
+
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e88d399becaa1f56fa053f977d2dca80d81d3888fb7e21c9b539c055ff65689
|
| 3 |
+
size 1145765
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ee3d01e8f8602cf9dda63326a472d31e190dad61a99beb948d02aa13c2db32b
|
| 3 |
+
size 687946575
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee32890780cd57c0a9e0c054d7b125c90be43fc99d12e44e92a3dad5eb6febf4
|
| 3 |
+
size 687944002
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1c061305e2974308d23f8df37279f07d4d357648abfe0597c4de00fe0431ba9
|
| 3 |
+
size 687423642
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42035d90d4ffb63beb004aaa39dc68cc9d49ee29c6e6fe95402da1b1b065e9aa
|
| 3 |
+
size 687437254
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3abada5a24824368c304c15cd64739379944d6931f72610579f2b59aa755dfd6
|
| 3 |
+
size 687641060
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2382958a5427be2c9e8a3242a85fe9e1de339810b736af918976eeb977c8eece
|
| 3 |
+
size 687662457
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b922da0a5f88d891753f7aa7a74e6aaaf8d6a87a1270e2bea0d0c6567f1ba479
|
| 3 |
+
size 687238284
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9550bfda4e8968231fe9dabac4f939b8926e6b3cf7ab5d5a4a4dc35dc510a83
|
| 3 |
+
size 687579804
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83a3de91f565cf7f54849f56b0b955f9ce73440ca418f068b50af657e151eda8
|
| 3 |
+
size 721091665
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcab00bd760ae799ed8c030c3c4f99033f50a9ed1615fb2a8308ea9599044778
|
| 3 |
+
size 720935490
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6914410aec76221a4b48f04538373e1de8f81e65d991e725f3b8be2aa9141f5
|
| 3 |
+
size 719517224
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2c516e610a696cdfe9f2a2f4905f7f3795969524025bab15b7dc52bf7e09fe9
|
| 3 |
+
size 720935490
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c09e1cbe0f6d3b975c2e58260f0bf8e86b6bddd1f954166423521a9524af1116
|
| 3 |
+
size 687238436
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb6e8d9f4cc74755e31c2f45510db351395ce97fc72db2be8821d28923488a8e
|
| 3 |
+
size 687842980
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4cf6bc747a4aeb7fdb47a65eefcc79c0af148e3792543bfff4f1594a25c014d
|
| 3 |
+
size 686847861
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18dc78e3cde92a3007340c8f3af5bb43a6d54b9a12099ae80c6a94eedc995180
|
| 3 |
+
size 686792827
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/common.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1f0b08ba7be4c843795023d2624ad763fbe4d544b18e289cd300459c5005e47
|
| 3 |
+
size 19175
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/metadata.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"sharded_backend": "torch_dist", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1}
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/latest_checkpointed_iteration.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
4768
|
model/dev-muon-gate-ts-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-mp2-pp1-lr-4e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/linked_runs.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
2025.05.22-00.16.53
|