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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/linked_runs.txt +1 -0
.gitattributes
CHANGED
|
@@ -627,3 +627,20 @@ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias
|
|
| 627 |
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-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
|
| 628 |
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-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
|
| 629 |
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 627 |
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-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
|
| 628 |
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-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
|
| 629 |
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-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
|
| 630 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 631 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 632 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 633 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 634 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 635 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 636 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 637 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 638 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 639 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 640 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 641 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 642 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 643 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 644 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 645 |
+
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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 646 |
+
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-1e-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-1e-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 sha256:26db2d499ba820723be62bdd2fa86fa2b9877e8f40c21d41d438ce1eea47b10c
|
| 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-1e-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 sha256:69a04a4d2e05d80e1a837b52ebfe694b6e0785299bdb40446ad3d2c8568d18b6
|
| 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-1e-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 sha256:237b2186f742cd4b011157394b0fe229f7e0242dd343cdf62990dc1e9789e640
|
| 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-1e-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 sha256:8beee01496c0efa0ed92e396da31a621af4287eb12b8442b7a0ca6aa98cc5db4
|
| 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-1e-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:f95a1838d17c7494b362c5c65a48e001f88e6af7a3e8aa4dc3d83f012937aa75
|
| 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-1e-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:db3c6273d3b0f68d4a593c5c302bd0fefe20940eebf0a19b757ba63e13237310
|
| 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-1e-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 sha256:687f0eb53b479596c027a14dce7ef192790f44fcca6b9315ff636f5c5f6f1d25
|
| 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-1e-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:fe3792444b2a0ab32dd4815f7d3e3a044cd58c9114117ff343d9007347fc15de
|
| 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-1e-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 sha256:83f2d6d50a16adc7ec16a80dc3d3ba9f9920a881246eb2d93b76657d9694c5fd
|
| 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-1e-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 sha256:116cdda8377b7c1513a793e6919790792120a909591d7157f56643bb9cec6483
|
| 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-1e-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 sha256:9db13d73d5dd945d52cefcf6e61fd1f323f7d9b5889b3d8b381000d784c11188
|
| 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-1e-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:dec6c88590398fa6e128070db8f452972b910d2ff23b4971d58efca8d0556bca
|
| 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-1e-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:cea69ed13540762f23df14aeabd2776f39c262219f4a8040df2d174f381bebc6
|
| 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-1e-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:f4d25aa9b633836dc4ac0d2af3ded0f601bf6acc8c8bcbedd8b194cf9ea67713
|
| 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-1e-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 sha256:7e7cada9e6e200de5d5bb0eda3a881741a5ac4941a34dc0e13433f41ba93b394
|
| 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-1e-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 sha256:32ee304d48e5c1b603edf858f5c25da4a031d1ed4f8a94301d03e736208e192f
|
| 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-1e-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 sha256:57feaf599d12983ba9b07ee0be793e9e0033ea840a1c5a38b8e26dfc7598c35c
|
| 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-1e-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:bbed1daae3a52dc13d55810678442abdccda296b8f96456c066db6d131310f47
|
| 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-1e-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-1e-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-1e-2-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/linked_runs.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
2025.05.21-01.18.22
|