IvanHU commited on
Commit
e69bb6c
·
verified ·
1 Parent(s): d47beaa

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. .gitattributes +17 -0
  2. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata +3 -0
  3. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp +3 -0
  4. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp +3 -0
  5. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp +3 -0
  6. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp +3 -0
  7. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp +3 -0
  8. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp +3 -0
  9. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp +3 -0
  10. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp +3 -0
  11. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp +3 -0
  12. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp +3 -0
  13. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp +3 -0
  14. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp +3 -0
  15. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp +3 -0
  16. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp +3 -0
  17. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp +3 -0
  18. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp +3 -0
  19. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/common.pt +3 -0
  20. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/metadata.json +1 -0
  21. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/latest_checkpointed_iteration.txt +1 -0
.gitattributes CHANGED
@@ -440,3 +440,20 @@ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-bf16-ep4-mp2-pp1-lr
440
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-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
441
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-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
442
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
440
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-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
441
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-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
442
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep--top2-cf-2-mlc-0.05-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
443
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text
444
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
445
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
446
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
447
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
448
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
449
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
450
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
451
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
452
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
453
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text
454
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
455
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text
456
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
457
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-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
458
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-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
459
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-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
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:4c76566ec41a9aacfeb9efb7841700683990d162eb39522d2da95333b2758fd7
3
+ size 923218
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:5743b1913d9bf7441a963acfe698a39d4dc19c795b8e30d735d14a31013f65ad
3
+ size 545101300
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:159ee7b92688a1ac70f3dda417694981b8a35888bedf33b8626c2a38350dd709
3
+ size 545132060
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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:fb0723077da4e7c894dd9840cb75b597e5e925a9f8f7d9c9e8253efba6cb1614
3
+ size 499379568
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:1443dfec6eaf5411d31b41d9ac1e0d42487048eaf1b9baef8226eb6fbd6cdf72
3
+ size 498618012
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:23e73ea794b0f943658542439bdc3bed4887a282407520f2b8b975e128217c62
3
+ size 498643736
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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:ccdbd653d90aaf93a69c3816dcbde70b5edb43b7dce6309952409e843b7f95b2
3
+ size 499459932
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:6c534a409666787cd0392ed692171c1957246882309d315533ccea1d9f2471b4
3
+ size 498478892
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:3675d227b46e54daa1b6926145207c0c0618b49ebb4563d06ad2ce3d2ea4ff3e
3
+ size 499459932
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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:bcb3be03680f9e09c798998e57a41a4f5249b0f0c6c5b52476eb1a76a0376595
3
+ size 498583868
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:592741cedc6dc86e02a2a18f724781f64199dcbc2f1a1626068ca92b6fea2fac
3
+ size 499403292
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:4858d72b3cb9fa5719d46c085a946efe47d4c071b2d93517b69d93ab1c9e928d
3
+ size 544206316
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:655a68c53e33b6112972d230d4d35ddc48076984f63e654d6f0f43e1dd5165cc
3
+ size 544049468
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:9bf1763a986eb0a89ee9dd561c987e088dda8215c5366d1dc8bfe1c0e481f831
3
+ size 498583868
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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:d716704e1573e9aa0bc085f53d9c2a18aff273b3e0eefa969e7f060f3c8762f6
3
+ size 499403292
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:52ec83862940b8d19152721755dd0bec371de73a8fa4af0a743e702a8c197dfe
3
+ size 498422252
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:19d6fefcb7dbd3878674440ce269a5d4aa3b9fb6bcf397fc66541c7341597a6b
3
+ size 498353536
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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 sha256:8aee3d5918e1464ce743f079d2ea2a199de8fd232ac524c83088afdc5d04d2cd
3
+ size 18012
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-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-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/latest_checkpointed_iteration.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 4768