Hugging Face's logo

jayasriii
/
20M_57M

Model card Files
xet
 Community
jayasriii commited on
Commit
9c8d542
·
verified ·
1 Parent(s): da5ceb1

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. 20M_57M_15e3_8B.csv +0 -0
  2. 20M_57M_15e4_8B/blumodel_muon_step00013716.pt +3 -0
  3. 20M_57M_15e4_8B/blumodel_muon_step00014478.pt +3 -0
  4. 20M_57M_15e4_8B/blumodel_muon_step00015240.pt +3 -0
  5. 20M_57M_15e4_8B/blumodel_muon_step00015259.pt +3 -0
  6. 20M_57M_24e3_10B.csv +0 -0
  7. 20M_57M_24e3_10B/blumodel_muon_step00003812.pt +3 -0
  8. 20M_57M_24e3_10B/blumodel_muon_step00004765.pt +3 -0
  9. 20M_57M_24e3_10B/blumodel_muon_step00005718.pt +3 -0
  10. 20M_57M_24e3_10B/blumodel_muon_step00006671.pt +3 -0
  11. 20M_57M_24e3_10B/blumodel_muon_step00007624.pt +3 -0
  12. 20M_57M_24e3_10B/blumodel_muon_step00008577.pt +3 -0
  13. 20M_57M_24e3_10B/blumodel_muon_step00009530.pt +3 -0
  14. 20M_57M_24e3_10B/blumodel_muon_step00010483.pt +3 -0
  15. 20M_57M_24e3_10B/blumodel_muon_step00010799.pt +3 -0
  16. blu_muon_log.csv +0 -0
  17. del.csv +0 -0
  18. del/blumodel_muon_step00013716.pt +3 -0
  19. del/blumodel_muon_step00014478.pt +3 -0
  20. del/blumodel_muon_step00015240.pt +3 -0
  21. del/blumodel_muon_step00015259.pt +3 -0
  22. train_muon_20MNe_57M.py +1 -1
20M_57M_15e3_8B.csv ADDED
The diff for this file is too large to render. See raw diff
 
20M_57M_15e4_8B/blumodel_muon_step00013716.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ae1d4212fb361be2e9386211a7a7501a5564c2a0084a9a58654ba2b64179b9
3
+ size 691253095
20M_57M_15e4_8B/blumodel_muon_step00014478.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6af661185766991d38880d980467968e97e58072ceffa29efd5c19ab1db8e8
3
+ size 691253095
20M_57M_15e4_8B/blumodel_muon_step00015240.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad0c93c4ded1a7d73232e6a9bc7da019ace0224fa14b0f88f5aea9008f04790
3
+ size 691253095
20M_57M_15e4_8B/blumodel_muon_step00015259.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b66764afdf3598c0291f2b77fd7b520e722773d2a9954de9c2c04789b932933
3
+ size 691253095
20M_57M_24e3_10B.csv CHANGED
The diff for this file is too large to render. See raw diff
 
20M_57M_24e3_10B/blumodel_muon_step00003812.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c22b39df38254876b99db346f5068b79701544627ce43341bde59fc20cdeaa
3
+ size 691253095
20M_57M_24e3_10B/blumodel_muon_step00004765.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefd78234fc685b476b28a2e949085e65eb3b0d3f84481000e74fbf8803bc19d
3
+ size 691253095
20M_57M_24e3_10B/blumodel_muon_step00005718.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a9520539f5dbe661dd6d31ca9da051fe929fd97218487c71a00cb42205404a
3
+ size 691253095
20M_57M_24e3_10B/blumodel_muon_step00006671.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d75561c6229cdf6d62c9b2dd74d366521b8a040ff857afb2d46cfef91a4931f1
3
+ size 691253095
20M_57M_24e3_10B/blumodel_muon_step00007624.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d3251d7bcb99cb40ff1327b188acacbfd46bb2471f712f0a3e0b287f6033a5
3
+ size 691253095
20M_57M_24e3_10B/blumodel_muon_step00008577.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ca842639f7ebb5f9388b89496058cdcbf985b0dbac4c1f36d0c976964ecbd1
3
+ size 691253095
20M_57M_24e3_10B/blumodel_muon_step00009530.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59994e392ae8a81c16b1b6ba83e5ba849556af4dee837f3bd3930467fc0ec6f0
3
+ size 691253095
20M_57M_24e3_10B/blumodel_muon_step00010483.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:784158703dad6a26a8bdcddbf595b984ce40d25089f283b95052dfb8a99302c4
3
+ size 691253095
20M_57M_24e3_10B/blumodel_muon_step00010799.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefc96765bae023ceb93cabfe77477d603cb1a39db6c7440ea5998f805a80777
3
+ size 691253095
blu_muon_log.csv CHANGED
The diff for this file is too large to render. See raw diff
 
del.csv ADDED
The diff for this file is too large to render. See raw diff
 
del/blumodel_muon_step00013716.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fffa711cf391e80d37366a0f725071dd3dbc2d4a4179f681417700503e3b09f
3
+ size 691253095
del/blumodel_muon_step00014478.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70949fc285be0e3dd8d6aa072fbf5969158d73753af768e469f355f268e6017
3
+ size 691253095
del/blumodel_muon_step00015240.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:758d28a4e93645033d5fafcdfe2f8a08408e5c98fa6fcf9badd4af071ba3ef6a
3
+ size 691253095
del/blumodel_muon_step00015259.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abed9bbd60c5de6297336df5b56119dd8d369cdc7a1760568cca6fd78a1412be
3
+ size 691253095
train_muon_20MNe_57M.py CHANGED
@@ -460,7 +460,7 @@ class ModelConfig:
460
  # the decay tail).
461
  max_lr: float = 0.024
462
  min_lr: float = 0.0024 # 10% of max_lr
463
- max_steps: int = 15259 #19074
464
  warmup_steps: int = 500
465
  stable_steps: int = int(max_steps * 0.9) - warmup_steps # steps held at max_lr after warmup
466
 
 
460
  # the decay tail).
461
  max_lr: float = 0.024
462
  min_lr: float = 0.0024 # 10% of max_lr
463
+ max_steps: int = 19074
464
  warmup_steps: int = 500
465
  stable_steps: int = int(max_steps * 0.9) - warmup_steps # steps held at max_lr after warmup
466