Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
b21d98c
•
1 Parent(s): a1310ac

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=18740/flop_3.20e+18_step_9379.pt +2 -2
  2. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=18740/flop_6.40e+18_step_18757.pt +3 -0
  3. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=1100/flop_1.00e+17_step_1108.pt +3 -0
  4. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=260/flop_1.25e+16_step_139.pt +2 -2
  5. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=260/flop_2.50e+16_step_277.pt +3 -0
  6. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=540/flop_2.51e+16_step_278.pt +2 -2
  7. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=540/flop_5.00e+16_step_554.pt +3 -0
  8. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=23440/flop_1.28e+19_step_11724.pt +2 -2
  9. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=23440/flop_2.56e+19_step_23447.pt +3 -0
  10. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=420/flop_2.51e+16_step_215.pt +2 -2
  11. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=420/flop_5.00e+16_step_428.pt +3 -0
  12. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=6860/flop_4.00e+17_step_3432.pt +2 -2
  13. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=6860/flop_8.00e+17_step_6861.pt +3 -0
  14. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=2220/flop_1.60e+18_step_1118.pt +2 -2
  15. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=2220/flop_3.20e+18_step_2234.pt +3 -0
  16. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=120/flop_1.26e+16_step_70.pt +2 -2
  17. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=120/flop_2.50e+16_step_138.pt +3 -0
  18. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=8860/flop_1.60e+18_step_8863.pt +3 -0
  19. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=8860/flop_8.00e+17_step_4432.pt +2 -2
  20. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=5M_maxstep=40/flop_3.12e+15_step_47.pt +3 -0
  21. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=520/flop_1.25e+16_step_529.pt +3 -0
  22. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=520/flop_6.26e+15_step_265.pt +2 -2
  23. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=11980/flop_1.60e+18_step_5999.pt +2 -2
  24. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=1600/flop_2.50e+16_step_811.pt +2 -2
  25. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=1600/flop_5.00e+16_step_1620.pt +3 -0
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=18740/flop_3.20e+18_step_9379.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6f6818f501870f697768fa3c757ebd4aec337bac9b1d0d97ad6835710e4672c
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05534d560477ef520a110ee9a131b8873f4b33bd1cb7529297893dadb0cd8c1d
3
+ size 563343939
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=18740/flop_6.40e+18_step_18757.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051239ba348059f576b47ce365c46db239bf7da87bee527d5129ce1961827039
3
+ size 563346828
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=1100/flop_1.00e+17_step_1108.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528a02571b75eafabe07a22310a75b2949caf079680d417eef42fb41eff57dad
3
+ size 179382463
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=260/flop_1.25e+16_step_139.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b051c2731ec860a2e2fecdd1f6383bbeeabbe5ddedd4fc4f75dfae99214f169
3
- size 179382468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:830716a6988976293b41673abdf3071e5a30a2677587cfe1979df39d0a40fdbb
3
+ size 179380676
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=260/flop_2.50e+16_step_277.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8056a778ad36186df650867eb95bfde9364977224adf11bf5491f67592f575a0
3
+ size 179382340
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=540/flop_2.51e+16_step_278.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12c1544b32ec7cae5a4846bedcb4e3461d090e64280a2974813e7574e55bd57d
3
- size 179382468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d21ef78946d71538750734fe14455ad4545aca82cb8b4c3e70c1a0f53f6624
3
+ size 179380676
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=28M_maxstep=540/flop_5.00e+16_step_554.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a38532e09d5d7a43db52426637a04396245e8eefb30d291e1b45d98a018076
3
+ size 179382340
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=23440/flop_1.28e+19_step_11724.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57dd427d724fb532185cad0c35f83c2e5b97e5e464e78f5cfde096ace637549a
3
- size 1595773156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6543d5d80cd1331ca1cf9e02eafdda01dab180d33f46592c960064bb59dd0366
3
+ size 1595768804
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=23440/flop_2.56e+19_step_23447.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64b67149022c9ec686ac4ce3b32e9ee3c913af12d3474126b6131f5c054b55d7
3
+ size 1595772900
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=420/flop_2.51e+16_step_215.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42caaa6f0fa20f6871c91ecee39c81b72773a0818701600ab5e734c004acdf20
3
- size 225884397
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4bd18bd2349dc694934cacc9d3d84154881f4599b755abfaef9544c6dc0884d
3
+ size 225882413
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=420/flop_5.00e+16_step_428.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a5f74a5a5b2914690c31ca3301a592e76f66222fa3b541b4181e6b76e3ce44
3
+ size 225884269
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=6860/flop_4.00e+17_step_3432.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee00380748170dbc9e66f99738d6ef934fa90e10145d412b8786550455aa1f88
3
- size 225884533
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d3083141a415e9da0edac96261ab401f885bcdeb9635082ecdddf5a2cad5122
3
+ size 225882549
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=6860/flop_8.00e+17_step_6861.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0feb0fb08a2756cecbd59e5a91d485398159136d9b2ee7651efb8b96c467be3d
3
+ size 225884405
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=2220/flop_1.60e+18_step_1118.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb78cb844bf8284e270c083eb63e4ff8e048d2d221fd802dbde93e407c9e5f68
3
- size 2048266581
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2a0eb8fc4cf149262c6f5e80904b0d448c8da9fcf16c5934171e37d5a9f670
3
+ size 2048261653
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=2220/flop_3.20e+18_step_2234.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea312af962360c0ee3fdb9ddfcc99a92ca8813091e51a6599146770bb716411
3
+ size 2048266325
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=120/flop_1.26e+16_step_70.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadb367f9244eb3dd736d39ef62e87d8b4f473e7b3faabd764ead31055e611bb
3
- size 326619997
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97711e113996b707e3c06d8f60c0b243efbbf7d800bf644abed6d3d848409d89
3
+ size 326617629
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=120/flop_2.50e+16_step_138.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9fb5c0549b53e4e2e562c78264ff315b845d70e05fafe18c613716d0b409f0
3
+ size 326620287
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=8860/flop_1.60e+18_step_8863.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa102211c7cddfe7f3ac73be005b620cb7e1f0fcabba041cc87710f04307b5ee
3
+ size 326620897
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=8860/flop_8.00e+17_step_4432.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf0939b575fce9a4ed8d7c233ac45c4b7ac546606a6c960057b8b5b0bd6fa56c
3
- size 326621089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8ce5bbfc8cb489e8e0a63d058add1ac1d5061e11b515c3ecb7e250290cddda
3
+ size 326618721
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=5M_maxstep=40/flop_3.12e+15_step_47.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4581b634e929d7c4f3d13c3afe3df01d3ba53736c80bc0c9f1a7fba645674f31
3
+ size 40084762
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=520/flop_1.25e+16_step_529.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b558c8f801a2d698cb615c82ae4f8269f004c1756f86b49abb2346ff0a214c7
3
+ size 55875235
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=520/flop_6.26e+15_step_265.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2fc36b3417a20acd96a64693ab22e708c307720cfa13eb4721c2dd859dca199
3
- size 55875363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c368a1c7d3e2f6a7968ff78d7988dac8a2145d5bc69f5e558429a88061388a31
3
+ size 55874467
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=11980/flop_1.60e+18_step_5999.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec245d7be344bb5ecf6133d9c7545d65dd0b64cadc38dfdadf2c8f40a358da86
3
- size 455680909
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad18c399523f8a9d04b5fa14be76dad861da7a9d9ca75734b9b266696fba3a1
3
+ size 455678157
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=1600/flop_2.50e+16_step_811.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7a072182e88fb0be5c35b3dbc6b15242c908ec8125bdae1512d7353043fffac
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43ae60ae3af24e2bf28c0734f5743f0241a5872e4280598141465f5180d240db
3
+ size 71568191
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=1600/flop_5.00e+16_step_1620.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a704489c5d3e2148b047d8c614c5713e65d7abb17989da5b2a55eea6209bc55
3
+ size 71569222