Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
6a981e4
•
1 Parent(s): 7150337

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_1.00e+17_step_2039.pt +2 -2
  2. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_1.25e+16_step_255.pt +2 -2
  3. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_2.00e+17_step_4077.pt +2 -2
  4. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_2.50e+16_step_510.pt +2 -2
  5. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_3.14e+15_step_64.pt +2 -2
  6. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_4.00e+17_step_8153.pt +2 -2
  7. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_5.00e+16_step_1020.pt +2 -2
  8. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_6.28e+15_step_128.pt +2 -2
  9. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_1.00e+17_step_4237.pt +2 -2
  10. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_1.25e+16_step_530.pt +2 -2
  11. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_2.50e+16_step_1060.pt +2 -2
  12. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_3.14e+15_step_133.pt +2 -2
  13. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_1.00e+17_step_3241.pt +2 -2
  14. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_1.25e+16_step_406.pt +2 -2
  15. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_2.00e+17_step_6482.pt +2 -2
  16. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_2.50e+16_step_811.pt +2 -2
  17. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_3.15e+15_step_102.pt +2 -2
  18. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_5.00e+16_step_1621.pt +2 -2
  19. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_6.26e+15_step_203.pt +2 -2
  20. dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=9200/flop_3.20e+18_step_4606.pt +2 -2
  21. dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=80/flop_3.18e+15_step_45.pt +2 -2
  22. dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=80/flop_6.25e+15_step_88.pt +3 -0
  23. dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=120/flop_3.12e+15_step_132.pt +3 -0
  24. dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=360/flop_1.00e+17_step_374.pt +3 -0
  25. dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=360/flop_5.01e+16_step_188.pt +2 -2
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_1.00e+17_step_2039.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5802b53aa78ffe13ab5dac92d1886525146c91a85a3d5d09dc1d9a55f507305b
3
- size 107653679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252ec6b0eb7960ffaaf515023b7b4950db009e1d7c6284b4cdfe2de56a3a8792
3
+ size 107652399
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_1.25e+16_step_255.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b94445c67f4a270f79d3bc37bc106e86e744982ef595f3b051e11a1564d3dea6
3
- size 107653275
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cc2072f698d8be5becf242b8fd22d45e60ae4c7482d054ee94350355ccd068d
3
+ size 107651995
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_2.00e+17_step_4077.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:960cf153b1a06dd36b1e8d696f45dbea2faaff2fb48762543dfee3e8b2f33105
3
- size 107653679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7af28751c7cc5cbffb765e0eade9dbcb9438ffa353eb5a307c8584878fc19f
3
+ size 107652399
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_2.50e+16_step_510.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16a13bb6899277a3030542ec6e579afeab7c0880ab9d91d1859cced70cbaec98
3
- size 107653275
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:174913683e24c89151abb282d427f5990920bd0b2c335923bace5ec1dcd9e24f
3
+ size 107651995
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_3.14e+15_step_64.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:595d7c0c4cec90115ebc84abcfca592c628b2df29c5edfa54f3d92f3db4da357
3
- size 107653127
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77ad28a7c5f49839bed4e5dcf554a73d07b69379a70670f9b8cff8d3922e534
3
+ size 107651847
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_4.00e+17_step_8153.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98ff89257fd2a89bc52288b688da1cf976ef96126e14f9a6c75c222bfaa51ed2
3
- size 107653679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6894d423038ff16c35395bd407803301583a455f92a9c21a7a3126c9d24c2c22
3
+ size 107652399
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_5.00e+16_step_1020.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e63b10717830e366db0d7bbc909addae76ebb5ba828022c6ceab9b2fed7fbfc
3
- size 107653679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dafddeda27a265c05ab4837c5b73306630cf17b531aa10aaee88fe2b8df32368
3
+ size 107652399
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=15M_maxstep=12080/flop_6.28e+15_step_128.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa6d16730fcc020eef316020701647f241d3562da1e23bfa562f722fd9f72ef1
3
- size 107653275
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763bb228ea12171cc0e16cc97c9b0d08e366d91207f61d4e2468a9a66d130455
3
+ size 107651995
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_1.00e+17_step_4237.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fc13a65f349ff012b3ced6ffbb2d51b5992441b4a55440796bf8f7553dab016
3
- size 55875421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54da06e57df771d9eaa6a7a9379360e811cc84b0cb7b58b19102d0c8c7c69270
3
+ size 55874525
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_1.25e+16_step_530.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:693b6f19b5c187a7bccefee79d895162a4529bbadaaad43f9b2e7de11f095060
3
- size 55875363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d41a81431837755323c9d81f886ae4579c87ffd071f54022dc757d480fb0c4
3
+ size 55874467
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_2.50e+16_step_1060.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:796ec0446d47a7a35aa4165b21c9bba629b5aa1720380abce837df20bfd839e0
3
- size 55875421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e38d656294095db5fdd555535037cdd039530890a7af4a0a38741eef37691b
3
+ size 55874525
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_3.14e+15_step_133.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8028488ff3993fe8b66407f2c3828d47934f0cd69e3f35c58a6e1758ff47403
3
- size 55875363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfbe5bc1da275f71d1ab546d38d43cde54628d7d6980df1e3a0143675c6ea820
3
+ size 55874467
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_1.00e+17_step_3241.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faf2b20ee866bdd3ab027481c83408568348b659c159c7d97fe7f75476ca1fde
3
- size 71569350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f841262dc67655603b33cef73d7f2976a18b6efbdf7b595c4dcdb1f69c8165f3
3
+ size 71568262
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_1.25e+16_step_406.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf3b7f435d93a80ec802466cff23bb9d55106a97a1609167c5383145417113d9
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ff02f47cb956e1088b33243c81ad4f57d2d459bac80fba444e75b35d52dde4
3
+ size 71568191
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_2.00e+17_step_6482.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed7f1e9ececcf4743dd8df8d64ab8d82430492531f7044ac2945798bc8eb286e
3
- size 71569350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0acd3fd29249260160951d357acd675e99942aeba6e9026fe220690b3730ed2b
3
+ size 71568262
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_2.50e+16_step_811.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:547b480107f4053161d7ba2777cdd379a80ed4097e3fd5cb98f8b41511665129
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4142103a75bec698deebe0d909efc7feee03e6db3b17a1607aa5a126f74d82cd
3
+ size 71568191
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_3.15e+15_step_102.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8108ae5afbb28de45bd50a60fde68ad1373358baffd8236e0a33fd430812438e
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ab873cd580a4c9dbb0632e1d76f0c4d3325ff659ba0fffc2c8d5118b19dec0
3
+ size 71568191
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_5.00e+16_step_1621.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f66ed9ac879b10f9a67e0d3fa0fa8f4d517bf02d079c76a8f2037e63c70eeae2
3
- size 71569350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9f0ce065a5f16840ae6619f0343e32d806cd49b6c6d8531434cf4c21dfbfec
3
+ size 71568262
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=9M_maxstep=12201/flop_6.26e+15_step_203.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98642939877a05208b36f2c356791eaeb83d1cbb4ca7cf0b04f4a206235d6b10
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6cde80e3fcadd32241892ef1e0c00becb27090927b0f9cd6520a12c0e661366
3
+ size 71568191
dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=9200/flop_3.20e+18_step_4606.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d2db7efd19262f73ec657918ba76767893751a07340c782bb4fff3598fe151d
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e3b9269417639508a78f1d93ca5f461ac0346316283f69c032e768a7a6f6a13
3
+ size 1052003591
dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=80/flop_3.18e+15_step_45.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d46553364052618b007f6eb9c712f8cc04df0a8770749ddc7ad0de4de0150957
3
- size 148163437
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:924ff0c8db65a5e70e5d3ce8c2e387e1bd07beb866dbe081a1cae9eacc4d2b8b
3
+ size 148161773
dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=80/flop_6.25e+15_step_88.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd5c1b9091b79a0cad56c41a54e241100869832ebac9d3dfd3f32a068d1b48c3
3
+ size 148163309
dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=120/flop_3.12e+15_step_132.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:357bc499ea1a40a06bc65d41e6f633373fe2dca912db5cc2511c10248e4eb483
3
+ size 55875235
dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=360/flop_1.00e+17_step_374.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b88047698758afbf789bf5fe1183a9bcd4f1159767ebe17039647e5568edbf
3
+ size 455680529
dataset=owt2/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=360/flop_5.01e+16_step_188.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7f44737a1d29588c87f425b051736f7b11e7762bf6ceaba7ed411312ca553e6
3
- size 455680721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f7c597268d0c1aead5e3650e5a2ba13f809aba3cc93f7675324640923ae153
3
+ size 455677969