Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
94faa5d
·
verified ·
1 Parent(s): 8331046

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_1.00e+17_step_469.pt +2 -2
  2. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_2.00e+17_step_938.pt +2 -2
  3. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_5.01e+16_step_235.pt +2 -2
  4. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_6.40e+18_step_30013.pt +2 -2
  5. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_8.00e+17_step_3752.pt +2 -2
  6. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_1.00e+17_step_4435.pt +2 -2
  7. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_1.25e+16_step_555.pt +2 -2
  8. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_2.00e+17_step_8870.pt +2 -2
  9. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_2.50e+16_step_1109.pt +2 -2
  10. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_3.13e+15_step_139.pt +2 -2
  11. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_4.00e+17_step_17740.pt +2 -2
  12. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_5.00e+16_step_2218.pt +2 -2
  13. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_6.27e+15_step_278.pt +2 -2
  14. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_8.00e+17_step_35479.pt +2 -2
  15. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_1.01e+17_step_74.pt +2 -2
  16. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_1.28e+19_step_9379.pt +2 -2
  17. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_1.60e+18_step_1173.pt +2 -2
  18. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_2.01e+17_step_147.pt +2 -2
  19. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_2.56e+19_step_18758.pt +2 -2
  20. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_3.20e+18_step_2345.pt +2 -2
  21. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_4.01e+17_step_294.pt +2 -2
  22. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_6.40e+18_step_4690.pt +2 -2
  23. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_8.01e+17_step_587.pt +2 -2
  24. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=901M_maxstep=3660/flop_1.60e+18_step_226.pt +2 -2
  25. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=901M_maxstep=3660/flop_3.21e+18_step_452.pt +2 -2
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_1.00e+17_step_469.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86f64a9131b37eb2554960a1436d485220dfd8d16e20898abd52fd1cd4799c98
3
- size 563346682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d30b6d89ed4e8bc220fa806ebb00b09be032156a39f4485a645c726e264f2474
3
+ size 563343738
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_2.00e+17_step_938.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9b06dc28867a10c0d291110a4670fbe2adf26e57f3699308f206d899744d9c7
3
- size 563346682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69cca98aa699c91d56c05e3daa1c839d60a308a36fd2d12d6102e4b2d64638fb
3
+ size 563343738
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_5.01e+16_step_235.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:612b79af7ff5d77e89c66514f62eaac56fc3f4d528c1479762438f7419ceb8cc
3
- size 563346682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5629716fb4bccf8411c24144dde4b933d0bbd823ede61c626316c42b6d3e99cf
3
+ size 563343738
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_6.40e+18_step_30013.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f1b6ccd79bbaa5324c8632e89923e6788b2638b994517fed3189fc89654e476
3
- size 563347084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54eebc665f759bbfceab640357f2ded82ca4a77b4b3a8e96421113a0b21efd90
3
+ size 563344140
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=108M_maxstep=66180/flop_8.00e+17_step_3752.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:406d635735ae573b4739a12f817c9e9a7964a003df74f8e9e640bd9f5eac97a3
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1036ee72d5de6d16e60e8eb47d9ba77fab288b9d7c4dc080fb777fc009ea2e1d
3
+ size 563343939
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_1.00e+17_step_4435.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c980629501262aaa51c3f72cebf2de21df98b7043a22d4c04b9614bd9fbca5e6
3
- size 179382655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527c2b82103a73b69631487b6fc83552165a3fe3fbc5f652889db56cb1f8acaa
3
+ size 179380799
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_1.25e+16_step_555.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:266854882e127e9457f999a704a57696bdc434a38d59753a51211b704e5efcaf
3
- size 179382532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6492498b3c51e53b8dcc69bf75708afd22d0ef293df84b2892757d08532ac5
3
+ size 179380676
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_2.00e+17_step_8870.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14d4ea9f9fe3237ca31748659a6a40db84fd985ddb0bf782e9c27559ed5332fd
3
- size 179382655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7400d5e5c80ab94222b7e2a58903db77de8dcbd8825d196900ae91f851e15da8
3
+ size 179380799
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_2.50e+16_step_1109.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dfc155dcc4058dcbfc65196cdc139906f5c6c8e48124a067048286c009bd330
3
- size 179382655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9fddd3d055a48c123d04f2c8d2c9e0b7a059dababf373e846a5c32c95425d2
3
+ size 179380799
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_3.13e+15_step_139.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2f3f3831d8a4a64f88e31efb5aca9f6bb140d3707b9c83eaf5d6373a1f76471
3
- size 179382532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d97598d42a1ea8e360ba93dc198e8dbd6b2cdc42d1f18e00da64adb175c4fbd
3
+ size 179380676
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_4.00e+17_step_17740.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07b2e537a4e88042fb14031e51cd22673ac41b6c3f25b045d55af4ee577c2164
3
- size 179382778
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b11e6276470961f183f4c168e81d9b022e2af31861fb3722fbf3d84e6af07b
3
+ size 179380922
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_5.00e+16_step_2218.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76b2dff7240e7a85762b61b59312dbfa4d9950e32c8543c43d0bb8c9cf77a769
3
- size 179382655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a302d6d9652a820466484f9149f2b576e666ff34c9b52619b5528117791594a
3
+ size 179380799
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_6.27e+15_step_278.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9a84e404cc3e5f784391c240ebefdefb5eb0d86bbd5f4a56c2488384f02eeaa
3
- size 179382532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b98b9cbb588e9e462ea92dfd5533d462588ae3e1ec6644ff6c41a0e34ec2174a
3
+ size 179380676
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=28M_maxstep=43740/flop_8.00e+17_step_35479.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79695de4a9652781ba73220be09b4bb05acbe19c3a7bc9c2ac0ff7e1b3c764fc
3
- size 179382778
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8621c68bce3fd682409ba8d5cde3de3c30ef0c2b62ebda71539ad5765f2abee3
3
+ size 179380922
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_1.01e+17_step_74.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccf3b37bbe38a315dc1673634c1c6481bbd70bccb8436e370c80a98c18247e30
3
- size 1595772241
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f83c9c1423b348da6f75ceebdbf616c6f7de9f998afa15b0db2aad9ebd0adef
3
+ size 1595767825
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_1.28e+19_step_9379.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:668be163a8ba0ad34dd6b93cfe5097b5eaddd77544e384a857b8d78524caa4ed
3
- size 1595772915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52106d622313f0ef9a603b061c6a77cc6ce87f0ad723cabe3ba6c26832bec4b6
3
+ size 1595768499
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_1.60e+18_step_1173.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1916ab8925d0892b75b920980aba48c01ef3ac98945372dd851e4b2ee978a178
3
- size 1595772915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb40a9aef489bfeb847f755dad753c3e5c67e507ba399d565989421df0c460c
3
+ size 1595768499
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_2.01e+17_step_147.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e99e5f71c215e9228051e704ee7195fe47e618c31a44de79bc5fa2d3a268f54d
3
- size 1595772610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3438c135559736941e823f41442b20e679fb2a77f9b5e5a8560c1af243a6a2e
3
+ size 1595768194
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_2.56e+19_step_18758.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d92efabdfe6f2de1cd67aa722bfcd0108b79e49d92386b9c8f392109f447be1
3
- size 1595773220
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ccf0cc357d2323326c1044cbcd8431930ff2d7dc793d65b90c5ae44f3f6c0a
3
+ size 1595768804
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_3.20e+18_step_2345.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4199b2d4b6f8ab937b1111333105f24cb8a73d8cf88514f8341d60591175d459
3
- size 1595772915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9d8dd526fc4ab232b8073320cd7245f53132412f56df3e108c46a47cd437e6
3
+ size 1595768499
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_4.01e+17_step_294.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:926fefb2c20c6818a74cfaa1a54e72e821995b1fd5a25cb5942652fe86da8917
3
- size 1595772610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e53d3b7950ce7e58a4a4225e30354068ff771e105452a24b0010f77e2765bd9
3
+ size 1595768194
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_6.40e+18_step_4690.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:986008150a39324bfe673a8ee0c0a35721f06fbeb1185d746fbfa208bab72c21
3
- size 1595772915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552c1425fefe24defbdc78f2f8c12e4cace7d91a368b0061ebc85fbc62378553
3
+ size 1595768499
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=347M_maxstep=19040/flop_8.01e+17_step_587.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b907a67e6379dced4946b925fc8d3ce8a382060cfc67e5e18a1990c9657f0bab
3
- size 1595772610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889a128cad6bd6282c4e4e44641d4b672e6badd1f448a3764ab0f93a2283a342
3
+ size 1595768194
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=901M_maxstep=3660/flop_1.60e+18_step_226.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:092c8fb5f1d6f01fffdf2c9352a1fda561546803f9fe0033c2ff25a59d600582
3
- size 3911931681
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c429223b899489476b4fa37e15e4d3f9d9c851fca5cd7b14edfea082f56fca9
3
+ size 3911925921
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=901M_maxstep=3660/flop_3.21e+18_step_452.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7db84d9e5534404a8dc74ce73c1669c8ef285cf196ea846c19e4200bfebb589
3
- size 3911931681
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c2d2f5cbeb169739b5ace3098383d0b610610339ee16abe43721e1049827c5e
3
+ size 3911925921