Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
7150337
•
1 Parent(s): 25a67e3

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_1.00e+17_step_294.pt +2 -2
  2. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_1.28e+19_step_37516.pt +2 -2
  3. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_1.60e+18_step_4690.pt +2 -2
  4. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_2.00e+17_step_587.pt +2 -2
  5. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_3.20e+18_step_9379.pt +2 -2
  6. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_4.00e+17_step_1173.pt +2 -2
  7. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_5.02e+16_step_147.pt +2 -2
  8. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_6.40e+18_step_18758.pt +2 -2
  9. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_8.00e+17_step_2345.pt +2 -2
  10. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_1.00e+17_step_144.pt +2 -2
  11. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_1.28e+19_step_18423.pt +2 -2
  12. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_1.60e+18_step_2303.pt +2 -2
  13. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_2.00e+17_step_288.pt +2 -2
  14. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_2.56e+19_step_36845.pt +2 -2
  15. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_3.20e+18_step_4606.pt +2 -2
  16. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_4.00e+17_step_576.pt +2 -2
  17. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_6.40e+18_step_9212.pt +2 -2
  18. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_8.00e+17_step_1152.pt +2 -2
  19. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=57M_maxstep=53060/flop_1.60e+18_step_8864.pt +2 -2
  20. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=57M_maxstep=53060/flop_2.00e+17_step_1108.pt +2 -2
  21. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=57M_maxstep=53060/flop_4.00e+17_step_2216.pt +2 -2
  22. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=57M_maxstep=53060/flop_5.00e+16_step_277.pt +2 -2
  23. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_2.00e+17_step_8473.pt +2 -2
  24. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_5.00e+16_step_2119.pt +2 -2
  25. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_6.26e+15_step_265.pt +2 -2
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_1.00e+17_step_294.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2f75976bd8f87052e78124683d2fa49ac60dceed6379ef15dc06cf63eb67d12
3
- size 563346682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e25148ef7aa2f759198f1341f931cbff636775589421855b096609343eae4b6
3
+ size 563343738
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_1.28e+19_step_37516.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50c397a491563239616788a724d571e9c0baed9d7fcc1de0d04c7212119d6986
3
- size 563347084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a322e6a02943f7ab7e8a2e1ffc7aaf5897542e24b30871d5084b37724da8a97
3
+ size 563344140
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_1.60e+18_step_4690.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65c2d1f5e07cddb3bcbaa0370b8ff78a3fa8cd09ef5939dcfe78f61c755a19cc
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d48928684a45cc1b6611655461b7302508070127104655c5ed957df1e5e3c2
3
+ size 563343939
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_2.00e+17_step_587.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12c561462d61c3050642f0552b38f2dfa976382b1d55c11dad6a5b05571a333c
3
- size 563346682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a55d1f534e476e5d5193fa1dd79cef896e8acd34da71283212bd95597549ef8
3
+ size 563343738
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_3.20e+18_step_9379.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d39c86ab1ed8a8c59669f16dac1443dc00a811418c86035a07fb6112c8a94234
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d61c3e676af804998132c19b19005e698e202213c4d53973b903431a3064ed1a
3
+ size 563343939
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_4.00e+17_step_1173.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66397bf6ad0db371f8b565db28a4150e92f0e94e022216a509276a666d6472d5
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16681faa5fe9c4ad09719be9b38be60d0152180d62f301f90b7f725c8ad3284e
3
+ size 563343939
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_5.02e+16_step_147.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75546f7817624cef7e47617700dac2359a14036079915c50eac60c12bfc9830e
3
- size 563346618
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:905bca72c5c3557ce5f8f6ae35753508b52c38c8c0230d7b021b98fb0358e098
3
+ size 563343738
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_6.40e+18_step_18758.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51a0c8f0e4f7e4936e0b288c3e1009531b7835b10828320e4da675c8e5a0a583
3
- size 563347084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35bbefb9eb14f751bb7b813afd27bbf13315feb8a7b9de08f434a129b1c2b572
3
+ size 563344140
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=108M_maxstep=41414/flop_8.00e+17_step_2345.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a435c482fd47866bec0eeefb24c033d3ad0211208aed540a9693bde83c7d7ad
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61cee6db006b5f7793ce4a192813c5eefe69d7dfa9c4de609caf9898bd5a8d90
3
+ size 563343939
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_1.00e+17_step_144.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ac89b7486596dc1453178014c362b6d3480fa389828da118af20b0a0d5e7baa
3
- size 1052007280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6e0ac192e08c09e29bcf6ef4ffcb21d1b716048ee3eb6fe19d014ac0566d1bf
3
+ size 1052003312
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_1.28e+19_step_18423.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad5a0ec9a15b0634a74fe7954b5f8af67a34aefe81f24f26b2fc6013fc38a804
3
- size 1052007838
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca1c2db86a77aaf8217a3ca560672edc12e5543dd02576faca3540b67102736
3
+ size 1052003870
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_1.60e+18_step_2303.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23748086b88ca94d9019493040f55fe467fda8cdd0a051fb6643f41a4f77f3ee
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f4120f6483c3309128dfeaa974cd27e3450c72abcf08bdde8bc131c139aeb8
3
+ size 1052003591
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_2.00e+17_step_288.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:422a83aa49ee8a2ba8e12d1a2049c635d90c324a2ac731aa54b2eeb305d79da4
3
- size 1052007280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7159e6f891a59daa06271512e22decf3871d6fe0bbe46ed1fed66d016da1445
3
+ size 1052003312
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_2.56e+19_step_36845.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28b1912fd5ceb2c50086e3606c58ce4df280fdfe8a880c9130ee480c17053bb8
3
- size 1052007838
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ba389dba895197251a4a6b155befb2eebdb98fb8436d7e6f2707dcb7820fe3
3
+ size 1052003870
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_3.20e+18_step_4606.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:859dab4224c7f573872d07a0cc4c0613a3150c0c2bc7f3e7f3d1ccec49b6440b
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:878063659e082acfa953d5c5b88b07f87d590479cfd0b05ec4f1a6f230c618cb
3
+ size 1052003591
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_4.00e+17_step_576.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02f2ecf9161d983665b4c0f859600937999b8c6589baedb2c8cef0ddf514f38e
3
- size 1052007280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208f6eefaa0c34c5126e357468adefb2392eba87953f72826f049c2784a68b8d
3
+ size 1052003312
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_6.40e+18_step_9212.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:450afb6d2edeba909f614408676269f860bd90a4f865be8d902c6876aea34771
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08f82d0739a0084449731af28ced5b020ba41c40ec906edf92d1b460a07a074
3
+ size 1052003591
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=220M_maxstep=37771/flop_8.00e+17_step_1152.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7645691bbe501e356d79dd6195a1a73942ede4ed5845e0c32c3b43670ac89b73
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140e42fa14ed93eeabd3f3e96697805df3bf31886f0a180d229cd0479abe0ce5
3
+ size 1052003591
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=57M_maxstep=53060/flop_1.60e+18_step_8864.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bc40042e8e56443be08c56a96fec7a46aa93dbe64b764e0fb2b39280f6ca413
3
- size 326621089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee8395bef87706f1413c57172c7ee279c35303a352cdcd4068a5a5f8c0464ec2
3
+ size 326618721
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=57M_maxstep=53060/flop_2.00e+17_step_1108.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b49c738148b0b3f13270246993f6415b7643c69d2c2393911028790d13cbe331
3
- size 326621089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05cf17a56399972331c51e46c778a151645635680e84b74b10fda05a73dddf75
3
+ size 326618721
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=57M_maxstep=53060/flop_4.00e+17_step_2216.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccd05ff72b2a0d36cc496d33519e973acebaea59879fe504cac2ac0ec50cdf4a
3
- size 326621089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c8dcdee62a4e93d22b6efa02886ad0f80b3cf340b1c42bd8dca8bc72bc26c13
3
+ size 326618721
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=57M_maxstep=53060/flop_5.00e+16_step_277.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e4ea09d5c2522f4e8ef375d413e311c45b152e901fd5ec8677c3cb22d8fd450
3
- size 326620479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01cb2f6be95a81d36879a595f2c1464add2c2e03a2fc0a1c7704a3c48f94c812
3
+ size 326618111
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_2.00e+17_step_8473.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:541a8ed51d8b0f6cdb7e5d153995637d6ca12c499487b5ce66bba70f9d86fd48
3
- size 55875421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d88803d752cc8c466aea3b5a7f076eeee3d56a3ee51406745b4968d5eef40b5
3
+ size 55874525
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_5.00e+16_step_2119.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93536d757c99d86c0ba97a18a71457e59ba9e2a8ab153576fd97f1fee346f529
3
- size 55875421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0790194e564301c9d6aa06e6f9673088f4775b739a5ccf3701263072168be761
3
+ size 55874525
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=7M_maxstep=12341/flop_6.26e+15_step_265.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb2efa449f951c6deff77ec6a7ab157ea4f9b14a6c06bac372efe199132b621d
3
- size 55875363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acc55ee9a8cd8ad424d4502e3569c0b5d7a8b4595e92e9b43d356b0472bdec3d
3
+ size 55874467