Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
50cc997
•
1 Parent(s): af6e2cf

Add files using large-upload tool

Browse files
Files changed (24) hide show
  1. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_1.00e+17_step_214.pt +2 -2
  2. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_1.28e+19_step_27301.pt +2 -2
  3. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_1.60e+18_step_3413.pt +2 -2
  4. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_2.00e+17_step_427.pt +2 -2
  5. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_2.56e+19_step_54602.pt +2 -2
  6. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_3.20e+18_step_6826.pt +2 -2
  7. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_4.00e+17_step_854.pt +2 -2
  8. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_6.40e+18_step_13651.pt +2 -2
  9. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_8.00e+17_step_1707.pt +2 -2
  10. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_1.00e+17_step_70.pt +2 -2
  11. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_1.28e+19_step_8937.pt +2 -2
  12. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_1.60e+18_step_1118.pt +2 -2
  13. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_2.01e+17_step_140.pt +2 -2
  14. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_2.56e+19_step_17874.pt +2 -2
  15. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_3.20e+18_step_2235.pt +2 -2
  16. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_4.01e+17_step_280.pt +2 -2
  17. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_6.40e+18_step_4469.pt +2 -2
  18. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_8.01e+17_step_559.pt +2 -2
  19. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_1.00e+17_step_6145.pt +2 -2
  20. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_1.25e+16_step_769.pt +2 -2
  21. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_2.50e+16_step_1537.pt +2 -2
  22. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_3.14e+15_step_193.pt +2 -2
  23. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_5.00e+16_step_3073.pt +2 -2
  24. dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_6.27e+15_step_385.pt +2 -2
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_1.00e+17_step_214.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69eefe03831c6c78ca7c10e3545d93190b2b7b94505e89260c00b65f69192d93
3
- size 738704501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3aeee7e00f5e3f378fbc28a6043a57cd43dc57a7c1e060f9f5eb14a23b6d7c4
3
+ size 738701045
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_1.28e+19_step_27301.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d844d9b25fb444fe56a211049ca3ee9cc58b0bc99ca4a048a488499e05f31eb2
3
- size 738704981
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53023a6fcbb9a53e61a2c2105811518590b0afa6433980acd0f2edc92cde02ae
3
+ size 738701525
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_1.60e+18_step_3413.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2152375f3a9475852b858fd463bb3f6361681ef728adb662cbb60d7f786d67eb
3
- size 738704741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6495cf37aa5f7c825809463c6f967f4838d406f54779baa702cc371bf28e8a4b
3
+ size 738701285
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_2.00e+17_step_427.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ea3366da9667d8c89904430446bfff927a0c769e8395ca0b9f47d34b2c25a69
3
- size 738704501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2550d896149f08fed0040c61ef07b64db9eb3fe0df9cc4c9fe5bc0014c0e73f
3
+ size 738701045
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_2.56e+19_step_54602.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:027b7d9034c1e781cb26013131eea20c3cdb9ee451009d5cedaa6aebc4c3578e
3
- size 738704981
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75864f90ae348e6c9a88d3bfd971ac91c4d6d30a6cf0ad44961db5599168b53
3
+ size 738701525
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_3.20e+18_step_6826.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45424e2144654b34f422167ce1b6dc3f89064bffdd7d73e0fe8c8d481b2d15cf
3
- size 738704741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6a87cab2bdb8ed9036950035eb9d24fecafd66568fca10f8e2b8cf6b7dea360
3
+ size 738701285
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_4.00e+17_step_854.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2cecd59274a35bce8af617094f1758a472ee8cebc15b1a4086bc1e81e29191d
3
- size 738704501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f318f0a90b1b094087b3ba6cff1f02734ff584370724787d3433e908d8c26f7
3
+ size 738701045
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_6.40e+18_step_13651.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c78f671cfe9e4853d9ad9033696043760cfb7aaa54dd3ca2449c4dc62ac09f7
3
- size 738704981
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d834e952d9a4a3210ec3dffb00f06037163fd15d3c73b4d8ba30bd6aaac7bc0
3
+ size 738701525
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=149M_maxstep=55533/flop_8.00e+17_step_1707.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53b62c6dc86f300990100d3cb67adfed09238342c911d8f1f9044175a4c9a244
3
- size 738704741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e540673384e75150938adb4c21c179e411cfca30f80653f1ecfe0f4615cb485
3
+ size 738701285
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_1.00e+17_step_70.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c58c57e11824a8c332c49205a36bfc56df553c6e5cf981eedfef3d2f87e9b932
3
- size 2048264165
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9591118d83d59eb04b6cf8be0a2b2a4e129aad7e3a441c5ce97da38565957dc
3
+ size 2048259237
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_1.28e+19_step_8937.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72fbeb4d0175aa7b1fdbc849e693d69e4837178721e81ce92a11e0758799f40c
3
- size 2048266581
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df44b4cf0419ae96e1da95e15d54099774099e47d8ac30ea9a60821a23ef0a3a
3
+ size 2048261653
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_1.60e+18_step_1118.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4f5a7759ea65f11c0daf6a17ab730c74eef2aa443d0c39602bdf888c9f15625
3
- size 2048266581
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c8a65d3fc82f007cc593aa4b535cfd0cc731674e42c5b44988f7eddf3d64af
3
+ size 2048261653
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_2.01e+17_step_140.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd55c2eb5bd905e58ae31bae42bdce09e16b997ff02f9a3bf0d93a62e31b36b7
3
- size 2048265725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8588e21d2ce64d60d496b2a8d255bdffa80eda935d197087df539f942cd08575
3
+ size 2048260797
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_2.56e+19_step_17874.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95c84787a40de332a0b574b2f1ba18b3e1cb7e0f0c68090bf16b184a0b119408
3
- size 2048266925
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ea2dbdef9028ea10af845d11c3a6f3feb32e5f0cc7c39240a20a4630ae11b10
3
+ size 2048261997
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_3.20e+18_step_2235.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7070d6f76cc62425864a3438088dccea70170e7471a8297629fe3a4f44ad034
3
- size 2048266581
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:697b72a5d758185e0015bf625abc3e5b5b11f64296ad086a15a5c665a6acf137
3
+ size 2048261653
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_4.01e+17_step_280.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0ae26c6652054232692d99d34d225fd6ebd01dda12b956ebbc9fc188baecbee
3
- size 2048265725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7840a547cb95d39627aa3686a128ce2b9f13bedda4bb5c172c33cb931f5c1e17
3
+ size 2048260797
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_6.40e+18_step_4469.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04bb923325319e2470b3fa6afa219de3aff100b925a4f718b385fbc3055df15c
3
- size 2048266581
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a00f1358667834ed5fee01ebea74e38754e534114bb6a63817443deb923eb772
3
+ size 2048261653
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=455M_maxstep=19100/flop_8.01e+17_step_559.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:074b822a598ab7b31b7ebda0f5171e3cb8ae64455e1669f845038044de2e056a
3
- size 2048265725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b4bd11742caaea9a1be449e2e1fe9e178682b725f39acaa1c1f64c39adeafa
3
+ size 2048260797
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_1.00e+17_step_6145.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54da1f67568f66039558ca5a90768d19100fdce9eefeec3d12751e66afd11659
3
- size 40085172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484a401ae11ebd943c08b3f5ece82bd3b2aeaa4af67d070936768b9e9b6fad78
3
+ size 40084468
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_1.25e+16_step_769.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5682c761d528e71b12207a6de6262b50d869ca3f8f39a205665a305cf2ca6b97
3
- size 40084999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ddcd7510d03d5a4c3bad88efe7870d4faef00a728a55386c7a606b8b697a31
3
+ size 40084295
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_2.50e+16_step_1537.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9230e288d5d3efac0cb8503d8587da93c819989878509e516302ea203edfb606
3
- size 40085172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da68f03b01fc42f5fd338ca3bc90823cc59dc4b23623daf1de914e0ed408b4ab
3
+ size 40084468
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_3.14e+15_step_193.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc793f964db9bd16d9e41ce876bb599bb60b5fb7f84cadb33d3a78d4f3f1c4d5
3
- size 40084999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3fe2a7db5ec4319fb373dc92f0a99cbc27dc98b9d60961763a44083b80c009
3
+ size 40084295
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_5.00e+16_step_3073.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ecfee9796ea7d26ea5648661cd77c860f11bf7f32867b915561496d19157e11
3
- size 40085172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f79890ac3917b8178f421c7e8184f4895bbd63afe048ee5e70f5a060d774485
3
+ size 40084468
dataset=owt2/hparams=base_warmup=long_decay=kaplan/params=5M_maxstep=11970/flop_6.27e+15_step_385.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebffbede492a881f734d47ed8e5318833dfa2438798016b01cff254c29914e09
3
- size 40084999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e499d3abdc358bee01c6438546104798a1c19e4741881ecc2f4cca3a9b85e3e
3
+ size 40084295