Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
51d96df
•
1 Parent(s): 2d85ff2

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=180/flop_5.00e+16_step_187.pt +3 -0
  2. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=180/flop_5.02e+16_step_147.pt +2 -2
  3. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=420/flop_1.00e+17_step_214.pt +2 -2
  4. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=420/flop_2.00e+17_step_426.pt +3 -0
  5. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=1140/flop_4.00e+17_step_576.pt +2 -2
  6. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=1140/flop_8.00e+17_step_1151.pt +3 -0
  7. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=1400/flop_1.00e+17_step_1413.pt +3 -0
  8. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=1400/flop_5.00e+16_step_707.pt +2 -2
  9. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=3660/flop_3.20e+18_step_2931.pt +2 -2
  10. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=100/flop_1.25e+16_step_107.pt +3 -0
  11. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=100/flop_6.30e+15_step_54.pt +2 -2
  12. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=1100/flop_1.00e+17_step_554.pt +2 -2
  13. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=1100/flop_2.00e+17_step_1107.pt +3 -0
  14. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=2200/flop_2.00e+17_step_1108.pt +2 -2
  15. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=2200/flop_4.00e+17_step_2215.pt +3 -0
  16. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=540/flop_1.00e+17_step_553.pt +3 -0
  17. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=540/flop_5.00e+16_step_277.pt +2 -2
  18. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=5M_maxstep=80/flop_3.12e+15_step_95.pt +3 -0
  19. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=260/flop_3.14e+15_step_133.pt +2 -2
  20. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=260/flop_6.25e+15_step_264.pt +3 -0
  21. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=60/flop_3.12e+15_step_66.pt +3 -0
  22. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=901M_maxstep=4500/flop_1.28e+19_step_4512.pt +3 -0
  23. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=901M_maxstep=4500/flop_6.40e+18_step_2257.pt +2 -2
  24. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=800/flop_1.25e+16_step_406.pt +2 -2
  25. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=800/flop_2.50e+16_step_810.pt +3 -0
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=180/flop_5.00e+16_step_187.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33a546f843e020ec16238c096bfd1e1fbb78a74487f20e585c2e373013c8c0f
3
+ size 563346426
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=180/flop_5.02e+16_step_147.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ec8faaff6b622e77dec03279ab6c5dc9e1003c97e9c8841a5072e83a3135f11
3
- size 563346618
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e92d924d8d7e07c63e885f01458a2ae6f19be0f9ec12d04ac48a7fcc646f900
3
+ size 563343738
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=420/flop_1.00e+17_step_214.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfdb650a37ffed92f34cce3abf416d3e835cf34415b2a5a9891acba5ad779bee
3
- size 738704501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d96c29efbd8a6e9a2c936b1e590ded0bf11dee2a6bc390edc292dfb44757e2
3
+ size 738701045
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=420/flop_2.00e+17_step_426.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a982cd9024c58dd6a109f3d3f9e66568dfc017c0e8e7ca7f64933f46ce03a3
3
+ size 738704309
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=1140/flop_4.00e+17_step_576.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:953aebe4ddcb988ee3e982d5a600e1da441a6ae91b2c97ba0d809902a0b05f93
3
- size 1052007280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6850ce956176ced8d26ed77fec7e5fcb966f6edce059f6dd85bc7572bbb831d7
3
+ size 1052003312
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=1140/flop_8.00e+17_step_1151.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8334c0e1b59184d38bdb127ca77c0196cf0094fc6b46743bb0998cb650b9fc61
3
+ size 1052007303
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=1400/flop_1.00e+17_step_1413.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c12f73a7ad36c69d5f71c4af8d49a6dc6556d5cc8e3b63c5ab7624bfed95ce
3
+ size 148163593
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=1400/flop_5.00e+16_step_707.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c85e4fa3a77d899d60380456e58a49fa02be9d81b678b773d141bb5b981f48eb
3
- size 148163611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e5672324bd51e5ff7f1117e5881a8d3ce97687a40044a8b889dcac305a545d0
3
+ size 148161947
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=3660/flop_3.20e+18_step_2931.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b906f0c3ee9fc06a48c3eaae08009d37a4bf084a255f51f035fa53eee62a0c9c
3
- size 1595772851
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9819cbc24e38432e80eca8a520b55de32ab13bfbb2256dd2798842a154e62ce3
3
+ size 1595768499
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=100/flop_1.25e+16_step_107.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c403254ced071ef614d376bf23941640d00c212ba2830698cfaed72b2814256
3
+ size 225884269
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=100/flop_6.30e+15_step_54.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:876949e10983f0ba2556ef4ae424b7eb1bb9d4be596917e331402a068492b8e5
3
- size 225884197
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89b768a4a69d2c743ec6d1efce69dd4b9104e75c63d9c756315248f6308f1f3
3
+ size 225882213
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=1100/flop_1.00e+17_step_554.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a73f2f365743f60f4b29fb18b3fef5cea33197e270aeeee76cee1cd60ea889f
3
- size 326620479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da7976860afcb9e23a8f80410f16084a1082e48a802f14211943d6e0277e84c9
3
+ size 326618111
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=1100/flop_2.00e+17_step_1107.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:561892784301a6ab35a6a26f59bb21f3d4a510e1e7fd523d2d8d1d9ef21aa312
3
+ size 326620897
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=2200/flop_2.00e+17_step_1108.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b9b3996820988507729da0245835d9fd563bfa3ae5b727e711f17bea45b7d56
3
- size 326621089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d567ecfcc5dcb7ae662caf0f95d2f877f36fec090c2938ab40248cb73404fdaf
3
+ size 326618721
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=2200/flop_4.00e+17_step_2215.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ba1059a3763c209406c43d081e7475bfea8a8016d98e4108350ffc2b2149e4
3
+ size 326620897
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=540/flop_1.00e+17_step_553.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c21b2da937da99c8eb1234eee4cd200b7fc5543df57ec94bd8c72056d71ced6e
3
+ size 326620287
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=540/flop_5.00e+16_step_277.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc1592786e5c12227639dbebe13120a212b9d93a835f0754ccbb105634b31a0d
3
- size 326620479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10c7121d94d151a6741dac81ac18224507f453cc278b7f04e0bc1ce716cb074e
3
+ size 326618111
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=5M_maxstep=80/flop_3.12e+15_step_95.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aeaa1180bb63125b0d698e19cb02f5cd8ca9e0209b228d421a53754eb83339c
3
+ size 40084762
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=260/flop_3.14e+15_step_133.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c63c7ce073b45b5130c45ca6f6f48525b394aea447c7505f50026a3d73d9b91e
3
- size 55875363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe656df1637b9050806524d083e610885ec6335b127b8085666a3877957c6c4
3
+ size 55874467
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=260/flop_6.25e+15_step_264.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daadc9e41e884f63958edbacfa44ffb030bb651531d1a9535d3475bcb2bb586c
3
+ size 55875235
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=7M_maxstep=60/flop_3.12e+15_step_66.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe205535e9168effc363bcc1fb212cfa1de0416b0d504f9b6f3feab3e9735d86
3
+ size 55875113
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=901M_maxstep=4500/flop_1.28e+19_step_4512.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24e42ddc1d45c60d8271c61f54a84206f081c2e1a7d4621efaa036f328f43f3
3
+ size 3911932205
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=901M_maxstep=4500/flop_6.40e+18_step_2257.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a08f2a34a43b748c682ce1c0aa0a6a401a590110a4215de0afb4c6df9af2cc1
3
- size 3911932525
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f3371226b4a7fe0007e3a261dc3d030ffe6a4948bb4d5679cf12a6484db82d
3
+ size 3911926829
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=800/flop_1.25e+16_step_406.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32d667bc0afc5acdfcce5b14cea04d436ac86ff529b97645791242a95d7b04f2
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c4fd37ab41721d0dc1e80e07c200330bbf511e272cb899bde98f2bab2ecc4d
3
+ size 71568191
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=800/flop_2.50e+16_step_810.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df36ada5372e0517e6e0a429c6d2add22d9728dc5db0e9d6892f6e1035b08d0
3
+ size 71569151