Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
9cb1cca
•
1 Parent(s): 51d96df

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=1700/flop_4.00e+17_step_854.pt +2 -2
  2. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=1700/flop_8.00e+17_step_1706.pt +3 -0
  3. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=1016/flop_2.50e+16_step_510.pt +2 -2
  4. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=1016/flop_5.00e+16_step_1018.pt +3 -0
  5. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=20/flop_3.12e+15_step_31.pt +3 -0
  6. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=2020/flop_5.00e+16_step_1020.pt +2 -2
  7. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=500/flop_1.25e+16_step_255.pt +2 -2
  8. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=500/flop_2.50e+16_step_509.pt +3 -0
  9. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=60/flop_3.12e+15_step_63.pt +3 -0
  10. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=18420/flop_1.28e+19_step_18422.pt +3 -0
  11. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=18420/flop_6.40e+18_step_9212.pt +2 -2
  12. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=160/flop_1.25e+16_step_176.pt +3 -0
  13. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=160/flop_6.30e+15_step_89.pt +2 -2
  14. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=2820/flop_1.00e+17_step_1414.pt +2 -2
  15. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=2820/flop_2.00e+17_step_2827.pt +3 -0
  16. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=3660/flop_3.20e+18_step_3663.pt +3 -0
  17. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=3420/flop_2.00e+17_step_1716.pt +2 -2
  18. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=3420/flop_4.00e+17_step_3430.pt +3 -0
  19. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=840/flop_1.00e+17_step_857.pt +3 -0
  20. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=840/flop_5.00e+16_step_429.pt +2 -2
  21. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=17860/flop_1.28e+19_step_8937.pt +2 -2
  22. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=260/flop_2.51e+16_step_139.pt +2 -2
  23. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=260/flop_5.00e+16_step_276.pt +3 -0
  24. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=200/flop_3.15e+15_step_102.pt +2 -2
  25. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=200/flop_6.25e+15_step_202.pt +3 -0
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=1700/flop_4.00e+17_step_854.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce1886b8837b11308b9ce5d73a74687f3afd56899dda2564a19bbc5196786c70
3
- size 738704501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5a36df1bdb80bbd7ac8b30c20f970e71d086f745452c25a4b597edf5b3ca72
3
+ size 738701045
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=1700/flop_8.00e+17_step_1706.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f1a2d56916de0b51d5c6268f7b4f51840c396023fe7fde190b36faad6d025ab
3
+ size 738704549
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=1016/flop_2.50e+16_step_510.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ed0f229263e5b85b6133253a8c94b664310950a520f4f1d4c756565a486fc14
3
- size 107653275
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ed241167fcf02b24f76acf6263375eeeaa8f9996e0f990fcc50d73824a282c
3
+ size 107651995
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=1016/flop_5.00e+16_step_1018.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae6d8fe2c646dfea07e09ae7021afa7eef557a1f2155aacecc864ca32f1178a
3
+ size 107653551
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=20/flop_3.12e+15_step_31.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f14db10ee450127c27ebe1eabaa34593ca6a27aab9570239bc6a9fe93b92dc
3
+ size 107652999
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=2020/flop_5.00e+16_step_1020.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:227cf74f5f657179c4ec8d005d547dbaef50de846d226dfe5e6084adc90ab505
3
- size 107653679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec39d4ebf3733c6781a2bbcda59e31388b3f7acf1924a9a4515136258d32fd5f
3
+ size 107652399
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=500/flop_1.25e+16_step_255.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d70842c4675d8847beefd0197acbb686592fc4044adec80e772de7c776c543cd
3
- size 107653275
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdaaab3f5589fdd1437470f2788ce06ea28c7437c205523edd71084e132cc655
3
+ size 107651995
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=500/flop_2.50e+16_step_509.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd4c34ca8394da1d8530b51e01425f3323aa8f626e82bc3e6c9cc1aa0afcd35
3
+ size 107653147
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=60/flop_3.12e+15_step_63.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b06c853b2dd23157174aac7ac988739fbfe64c60746589f437c90c9cdabd1ba
3
+ size 107652999
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=18420/flop_1.28e+19_step_18422.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad3d23c72a7a53944947edf06f954e2435bbf06c55c04684fbec1f79c6d4c74
3
+ size 1052007582
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=18420/flop_6.40e+18_step_9212.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f355d1fd81ca86f9916b3145ad0f383f3068dc06a2a8b34e525ada9cee0440c6
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8bdfa4757aecc73e81b61579c9354ad56c1735b75313dcc83100ae8f9675e0
3
+ size 1052003591
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=160/flop_1.25e+16_step_176.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf421ca8ec1ca8fdae918770a2129e8508ec484c9c9096f5abed4c78ebd27ff7
3
+ size 148163483
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=160/flop_6.30e+15_step_89.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55d357e0335fd09ac23062d133bd5e27c1d9900f61222c820de889b1b0b8835c
3
- size 148163437
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbcb0c8bcd3d0071951fcf283afe9becd91942a294668579f6829671039cf62
3
+ size 148161773
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=2820/flop_1.00e+17_step_1414.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd1861b1947786d07e36b685b77e788f8715a7b27a3e8dfe708f5366f1d8fcc8
3
- size 148163721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa45e1fddc9de5de8df288a6d93a3781b6297c0460e578e7c12e1c26a41a76f
3
+ size 148162057
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=22M_maxstep=2820/flop_2.00e+17_step_2827.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5861b0910f251d31fd063f77c343107179d97f22f34817e1b8a8cdc978efc1
3
+ size 148163593
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=3660/flop_3.20e+18_step_3663.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f336e37f2fe6a754973a27c14478c1b137460b467074883bd7ec0350a087900a
3
+ size 1595772595
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=3420/flop_2.00e+17_step_1716.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24e5fa8976612ac4e951ec377564d0d2db62d369b3804e82eabc4514b3df1bdf
3
- size 225884533
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3712a4be5fe7a67d0f3ee3da198137f4a6af4b2165582c5d6a90e169627073e5
3
+ size 225882549
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=3420/flop_4.00e+17_step_3430.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a419a8e843cc7f39c8d1c7d6556bbc2111cfc8f2e9f5e1fbd99520f69b7c8e00
3
+ size 225884405
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=840/flop_1.00e+17_step_857.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fb1dd4c34392435dd5b1cf5dfcb14b2dc3c257dc2dd2b4b331bcc31b5b3cc8
3
+ size 225884269
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=37M_maxstep=840/flop_5.00e+16_step_429.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0a41281c29c2dca92551029043470da4a72ce63af2c97d760f2bd0be852c020
3
- size 225884397
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba932cc2be4c73d45222878fc9ab522ead065aa3743f697a72d315b78a28e976
3
+ size 225882413
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=17860/flop_1.28e+19_step_8937.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f35b56624b89e8f56786a8cbad5d5f5b17332644d7d7e91ecde843d6bbbcfe17
3
- size 2048266581
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d808132152378e33f7bcffb7c8d5c145341bbec231494f7abc24699bbcca59d
3
+ size 2048261653
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=260/flop_2.51e+16_step_139.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6084cd577a2de5f53d7c1503ccf51cbfdaaf979d845aab0c1d02eb0a989e4842
3
- size 326620479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afee64b38b5cd9e774ae210e998af880051c499ca54098c09d035687072bf59c
3
+ size 326618111
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=57M_maxstep=260/flop_5.00e+16_step_276.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe397526c5d54aad646dca5ab0170176e2559b05e9800092f97de21d72e98c4
3
+ size 326620287
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=200/flop_3.15e+15_step_102.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:214023585298d4857640ef0dcc00b855acb5995b469ae9aa8faad65e3dee8860
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d49cd9177adce9b513f8a406af849c86f8b59d69ed90e71f5f837a63eca1217
3
+ size 71568191
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=200/flop_6.25e+15_step_202.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992744295fe6a30af6b1efd0815517e10727e8a9052f3ad201339230b317b032
3
+ size 71569151