Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
45804fd
·
verified ·
1 Parent(s): 99e2700

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. dataset=rw/hparams=tuned_warmup=long_decay=const/params=15M_maxstep=69220/flop_1.00e+17_step_11858.pt +2 -2
  2. dataset=rw/hparams=tuned_warmup=long_decay=const/params=15M_maxstep=69220/flop_1.25e+16_step_1483.pt +2 -2
  3. dataset=rw/hparams=tuned_warmup=long_decay=const/params=15M_maxstep=69220/flop_2.50e+16_step_2965.pt +2 -2
  4. dataset=rw/hparams=tuned_warmup=long_decay=const/params=15M_maxstep=69220/flop_5.00e+16_step_5929.pt +2 -2
  5. dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_1.00e+17_step_2745.pt +2 -2
  6. dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_1.25e+16_step_344.pt +2 -2
  7. dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_1.60e+18_step_43918.pt +2 -2
  8. dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_2.00e+17_step_5490.pt +2 -2
  9. dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_2.50e+16_step_687.pt +2 -2
  10. dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_4.00e+17_step_10980.pt +2 -2
  11. dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_5.00e+16_step_1373.pt +2 -2
  12. dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_6.27e+15_step_172.pt +2 -2
  13. dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_8.00e+17_step_21959.pt +2 -2
  14. dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_1.00e+17_step_40.pt +2 -2
  15. dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_1.28e+19_step_5107.pt +2 -2
  16. dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_1.60e+18_step_639.pt +2 -2
  17. dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_2.01e+17_step_80.pt +2 -2
  18. dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_2.56e+19_step_10214.pt +2 -2
  19. dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_6.40e+18_step_2554.pt +2 -2
  20. dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_8.02e+17_step_320.pt +2 -2
  21. dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_1.25e+16_step_9832.pt +2 -2
  22. dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_2.50e+16_step_19664.pt +2 -2
  23. dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_3.13e+15_step_2458.pt +2 -2
  24. dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_5.00e+16_step_39328.pt +2 -2
  25. dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_6.25e+15_step_4916.pt +2 -2
dataset=rw/hparams=tuned_warmup=long_decay=const/params=15M_maxstep=69220/flop_1.00e+17_step_11858.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0384bb476f2840623e27c2d12adec77de1b35ed0dce8feee2886934f3cdcdf5a
3
- size 107653891
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ef88dd14b35c53fd1b18d83628ba3d989e2e76908547a18d0219e7c00d71603
3
+ size 107652547
dataset=rw/hparams=tuned_warmup=long_decay=const/params=15M_maxstep=69220/flop_1.25e+16_step_1483.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bc108a8303ce6a237ff224b772a89fabdf3f7c5de0812838799e0a38e2bc9fb
3
- size 107653743
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0ba0ee254b8863c2aa2ced19646dcb6c2370be97408e5a40faecdf90127c39
3
+ size 107652399
dataset=rw/hparams=tuned_warmup=long_decay=const/params=15M_maxstep=69220/flop_2.50e+16_step_2965.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b421d1d046578339df2dc76ab7303e64ff7a525aad292d64a18b44b77e8ca466
3
- size 107653743
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f776f4c16f1e8e11ca7c98503c8bac11045931941e8692d99b0bbcca582147c3
3
+ size 107652399
dataset=rw/hparams=tuned_warmup=long_decay=const/params=15M_maxstep=69220/flop_5.00e+16_step_5929.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f12d3746151389f5b622c6710db7ffa140812c6f66b2e09e072e64560cf366af
3
- size 107653743
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3357bbbcdcb2eb7152b24bb93c96a0dd7b8944d82e9266d3899e264908ec0b9
3
+ size 107652399
dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_1.00e+17_step_2745.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ace0dac721cf9608a908b0e83c620c7a28a83cf0e4662b2bff66f6c3096bed0
3
- size 225884597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119f5e15f27f578cf9ea704fe80b7acbdf804099fdb43c6fa1f20e1454d94e95
3
+ size 225882549
dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_1.25e+16_step_344.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e2777b48348579d53e421f61629a1226a33d41966e3251b99eb652475ab7762
3
- size 225884461
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d352fee20ab8e73a5068f1f9881a3992447c033c4e76c9c0d94c771f7c8ca83
3
+ size 225882413
dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_1.60e+18_step_43918.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4159a4cdec80115e1dc9a5b05583961d95233098ff37795a9a3fbf211036e527
3
- size 225884733
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b599a5ecd039c16589d144d56b6444ee6b6fa2ce82f7cd4cd9752daf79cae535
3
+ size 225882685
dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_2.00e+17_step_5490.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e29a1327c962e7ecd94b673aadb3d6b3fa800d61b714eb4a49b57f3c48c1c630
3
- size 225884597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37b53cde4d3116bb47baadcb83daf0bd9f58115b96e894c43d354b0ea7efc60
3
+ size 225882549
dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_2.50e+16_step_687.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bac1cb310be9e62c15cfbf506f6a101547521f84a4c12c687c7284619753169
3
- size 225884461
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415a70ed473490bdc2d74d6e72a0cf5ef7b08913b707adfa6d6020dfd94a3dcd
3
+ size 225882413
dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_4.00e+17_step_10980.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2404b858c7c33b91d10468efec7942816be2a3d7df184d67f8cbdbd00af55e0f
3
- size 225884733
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce3e625a7b9bb3d5b680e12e7bfcdffac4d453c03c9a4ef9380c7827da2ac4f
3
+ size 225882685
dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_5.00e+16_step_1373.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4924052746c8febbadb6bea46f708f3d9ace57083bf728b327f908bd49bb0dad
3
- size 225884597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ac1bd6c6e100fc964103cacf960a89981f15b766f286edef84aaa03023c138
3
+ size 225882549
dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_6.27e+15_step_172.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5055c01c808f36c064c3a735f21ebabd5e4519b6c8083519224cd78c9d92eb4f
3
- size 225884461
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec5c73ae8f5951cebea6ffc890342c99c71f43302f493acaf3333a8414d5217
3
+ size 225882413
dataset=rw/hparams=tuned_warmup=long_decay=const/params=37M_maxstep=45220/flop_8.00e+17_step_21959.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e9e3d5d612be5752398d3ca0af54aece83f6ce229f5f5f77c60cb44598c4b33
3
- size 225884733
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc907c59e2032ee137fa4151fc451a91a6cb82129e9a32e9221d8efe61cde38
3
+ size 225882685
dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_1.00e+17_step_40.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6d758a418cf23e263a0a6f7bffc8f434c4a591b0bdcd5e89d1b323adee1d01b
3
- size 2048264229
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:319525ddbd67b5c273fa79127ee62900beae2fffe6e4eaf85aec9535cad56d1e
3
+ size 2048259237
dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_1.28e+19_step_5107.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a376d628c942ebfb60e55965671ed28be90b357604c8bebc238030e788774c34
3
- size 2048266645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad162f371eb91137de79ca6a78ecfe143927966b94745b32ab8a8c4851f38b9
3
+ size 2048261653
dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_1.60e+18_step_639.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8034e3cff502a0f500211abebb93943ebea26e94b9c7569a05662f95c8868169
3
- size 2048265789
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9755aad35314420796a9a0485808b7ca321ab768c5d2f201eaee27bcf5efffb0
3
+ size 2048260797
dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_2.01e+17_step_80.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d672afcb7dc3839dd6d12fad23c8072931018dfac407f20dc7f59e56bcea20c1
3
- size 2048264229
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43e497c28a8c65c8acfa03a9f7e61a2f44c2b56f785e7e683fb544f0247683e
3
+ size 2048259237
dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_2.56e+19_step_10214.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:038bdb192f374409f80e5f6039b5effaeac2afd4ee62bb7404a3af07d2f3e466
3
- size 2048266989
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b61c4c43a76fa3e68977c16b38e835908c4cb48c2f0c5e5ed024d2b0cf36e66f
3
+ size 2048261997
dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_6.40e+18_step_2554.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5f9140b3b8bef71e959a10ffa824311463498cbba48ebe9d941c7c89f83378a
3
- size 2048266645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba48798bd016b603270d94aef226007dc6a1fcf420d364b125b10a725a676bb
3
+ size 2048261653
dataset=rw/hparams=tuned_warmup=long_decay=const/params=455M_maxstep=10360/flop_8.02e+17_step_320.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc8b22248daac5f4984730002db594569135af1d59b896740e4278726afe7dad
3
- size 2048265789
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8b871ffb939f9fb812a6c1679c7294a23b2a923e83b6812e45b811b0ea3f30
3
+ size 2048260797
dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_1.25e+16_step_9832.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4833dcf305b15ae34661b2c29604aa5dc1a455379f8de649be85fad57d8599c7
3
- size 40085236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b2639d2b256fbe2b1f8cdd2b0d74636eb3d89cbecd17d8be81b9a06011ab4c
3
+ size 40084468
dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_2.50e+16_step_19664.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40a47e6ad62844ebc7a7d418ce37a457f7c89fbc5b4e5c647d91bc26d6261f39
3
- size 40085345
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f3160b7450365135e04268c4fa36b3eea2c345773bc05d08e282e56551ff09
3
+ size 40084577
dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_3.13e+15_step_2458.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7449d505132ebb9fe300321a2f1a93ff0c134fe356c16725b849d54bad400f9
3
- size 40085236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b007a9739424cf92b321c9d50dd0fbd02a8dadb934f802c30870318875c696
3
+ size 40084468
dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_5.00e+16_step_39328.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcca7c9942cf9a4e732c54909f8ce45d9b60cae784561c5cfd493ffac3b55bd1
3
- size 40085345
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9dc4df1f16c1497c17bbd2d869d7f0d226a3116af64bc33880d3b8df7b3c742
3
+ size 40084577
dataset=rw/hparams=tuned_warmup=long_decay=const/params=5M_maxstep=50500/flop_6.25e+15_step_4916.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51f5455186ed25fdc10b4cdaae48a035528f343eb865c7d2012af9f7dd45be3a
3
- size 40085236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6633e6c8477522845b72269248b8698364da9406fa12847051e66f1ae7aac2
3
+ size 40084468