Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
8fc31a6
·
verified ·
1 Parent(s): 98b002a

Add files using large-upload tool

Browse files
Files changed (24) hide show
  1. dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_1.00e+17_step_469.pt +2 -2
  2. dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_1.28e+19_step_60025.pt +2 -2
  3. dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_1.60e+18_step_7504.pt +2 -2
  4. dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_2.00e+17_step_938.pt +2 -2
  5. dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_3.20e+18_step_15007.pt +2 -2
  6. dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_4.00e+17_step_1876.pt +2 -2
  7. dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_5.01e+16_step_235.pt +2 -2
  8. dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_6.40e+18_step_30013.pt +2 -2
  9. dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_8.00e+17_step_3752.pt +2 -2
  10. dataset=rw/hparams=tuned_warmup=long_decay=const/params=347M_maxstep=19040/flop_1.28e+19_step_9379.pt +2 -2
  11. dataset=rw/hparams=tuned_warmup=long_decay=const/params=347M_maxstep=19040/flop_1.60e+18_step_1173.pt +2 -2
  12. dataset=rw/hparams=tuned_warmup=long_decay=const/params=347M_maxstep=19040/flop_2.01e+17_step_147.pt +2 -2
  13. dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_1.28e+19_step_3325.pt +2 -2
  14. dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_2.00e+17_step_52.pt +2 -2
  15. dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_2.56e+19_step_6650.pt +2 -2
  16. dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_4.00e+17_step_104.pt +2 -2
  17. dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_8.01e+17_step_208.pt +2 -2
  18. dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_1.00e+17_step_25925.pt +2 -2
  19. dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_1.25e+16_step_3241.pt +2 -2
  20. dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_2.00e+17_step_51849.pt +2 -2
  21. dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_2.50e+16_step_6482.pt +2 -2
  22. dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_3.13e+15_step_811.pt +2 -2
  23. dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_5.00e+16_step_12963.pt +2 -2
  24. dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_6.25e+15_step_1621.pt +2 -2
dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_1.00e+17_step_469.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7edd2842a61baa8cde28a7f97072e7cd684a4278fdea2a0f6a783802265c8dfd
3
- size 563346682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ce58c26e420fff2f8a964da2d787dcd3eea53a21465efd664df0f8fe01395f9
3
+ size 563343738
dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_1.28e+19_step_60025.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70692b9196f60b5c022c7c9d53256a0b154ee9d076e571ba949c9d5b8eb5e8d3
3
- size 563347084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3d1defd742a1682af773ea5ff8bcdd83f7b9447b026ff06ea1f8c0ccd7f627
3
+ size 563344140
dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_1.60e+18_step_7504.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f412ae3c7984836dbb0a5368e6d08e8d02459ac90c45133185959bb28d02c865
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a961d668443dd06d7b18389a97883c245adc2168a2b088bf6b84646925868d5a
3
+ size 563343939
dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_2.00e+17_step_938.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cf327032fcfd200594efe376b7183b305c7e5c0707223928630ad7146bed0a6
3
- size 563346682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cf1f8e62d7a6cbf8627e3f043a0ee17775bb2d80db3e548416c951fcc1d9033
3
+ size 563343738
dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_3.20e+18_step_15007.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2e09258c5593f5b5c2869abe97944c7b88775f0a4d8270abe145e632a537b0a
3
- size 563347084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d58c027b04763132d4b0edc757ae6e96b2dd2fa5e031da239f8e0db4643c2ec0
3
+ size 563344140
dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_4.00e+17_step_1876.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65b549dac826a8e0ecc569e25795b242915a1307ce13c734a08e869fbedbe06d
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df1dc0ea450b0b814db35ab075f0259072071e9b61d64f6402e4b3691a25c6bb
3
+ size 563343939
dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_5.01e+16_step_235.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1320234f1689f7369d07bb04f51e02b84d63571964ab9b8d4929fc07a429525
3
- size 563346682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57861febbff11ac81327f9e81dbbdcc5c1438a096b58527bcfc6e71d11e002e3
3
+ size 563343738
dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_6.40e+18_step_30013.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:594651b4e71ace5af5d2394f592b57092cded9d1e53eb756760f355a4d3d33c3
3
- size 563347084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b4b9f65a53b9880959d4edfe373169d21a98170feaa41e02d63575f9b15879
3
+ size 563344140
dataset=rw/hparams=tuned_warmup=long_decay=const/params=108M_maxstep=66180/flop_8.00e+17_step_3752.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:969eecd4924277ea656b5cd3559a421e85b53ef08438a5f100989adbc6fce217
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a6a1d98adf900b24c65ece53f96df727886f6d98917c2b93aadd35aea7baa0
3
+ size 563343939
dataset=rw/hparams=tuned_warmup=long_decay=const/params=347M_maxstep=19040/flop_1.28e+19_step_9379.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:077d7827ffe7e5598aada8084ac18bea7f3e80ab9dc66a599597cf74ba70134b
3
- size 1595772915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25408c688bd840d893ba47c592bae5411f9339fcea52a676abd90fdc28b2378e
3
+ size 1595768499
dataset=rw/hparams=tuned_warmup=long_decay=const/params=347M_maxstep=19040/flop_1.60e+18_step_1173.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d14b778584827f4eb19b3e2fae8513d207d3a69cf6252e229c242f2b229ddb06
3
- size 1595772915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5916f316d79ba39571ae11bdac0f69a1f2690ba44db94554c926659128cfcdfb
3
+ size 1595768499
dataset=rw/hparams=tuned_warmup=long_decay=const/params=347M_maxstep=19040/flop_2.01e+17_step_147.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57dea38a2293f59c3dc05ee38ba7fbf1c920048d80e22aa57db4fc0e95408e69
3
- size 1595772610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7401c8f35847de0a69fd871141f8bb1f7f3719c7e738210013f1fd55af42c2be
3
+ size 1595768194
dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_1.28e+19_step_3325.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:036867c67d7bdadaaf12225e02f529b98ade129b225ca5ef8e20a51c5d94fe6b
3
- size 2713751061
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53be2e4f1032653c74843bb2929fc2716eae441c36ffc424cf93341ba4943a3b
3
+ size 2713746069
dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_2.00e+17_step_52.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b80f67a00a2ef96a32e8b0d62b52eccb575a9daf67464e57109830dfd635d2be
3
- size 2713750309
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e557f319609bc537a388e6ff39f451e8deba10f16cd8e7dc299e1ff6d27d50
3
+ size 2713745317
dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_2.56e+19_step_6650.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7710a8fa6451b0d930a5b7b76ce1d414aedc780be0fe9e348b0d4da63061f2d8
3
- size 2713751061
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa7d9e8ad96e4ec0bf250eee643335e0f0d3b677b09adfd7ff5d2dd3fbab1f8
3
+ size 2713746069
dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_4.00e+17_step_104.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b8ee6c857039220e65e99b0a13f6385d012b6c0825af2942ad2dee279bf1e7c
3
- size 2713750717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ccef82002fc4397150c44a15fd49442aa58fba049f66a9423b7dcc468c5d201
3
+ size 2713745725
dataset=rw/hparams=tuned_warmup=long_decay=const/params=611M_maxstep=6740/flop_8.01e+17_step_208.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51b859c764c98d62293655d516b6a1bbc81f7bcef1f20ec379d9677d94ee854b
3
- size 2713750717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df8b1af692989860e8b68b6e5cd92a02e54140697dfc42fa7187212bc21caa7a
3
+ size 2713745725
dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_1.00e+17_step_25925.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e5e1ff018b59ae8a242a3a2bbebb9387793149aba4c4666d6fcb7f48e176cb8
3
- size 71569421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e5c893e28c777146d0a8f275d46b57f259dc7d9587da8cc7c53ce95559dea9
3
+ size 71568333
dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_1.25e+16_step_3241.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6b7f1b9a3da172ddcda38249a2ac0957bfe10e5a6793e5b235f4fbb06182633
3
- size 71569350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e8fd82fa169ef500ac10c5518a09314d9ea2113e57c77f48af832c73c7c99f
3
+ size 71568262
dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_2.00e+17_step_51849.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a940cefdd53963013fde3396a0a4e495cf482bbca92c7a464b6fce11ca83c32f
3
- size 71569421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e719af9df5e37be4b9adf5363c8fc749f529d1df3898b920a8e234f83290a4a1
3
+ size 71568333
dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_2.50e+16_step_6482.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20c4ce20a838c8d709dc2dd2e6d0a17c5a5f5c709090b555c045e69fa3541c56
3
- size 71569350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157768609ef93184cc623de35f5996ed2fa764adc2c119e029a49b03495a5f6d
3
+ size 71568262
dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_3.13e+15_step_811.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dc539fd477bd1210d284036f58a8d8d201ce997c94b2193a9f649def9d2ca4c
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6377bf7a58720e24e1d167cc3c04e4acf6696278e16bcd15cfe99ca4b9cfd233
3
+ size 71568191
dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_5.00e+16_step_12963.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41f492836ab5f61e3cca2cd1dfde142df57cad301a440f241957cf449b0fe6ea
3
- size 71569421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5243284ceae40951e78735c51152e2b0c5a7db9b0d2c129804bd6976fbe91a
3
+ size 71568333
dataset=rw/hparams=tuned_warmup=long_decay=const/params=9M_maxstep=59860/flop_6.25e+15_step_1621.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23bde8191b7bcf478e2ca6e51204165f0becfaecba1aa2da40888a8e8820bfdb
3
- size 71569350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c2fa9ddb1fd8c0330420bd763f81f3e97ee6e27138b4d04720536e7b930aa7d
3
+ size 71568262