Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
af24491
·
verified ·
1 Parent(s): 2b577ef

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_1.00e+17_step_285.pt +2 -2
  2. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_1.60e+18_step_4551.pt +2 -2
  3. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_2.00e+17_step_569.pt +2 -2
  4. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_2.56e+19_step_72802.pt +2 -2
  5. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_4.00e+17_step_1138.pt +2 -2
  6. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_6.40e+18_step_18201.pt +2 -2
  7. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_8.00e+17_step_2276.pt +2 -2
  8. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_1.00e+17_step_144.pt +2 -2
  9. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_1.28e+19_step_18423.pt +2 -2
  10. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_1.60e+18_step_2303.pt +2 -2
  11. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_2.00e+17_step_288.pt +2 -2
  12. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_2.56e+19_step_36845.pt +2 -2
  13. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_3.20e+18_step_4606.pt +2 -2
  14. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_4.00e+17_step_576.pt +2 -2
  15. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_6.40e+18_step_9212.pt +2 -2
  16. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_8.00e+17_step_1152.pt +2 -2
  17. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=5M_maxstep=25240/flop_1.25e+16_step_9832.pt +2 -2
  18. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=5M_maxstep=25240/flop_2.50e+16_step_19664.pt +2 -2
  19. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=5M_maxstep=25240/flop_3.13e+15_step_2458.pt +2 -2
  20. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=5M_maxstep=25240/flop_6.25e+15_step_4916.pt +2 -2
  21. dataset=owt2/hparams=tuned_warmup=short_decay=const/params=611M_maxstep=6740/flop_1.00e+17_step_26.pt +2 -2
  22. dataset=rw/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37492/flop_1.00e+17_step_144.pt +2 -2
  23. dataset=rw/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37492/flop_1.28e+19_step_18423.pt +2 -2
  24. dataset=rw/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37492/flop_2.00e+17_step_288.pt +2 -2
  25. dataset=rw/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37492/flop_8.00e+17_step_1152.pt +2 -2
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_1.00e+17_step_285.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f15a0a5bb3cd3e545e0b71a3da5682f1be03af5f9af740e55f5edb04921f9dc
3
- size 738704565
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465b70cba3dbe52bdfc7b1a80e812f0807a1f8d76236e0e7ed97899636956f33
3
+ size 738701045
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_1.60e+18_step_4551.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e587b73ddec33badb0fadfab3cf17b6bc9b76ad07daee89acd03d8ebeab73c6a
3
- size 738704805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff814cdbf4206550a55ca83159404c69df0945cecca06c3a949426f0a0b70cd
3
+ size 738701285
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_2.00e+17_step_569.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d0c7a37c45d1b3ec3d475c1bd2528ceb6c662b4341e9dfd614f785235be5eaf
3
- size 738704565
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45fafab6aa9649d43fc4e5ff6a51d27a3ca79bd9beb7432eb57a763f10e7891e
3
+ size 738701045
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_2.56e+19_step_72802.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce2e6bd03b7fc5456da2e472c53fac45fef94e97b4a2c9925326feb82d71c173
3
- size 738705045
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a407f4095868ebf852121522100ad7963e0d7e393b28ffca6becfc8ac9a880
3
+ size 738701525
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_4.00e+17_step_1138.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62161e7d1f3969bd58c98a6e153d3010a032eb59653baf4622d6203a4c73f59b
3
- size 738704805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2206330ab7ed4a159a552ba02edafa5d44f5003100e7499ea63d42e14bcd56
3
+ size 738701285
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_6.40e+18_step_18201.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34c9069445f48ee438ffea151e73e4d789610fbfd1d4b625e4b8e1fe308b7e5b
3
- size 738705045
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c414e2ae32ca389a6c486811f129047685315bf85eb26459610a697e2afacdb9
3
+ size 738701525
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=149M_maxstep=73920/flop_8.00e+17_step_2276.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c4479cdb6f45ddbfa143e29ca7e8762337c5384e080ad71a9ea051169bc7183
3
- size 738704805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70f1ed5948ee04de0fb0e673bdffab54a8d408f3f3a44ca1b0f6980cef2f257d
3
+ size 738701285
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_1.00e+17_step_144.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:511c9439e91c857c0d105d3676c081dc7d6518ba7ed3bb9da0fcbf600c27fbd1
3
- size 1052007344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b2de63eddb86e219d2434d7bd8e466c535b0461c97cf71daec7a381f6753fd
3
+ size 1052003312
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_1.28e+19_step_18423.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:608b53b89b4d1094e04fe7ecd8f9ef77c361e3d3370430107fde94da12f29075
3
- size 1052007902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52dc7060c1946b343d265feed53e62fa04eaae8a31bc448956c8cc2821853cee
3
+ size 1052003870
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_1.60e+18_step_2303.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae10e27a71af4a701cd2da100d94804fa16aa973f1ddbcc00ed183875cdea44e
3
- size 1052007623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5e74f4b7529b40ff7a1ff35da4cf225c34bdccd3a6e9a0ecabfc34012d6228
3
+ size 1052003591
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_2.00e+17_step_288.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:922f666acc4a98f45a7330406578c597d66ecd80bfc34008a8fbcbd7f671a9dc
3
- size 1052007344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ccfa9e5fb137e269ca87d3ef21b091c06044f3adaf904462c701d070926d3ec
3
+ size 1052003312
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_2.56e+19_step_36845.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20159135a669bd7c8891ab85bd3b9815214afae3f0bf9cdd490d5a1608a6668c
3
- size 1052007902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d00d791eab771febac415aadcb7548c1343650b84c0760b02f812996a15feb0
3
+ size 1052003870
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_3.20e+18_step_4606.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb3d1d183a8c29cd9848ca9ba1bf73f2e1fe4f18106c3a030fea8d196620ad6a
3
- size 1052007623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4178e1be693f7d5494c8c9fd8af6f7107e294b9cdc02f9c2cdfc2b9a27f3bf
3
+ size 1052003591
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_4.00e+17_step_576.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a674f29ece77c999faeddf28e7391f90794a9d7a15d366a47c61127e160af2e7
3
- size 1052007344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb4b332e674d0c0a27b8f15e2d4d8cd7d210f1c5aee74db91e3eacf876dc070
3
+ size 1052003312
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_6.40e+18_step_9212.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:790415759029c3b370445c56252bc22eab82d490b1de6a8f21045332b5264a91
3
- size 1052007623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaacf388315a39f7004cf9c2f7dace47664d50b59c63f6ea5837623bbd2b3553
3
+ size 1052003591
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_8.00e+17_step_1152.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16d7b66fb9615d0b1ad49588f2e9b2c179b13c2fd0a6f4d4ae549e5a5c5d718f
3
- size 1052007623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992314eb29857f91814aff0b8149b7ae181d2eab1a80429855e0a4eba7c77602
3
+ size 1052003591
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=5M_maxstep=25240/flop_1.25e+16_step_9832.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b6558cac09b92315b388d52e6ca1599f66951e590d008d426da04c53313641d
3
- size 40085236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7476074771ce03a470c9bddef1eff5d760b1670a15ff40c217ae4581c1c0fdda
3
+ size 40084468
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=5M_maxstep=25240/flop_2.50e+16_step_19664.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9268350faf2c12f896da06619dbf9e19dcb67c10c8b77c9ad8b59941f363482
3
- size 40085345
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d85625c4fd4c89d79d5b5da00e246cbeac442fd6853d3633976af8adefa98e
3
+ size 40084577
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=5M_maxstep=25240/flop_3.13e+15_step_2458.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f694b67af1de35b59dfa958c29d68d8f9de8948a9fea0a87cded62cf59ba8f2
3
- size 40085236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ef80e397eb4b8d937651cd515b1421f96495a57e8b3453095fb122e6adf794
3
+ size 40084468
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=5M_maxstep=25240/flop_6.25e+15_step_4916.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4544f556033cb34bbf1f7c16fbcbd776ccc16d22dbb01199d86c1100c2a3806c
3
- size 40085236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a22c5c9137208f18ea42a851e7ae4103dd5938873f0ab9a6ef014cfa2c55d6
3
+ size 40084468
dataset=owt2/hparams=tuned_warmup=short_decay=const/params=611M_maxstep=6740/flop_1.00e+17_step_26.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76066f8caedfa3c051b7fcb5548fdf23858f6923b5f4ccbb0377645933107a56
3
- size 2713750309
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c700736d4d11e48dde79ffb28f8d43df6a70f5fb93ddcb714d8a103ea2579423
3
+ size 2713745317
dataset=rw/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37492/flop_1.00e+17_step_144.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9565b17a82645b661603ea7563419f3a747b703aa1aa29a5c3c0683fc6a49c1b
3
- size 1052007280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd76ae76d53b025fd6ff474fcd4024da394c217635a2d7f016c8e4e55c6edfce
3
+ size 1052003312
dataset=rw/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37492/flop_1.28e+19_step_18423.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:699c8c1afda54c2fda3b6b5ca2b69a84cca520ad4bec2c1cf27c8011e52990af
3
- size 1052007838
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5128939ffb09291ba0e6279cfa12b3e2f544e2895614457f9be7db40e8edb9
3
+ size 1052003870
dataset=rw/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37492/flop_2.00e+17_step_288.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39772d08b85783a9d7711d19fb5e6d10b0a303396333bcd5a6fd5d613dd201df
3
- size 1052007280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3ce1aecfb53de8e22874f31f410e56ad8cdfae03f0f8b929737921dcff9b28
3
+ size 1052003312
dataset=rw/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37492/flop_8.00e+17_step_1152.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0773ee0e738fc7839d6795d5ba8036066e57e8f756d6e85b1762c6712672adab
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88046df0b93d7b1bd704140120f5b1d734f5bb287fc72e12a7e8399a4252d27d
3
+ size 1052003591