Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
247c566
•
1 Parent(s): c115640

Add files using large-upload tool

Browse files
Files changed (14) hide show
  1. dataset=rw/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_1.60e+18_step_2303.pt +2 -2
  2. dataset=rw/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_3.20e+18_step_4606.pt +2 -2
  3. dataset=rw/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_4.00e+17_step_576.pt +2 -2
  4. dataset=rw/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_6.40e+18_step_9212.pt +2 -2
  5. dataset=rw/hparams=tuned_warmup=short_decay=const/params=220M_maxstep=37400/flop_8.00e+17_step_1152.pt +2 -2
  6. dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_1.00e+17_step_1364.pt +2 -2
  7. dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_1.25e+16_step_171.pt +2 -2
  8. dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_1.60e+18_step_21818.pt +2 -2
  9. dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_2.00e+17_step_2728.pt +2 -2
  10. dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_2.50e+16_step_341.pt +2 -2
  11. dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_3.20e+18_step_43636.pt +2 -2
  12. dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_4.00e+17_step_5455.pt +2 -2
  13. dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_5.00e+16_step_682.pt +2 -2
  14. dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_8.00e+17_step_10909.pt +2 -2
dataset=rw/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 sha256:63f67844fcc90fa2f8389933e916f7e68653ef9269a73dd6c5deb9a32cf8384d
3
- size 1052007623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52095c6350d768065f7f6f940a5fec1041cb8fd710900f5456a0487113364849
3
+ size 1052003591
dataset=rw/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 sha256:73c560283ac1b0c19511ec98cb7cf39f3ea5a9c306bbd2c439310964ab149eb9
3
- size 1052007623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083374de927d2110fe071de3d01d30013bd16ad57f22baa31d3e94e2d90bc776
3
+ size 1052003591
dataset=rw/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:dc6b24e82c9be6967c9e8ccf5273bedf19a64a43fa807d19e12955fac3acb940
3
- size 1052007344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234450ff779dbc2a95b24cc72ac31c96cb4576ca37f330fc26d089107764d992
3
+ size 1052003312
dataset=rw/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:f8ecff4265d97bcb241114315e1a2fb1289fb074e1ee1ba1bf6414abcf9bcad9
3
- size 1052007623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c169ada4776dd2fc681c4d5b40a720f94fe85dad0e262b1cb18fcb8df0700c
3
+ size 1052003591
dataset=rw/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 sha256:5be1f28e780d07e2848513e917b12fa08099bf16c5de8aaef1e48c4ded5dc08d
3
- size 1052007623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a01eb0859dbb47067a4e0cb038ef61ac23bcd4614c3cc5e8770122c5bbbce90
3
+ size 1052003591
dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_1.00e+17_step_1364.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae378679fb04e7402ac1fa29ccc008399d0acb4ae68ffc5ae8eb36b7a84e6456
3
- size 326621089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb5ff04044dc4d8117d6513b0ddcc5562bc7659851c46b3ff622455f6e9821e
3
+ size 326618721
dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_1.25e+16_step_171.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:111adf894e6f8a5c6f2f9805340047d5fd7e7e348a6d29c4a379c7a6530da0af
3
- size 326620479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa2593ecee7fa6e3566d816d752d70bb088e0b7f5d3cbf11614dddb82709b1b
3
+ size 326618111
dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_1.60e+18_step_21818.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45a669654ff6ae4da35d1af56f52b84f0f4a8175560e965c37fd15481c17cbec
3
- size 326621315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ca4654291a17eaa6e87953f7bd024c91a0a9fc0ed79f01b04c6baf1e7e4ef3
3
+ size 326618947
dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_2.00e+17_step_2728.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5f29fad43e88c134d79bed28abc9de78cfacc036f18998000243b37a22c74b0
3
- size 326621089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04844e587cfbaea56192acbe11144e19cb3bf89921651e05ceacd24155667994
3
+ size 326618721
dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_2.50e+16_step_341.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:575913698db6bf9e7877f50f147aef258b8cc2dccbddb3a704efa070d3fb4c5d
3
- size 326620479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:255f7a867f29534ed639e03f64db7a7a206a20d935b47fa2c03875c5dd7cc2bb
3
+ size 326618111
dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_3.20e+18_step_43636.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ca62102ce5146a5ab5287fc2faf627c80c17db5f9ec8599ea241dadd2f10380
3
- size 326621315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865ada31d3617695530345a73a03a369e8bba834ed6f231d3fc5cc141d4a8812
3
+ size 326618947
dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_4.00e+17_step_5455.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9376acc893a36d10422e6261e36c7c50fd0692a040f3e42721df5670cb561e67
3
- size 326621089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970273a167776915726d6baf522eb8a3fdbabc763322edda0ff36a2fffc08e30
3
+ size 326618721
dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_5.00e+16_step_682.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8aeef43d24b87f6f0fd5720d3196fb75b6dbd090462c345bab539484b62920a8
3
- size 326620479
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1775357e43a6be3c12f7a3b58c29eb0d556fd024e900544a5b6e068f0ee17e20
3
+ size 326618111
dataset=rw/hparams=tuned_warmup=short_decay=const/params=57M_maxstep=75540/flop_8.00e+17_step_10909.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1edefc5f5e20c1f96a4c1aad9bf7401d4c7f418863a767f8ce02031c4e963dd
3
- size 326621315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff58fed053e76dd100ed5cbe3ec170764ebaee8f28932f85285ff7f43618c6be
3
+ size 326618947