Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
54ddacb
·
verified ·
1 Parent(s): c358209

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_1.00e+17_step_294.pt +2 -2
  2. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_1.28e+19_step_37516.pt +2 -2
  3. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_1.60e+18_step_4690.pt +2 -2
  4. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_2.00e+17_step_587.pt +2 -2
  5. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_3.20e+18_step_9379.pt +2 -2
  6. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_4.00e+17_step_1173.pt +2 -2
  7. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_5.02e+16_step_147.pt +2 -2
  8. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_6.40e+18_step_18758.pt +2 -2
  9. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_8.00e+17_step_2345.pt +2 -2
  10. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_1.00e+17_step_144.pt +2 -2
  11. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_1.60e+18_step_2303.pt +2 -2
  12. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_2.00e+17_step_288.pt +2 -2
  13. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_2.56e+19_step_36845.pt +2 -2
  14. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_3.20e+18_step_4606.pt +2 -2
  15. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_4.00e+17_step_576.pt +2 -2
  16. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_6.40e+18_step_9212.pt +2 -2
  17. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_8.00e+17_step_1152.pt +2 -2
  18. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_1.00e+17_step_4237.pt +2 -2
  19. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_1.25e+16_step_530.pt +2 -2
  20. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_2.00e+17_step_8473.pt +2 -2
  21. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_2.50e+16_step_1060.pt +2 -2
  22. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_3.14e+15_step_133.pt +2 -2
  23. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_5.00e+16_step_2119.pt +2 -2
  24. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_6.26e+15_step_265.pt +2 -2
  25. dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=9M_maxstep=12201/flop_1.25e+16_step_406.pt +2 -2
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_1.00e+17_step_294.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5578b6323768c2cab8ed5e87f6cb13fa6a78aa2319540d11f5ef8a39120faf6
3
- size 563346618
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdba36999ea19f1955e0dde20861613cb48e2c23e1bcd07a3c2fa1def947d633
3
+ size 563343738
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_1.28e+19_step_37516.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3149aab9ba27dfd9206e737379d308bab3d4ab4ddf7a2571426bb5bd5d7f1c23
3
- size 563347084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6f708e6059d88e98d7d3a6a5c185da04195c39dbe2fa90091f50fb81bebac4
3
+ size 563344140
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_1.60e+18_step_4690.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b6e82e76db57b4adb99ed4c96ac1efc8d8f99936f2e0e303479a30454cf2fc7
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026ecb74b85e6f1e0ccc52b140ddd283e58145cee3406505b6a767e35dc9cde8
3
+ size 563343939
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_2.00e+17_step_587.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3a3e48ecc2721dbdb8a011cad50bc0893d70a90cd407659c3be1a25be79df50
3
- size 563346618
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfb1052fba56dd34a4721796e103f18518559bd4882609942a71cac18fd9996
3
+ size 563343738
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_3.20e+18_step_9379.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f001e38a0d540d9e2b39edb13abf960b472bd080e222e1b551a75a32d8ac807
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b0064444edd68014ab04b10329b391daf5a1ce2d2838b31c8dd3168b0733666
3
+ size 563343939
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_4.00e+17_step_1173.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2e907a52a18f693c37084bcf2753762616a647d1f792f807cf83b415666c9d8
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee344176ea6f9afa4bb4836e9260fb57403a888a75d2f907ec4e6c4be8040c1
3
+ size 563343939
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_5.02e+16_step_147.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:095169b6f7ddf21c37972ea0a88c7936b51b43b95cf5a777b5f0c8fff3092b25
3
- size 563346618
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6651cf1f1d6d856753702ea41748282be045cfb7dee3032b141f594911297b03
3
+ size 563343738
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_6.40e+18_step_18758.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c0e60fd82fe82a2410ecaf3a55eaa54c84f992e5ccc140a64797d6f839e06eb
3
- size 563347084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba49bcb839f206cbe0a47f10e34b97d7827ca2a620e03124fa903759470caa7
3
+ size 563344140
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=108M_maxstep=41414/flop_8.00e+17_step_2345.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b36e62e52cf5760d6e99c3c199305bd006c816fdeac34b5e9c0b09fc39c66a87
3
- size 563346883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d76c5caa21aaa1dc072a8acb0431dd0f41847a5c576708cc5811a3765dc4dbda
3
+ size 563343939
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_1.00e+17_step_144.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0dd948c767c987666e2d6b6bc47ef070ed28bd6bf5c240cb81e8b1b07c4187d
3
- size 1052007280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf219a2bb549ea04dccdfb2adf1cf494984d05db144dfabdb988b9c232b19dc2
3
+ size 1052003312
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_1.60e+18_step_2303.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36850fbe1c65eafda7067f9d466148fc524b90f1bf9ee997965b2ce1f20c2a4f
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a2d307c4bc29d26c849d7194ae2ae9481c59d979cd4548977aeabe24d611145
3
+ size 1052003591
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_2.00e+17_step_288.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8969660b8993af308cda8be0393803ba913574e1ef18b42142d4271725d5c60
3
- size 1052007280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e84d94075c26b8d08dd946a81e4719c838cc7fc7a2b5ddcee461578b97aa8fa
3
+ size 1052003312
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_2.56e+19_step_36845.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae935ce5b26180c464ed446262e5b9990764ab5b38cc2fd158ab292ebf9729ff
3
- size 1052007838
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b828548cbfed54787cdb36d7826f02f3a43f8ca6091e641c5effbb997984077
3
+ size 1052003870
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_3.20e+18_step_4606.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:841bc74e59f078e723a4bc5497ebd4cbbb58186118b54ca9bdc544c4ac5f906a
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b778ea866ade01f559866cc2064597cc46e6fba96fd657128af90bb59d0e604
3
+ size 1052003591
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_4.00e+17_step_576.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2fe1ccbca658de295710a51f9423070ea3821489b91b1a7188aa797b80195a1
3
- size 1052007280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ccc445ca7c8ade9e82e9fd7b143ca9de6f881e8da3f90224abd6e5345491ba3
3
+ size 1052003312
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_6.40e+18_step_9212.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:596bec4257385ec7e4fd7e7a2f1d17d5ff36084709ae328aee4352eaba4c074f
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984725f2aaedad6f3c0af1e210d7c7584c0900e1a0c8b1da295c98cc583b1243
3
+ size 1052003591
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=220M_maxstep=37771/flop_8.00e+17_step_1152.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:974df80743c91ee4128ed564829afb059d43ceb9938c49adaf97a6f5303e7d34
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca563186157ac3ccfc340f6be57514a249bd9645ce2586e57360f458a4b9024
3
+ size 1052003591
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_1.00e+17_step_4237.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc4ea91aeb33b14efa3b80033874cd23ee19242d567f0be4cb0a8d12d2acc78b
3
- size 55875421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a8ed7055317ee2a2ff24f0a45e12c8722cb1efd59bac90b96da1b788b431efb
3
+ size 55874525
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_1.25e+16_step_530.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9027431e998d51142c3c6eded3a0dcf74ec40b3ec39b3599bf6a65424c54cf1f
3
- size 55875363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60a337cb28eea0fc124568652c6c68782fe0a02666cf594b22eefeffd231327
3
+ size 55874467
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_2.00e+17_step_8473.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71f5ce3e3e9e397d5d4f3170926b660c58ba0c53d6231cb15b46dfea37d432b9
3
- size 55875421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad940d81771bcc1cc4429ae5afe82ed8deece39e7c9861bf77667d86cebf7ea
3
+ size 55874525
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_2.50e+16_step_1060.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b434f9d4d16e68702272937b14e9d9c6d427a1599977258d377f79ad56414c6d
3
- size 55875421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f996c53b69e9c90aa1da3b6b12d2ed97b1495965364ab5398f3be1fc771c499
3
+ size 55874525
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_3.14e+15_step_133.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26f6df391dc427c8cdaa8c70c1fc907435c66b01b7760247e2b22adcaf437618
3
- size 55875363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39d2636bce656f6899a4ef5ec310a4b78752b0cea0fac9d7b962574358f05320
3
+ size 55874467
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_5.00e+16_step_2119.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4f523a1e508bd03a98c5f27ba5dff244a52d9ad99d727571274b443cd01b806
3
- size 55875421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9673466a36302a0a32c08773f51cc4c37af1ee1beaa7e5deee841fad036e939
3
+ size 55874525
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=7M_maxstep=12341/flop_6.26e+15_step_265.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c1be070f01fc2503ffd6157dc7614ae8482b8d02177264eace8217f3fe4e682
3
- size 55875363
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0fcfafca5a67ef2ddf1f17ca37b6d455703e304e8a7715c44efebbd4a6ddadb
3
+ size 55874467
dataset=owt2/hparams=base_warmup=short_decay=kaplan/params=9M_maxstep=12201/flop_1.25e+16_step_406.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29f44c293e458242bc4d32702d77b0d623c8f502668aeb8135a19b8a1978dbee
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ef503db700b6b48b1e8d11bc67f4c15a8335a82d5ef454212d2fc20f77f37e
3
+ size 71568191