Hugging Face's logo

formll
/
resolving-scaling-law-discrepancies

open_lm
Model card Files Community
TomerPorian commited on
Commit
880f66c
•
1 Parent(s): 9cb1cca

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=580/flop_1.00e+17_step_294.pt +2 -2
  2. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=580/flop_2.00e+17_step_586.pt +3 -0
  3. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=840/flop_2.00e+17_step_427.pt +2 -2
  4. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=840/flop_4.00e+17_step_853.pt +3 -0
  5. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=2020/flop_1.00e+17_step_2037.pt +3 -0
  6. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=2300/flop_1.60e+18_step_2302.pt +3 -0
  7. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=2300/flop_8.00e+17_step_1152.pt +2 -2
  8. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=4600/flop_1.60e+18_step_2303.pt +2 -2
  9. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=4600/flop_3.20e+18_step_4605.pt +3 -0
  10. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=5860/flop_3.20e+18_step_2931.pt +2 -2
  11. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=17860/flop_2.56e+19_step_17873.pt +3 -0
  12. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=8920/flop_1.28e+19_step_8936.pt +3 -0
  13. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=8920/flop_6.40e+18_step_4469.pt +2 -2
  14. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=5M_maxstep=380/flop_3.14e+15_step_193.pt +2 -2
  15. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=5M_maxstep=380/flop_6.25e+15_step_383.pt +3 -0
  16. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=1480/flop_2.00e+17_step_750.pt +2 -2
  17. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=1480/flop_4.00e+17_step_1499.pt +3 -0
  18. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=2980/flop_4.00e+17_step_1500.pt +2 -2
  19. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=2980/flop_8.00e+17_step_2999.pt +3 -0
  20. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=400/flop_1.25e+16_step_405.pt +3 -0
  21. dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=400/flop_6.26e+15_step_203.pt +2 -2
  22. dataset=rw/hparams=tuned_warmup=short_decay=const/params=15M_maxstep=69220/flop_1.00e+17_step_11858.pt +2 -2
  23. dataset=rw/hparams=tuned_warmup=short_decay=const/params=15M_maxstep=69220/flop_2.00e+17_step_23716.pt +2 -2
  24. dataset=rw/hparams=tuned_warmup=short_decay=const/params=15M_maxstep=69220/flop_4.00e+17_step_47432.pt +2 -2
  25. dataset=rw/hparams=tuned_warmup=short_decay=const/params=15M_maxstep=69220/flop_6.26e+15_step_742.pt +2 -2
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=580/flop_1.00e+17_step_294.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fd06ae365c7a54641d03aba4e1363d9925e802053d51f6a56f24e7e1ce6de70
3
- size 563346618
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371b9d87cd5e2e6f2087f72bd3554ea486a971c56a2f21dba254b0b70ef33b90
3
+ size 563343738
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=108M_maxstep=580/flop_2.00e+17_step_586.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31cf4d791696ac1b99ddc64a20a07a066d8762f1024ca3ec34de6b3a296b96e
3
+ size 563346426
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=840/flop_2.00e+17_step_427.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8feec09e132d31f5795959a087aa17c56e47392ef67c5a9ce10951c2c0dfc5d
3
- size 738704501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4949f92882bd2bdb88590b7f7b265f8a1184936b51d7325beb984fd91a622f5
3
+ size 738701045
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=149M_maxstep=840/flop_4.00e+17_step_853.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d8a889755767977c04a467d37da92ffab0e782a559aa506ea057052279d866
3
+ size 738704309
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=15M_maxstep=2020/flop_1.00e+17_step_2037.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95718397536781d2c75cb93b3b13a66dec24a1b0f7741404dc5435d1ff247de
3
+ size 107653551
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=2300/flop_1.60e+18_step_2302.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5426a001808c1ba8ad0931d7cf8b6c90239e40b2a49b28bfc7edb1c612c765ac
3
+ size 1052007303
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=2300/flop_8.00e+17_step_1152.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6338c0302056c785cc784475b8d7db29ada87a3e98cd5da296bdce2e88c8913
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c107a3914af97dcfeb78536f82ad6470a5e4928526ce9e64ee14cd323c2f8c
3
+ size 1052003591
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=4600/flop_1.60e+18_step_2303.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c7d4134c200d3b897eb4f053af758d6e1c77e6f5b5f443f25c5fe0fd4610544
3
- size 1052007559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab063cd88210cfe678f3ae562471d8aee5902b2c35f0d7dc3e271b1fb47ee32
3
+ size 1052003591
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=220M_maxstep=4600/flop_3.20e+18_step_4605.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46dcfe8123311d9d94af91228e64f2b05870b8898e78ab7967c4029010a1f8ef
3
+ size 1052007303
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=347M_maxstep=5860/flop_3.20e+18_step_2931.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:214d3a96bfc6b98ca49c3acadee36c31bf69ef91ac11e48c2205f5d7e6b168d4
3
- size 1595772851
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11b635f3b1a14d5356a6a4c8a604f4ce4b8f02eb233d625baa380ccd5af1ada
3
+ size 1595768499
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=17860/flop_2.56e+19_step_17873.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60852ff14e4c9d0708de15310cff04ce54841fa6bccdc0b2478d8cf4b5874ff4
3
+ size 2048266669
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=8920/flop_1.28e+19_step_8936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec7f371fdaa696fa56228dddef4584c812d4758cf512235d6a2eed865a7b434
3
+ size 2048266325
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=455M_maxstep=8920/flop_6.40e+18_step_4469.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e60119435a734c8710237058011bea5671f51903a245465b13d5775bd2645ea
3
- size 2048266581
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f9445cbec5b9e6706060fd31f27443c74cf333508bf70f27c7e2556c560f04
3
+ size 2048261653
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=5M_maxstep=380/flop_3.14e+15_step_193.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:697258c9b56d1fbfd109733ec2f8b63d99e9261219316ce29d7b824b0cddd77c
3
- size 40084999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0deb5e249a3bd30b819278fbe1afaaccd2462664327a7c37f383ab17b2a977e
3
+ size 40084295
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=5M_maxstep=380/flop_6.25e+15_step_383.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1a996e94f09d3205ffeb5cd594e079c77714ce65c4838aa137e6f33cb35490
3
+ size 40084871
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=1480/flop_2.00e+17_step_750.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df01e0a60ef15729f3692ec3d2243970b050a0d5f7f79a00a01ba1eb462478c2
3
- size 455680721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940dab6031b110854ab29906ed424354615a17ce9fadabc9d281ac8637fe64f5
3
+ size 455677969
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=1480/flop_4.00e+17_step_1499.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a29a4d98b86709b292e85af5a99c624630441c69c4a04a26a2ca9244c9a8289
3
+ size 455680717
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=2980/flop_4.00e+17_step_1500.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c9deb888b2ed92589932f10b613ac819694f34e968732390267ad80cb96a7bf
3
- size 455680909
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1b8a48363b5ddd14d803ad399bdcfb2b52147a2101deeb5ce2a34b9ae90fe1e
3
+ size 455678157
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=84M_maxstep=2980/flop_8.00e+17_step_2999.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea3288cb09efb09cdfa3ccd300bede52c5e92d5c6e1eb9a8cbdf19de99bf800
3
+ size 455680717
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=400/flop_1.25e+16_step_405.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0188bbf7a3225dda0d58f7ca5c23c0df3ed9224f2d52ef3ed7a6c51e467135
3
+ size 71569151
dataset=rw/hparams=base_warmup=short_decay=chinchilla/params=9M_maxstep=400/flop_6.26e+15_step_203.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fde151967d51320c74c97c3c6c8c065c2e19059a2e0665af34dfd3bb9378d2c9
3
- size 71569279
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e3a2f753176a2e5c18e611d9d4c57eeca23edd8fcb12d992880d3f3f83dcbb
3
+ size 71568191
dataset=rw/hparams=tuned_warmup=short_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 sha256:5e062938695f582631eb40c5eb3b30c34f1e7662bec594a7464385c17bc9c0d4
3
- size 107653891
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea70cdaafc1ea4dd0aca23e2b04ca426bdc905a3ea0acc13305b2bbb8ff7ba5
3
+ size 107652547
dataset=rw/hparams=tuned_warmup=short_decay=const/params=15M_maxstep=69220/flop_2.00e+17_step_23716.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f73e72f1a36a20d6e7d6b67d0ad24df88abaf48d54ac89b5bdedc12c6dc43818
3
- size 107653891
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0215663908d254645ff72546700c6fee8bd8aeb300a9bac9a5a30e885ad233c
3
+ size 107652547
dataset=rw/hparams=tuned_warmup=short_decay=const/params=15M_maxstep=69220/flop_4.00e+17_step_47432.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b388c4b69d9a835fe847a594fb63de16d1a4fe191fcfad1546cbcf1fe3dfa95
3
- size 107653891
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db7c10e4cf64d3764903a7f7c9c66c0478d2473955b73760e7302ffc19b4010d
3
+ size 107652547
dataset=rw/hparams=tuned_warmup=short_decay=const/params=15M_maxstep=69220/flop_6.26e+15_step_742.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6da111968611ecbeee2fcca463001eb24ee7c935d6fd2d30fb2a9ad75dd8417
3
- size 107653339
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a17c859950802dc7ce4b00299f6f8d95c695aa53e5536830fec8b0858383dc83
3
+ size 107651995