qcz commited on
Commit
26f1499
·
verified ·
1 Parent(s): 81bc4f1

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. late/adamw-lr1e-5/checkpoint-1563/1_Dense/model.safetensors +3 -0
  2. late/adamw-lr1e-5/checkpoint-1563/2_Dense/model.safetensors +3 -0
  3. late/adamw-lr1e-5/checkpoint-1563/model.safetensors +3 -0
  4. late/adamw-lr1e-5/checkpoint-1563/rng_state_0.pth +3 -0
  5. late/adamw-lr1e-5/checkpoint-1563/rng_state_1.pth +3 -0
  6. late/adamw-lr1e-5/checkpoint-1563/rng_state_2.pth +3 -0
  7. late/adamw-lr1e-5/checkpoint-1563/rng_state_3.pth +3 -0
  8. late/adamw-lr1e-5/checkpoint-1563/scheduler.pt +3 -0
  9. late/adamw-lr1e-5/checkpoint-1563/training_args.bin +3 -0
  10. late/adamw-lr1e-5/checkpoint-2345/1_Dense/model.safetensors +3 -0
  11. late/adamw-lr1e-5/checkpoint-2345/2_Dense/model.safetensors +3 -0
  12. late/adamw-lr1e-5/checkpoint-2345/3_Dense/model.safetensors +3 -0
  13. late/adamw-lr1e-5/checkpoint-2345/model.safetensors +3 -0
  14. late/adamw-lr1e-5/checkpoint-2345/rng_state_0.pth +3 -0
  15. late/adamw-lr1e-5/checkpoint-2345/rng_state_1.pth +3 -0
  16. late/adamw-lr1e-5/checkpoint-2345/rng_state_2.pth +3 -0
  17. late/adamw-lr1e-5/checkpoint-2345/rng_state_3.pth +3 -0
  18. late/adamw-lr1e-5/checkpoint-2345/scheduler.pt +3 -0
  19. late/adamw-lr1e-5/checkpoint-2345/training_args.bin +3 -0
  20. late/adamw-lr1e-5/checkpoint-3126/rng_state_0.pth +3 -0
  21. late/adamw-lr1e-5/checkpoint-3126/rng_state_1.pth +3 -0
  22. late/adamw-lr1e-5/checkpoint-3126/rng_state_2.pth +3 -0
  23. late/adamw-lr1e-5/checkpoint-3126/rng_state_3.pth +3 -0
  24. late/adamw-lr1e-5/checkpoint-3126/scheduler.pt +3 -0
  25. late/adamw-lr1e-5/checkpoint-3126/training_args.bin +3 -0
  26. late/adamw-lr1e-5/checkpoint-3907/rng_state_0.pth +3 -0
  27. late/adamw-lr1e-5/checkpoint-3907/rng_state_1.pth +3 -0
  28. late/adamw-lr1e-5/checkpoint-3907/rng_state_2.pth +3 -0
  29. late/adamw-lr1e-5/checkpoint-3907/rng_state_3.pth +3 -0
  30. late/adamw-lr1e-5/checkpoint-3907/scheduler.pt +3 -0
  31. late/adamw-lr1e-5/checkpoint-3907/training_args.bin +3 -0
  32. late/adamw-lr1e-5/checkpoint-782/1_Dense/model.safetensors +3 -0
  33. late/adamw-lr1e-5/checkpoint-782/2_Dense/model.safetensors +3 -0
  34. late/adamw-lr1e-5/checkpoint-782/3_Dense/model.safetensors +3 -0
  35. late/adamw-lr1e-5/checkpoint-782/model.safetensors +3 -0
  36. late/adamw-lr1e-5/checkpoint-782/rng_state_0.pth +3 -0
  37. late/adamw-lr1e-5/checkpoint-782/rng_state_1.pth +3 -0
  38. late/adamw-lr1e-5/checkpoint-782/rng_state_2.pth +3 -0
  39. late/adamw-lr1e-5/checkpoint-782/rng_state_3.pth +3 -0
  40. late/adamw-lr1e-5/checkpoint-782/scheduler.pt +3 -0
  41. late/adamw-lr1e-5/checkpoint-782/training_args.bin +3 -0
  42. late/adamw-lr1e-5/final/training_args.bin +3 -0
  43. late/muon-lr1e-4/checkpoint-1563/1_Dense/model.safetensors +3 -0
  44. late/muon-lr1e-4/checkpoint-1563/2_Dense/model.safetensors +3 -0
  45. late/muon-lr1e-4/checkpoint-1563/3_Dense/model.safetensors +3 -0
  46. late/muon-lr1e-4/checkpoint-1563/model.safetensors +3 -0
  47. late/muon-lr1e-4/checkpoint-1563/optimizer.pt +3 -0
  48. late/muon-lr1e-4/checkpoint-1563/rng_state_0.pth +3 -0
  49. late/muon-lr1e-4/checkpoint-1563/rng_state_1.pth +3 -0
  50. late/muon-lr1e-4/checkpoint-1563/rng_state_2.pth +3 -0
late/adamw-lr1e-5/checkpoint-1563/1_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dca8b1bc111b21a7d1ce9fe143aa12a4b4ffe77eb6bf2ac2d3fff1273c97b15
3
+ size 9437360
late/adamw-lr1e-5/checkpoint-1563/2_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db9fae26e09e0c531089eb71cb9ac61c5e0e685d40321fb7b47c2eeb33d10619
3
+ size 9437360
late/adamw-lr1e-5/checkpoint-1563/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffacfe054427b76f0848f74221ee27f82b0e579e2453899b29943d6fcd6f44f5
3
+ size 596076280
late/adamw-lr1e-5/checkpoint-1563/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659b1cdee2219458dd84ce6a632a595465680b8080e5c44bd600ff97eca8d752
3
+ size 15429
late/adamw-lr1e-5/checkpoint-1563/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
3
+ size 15429
late/adamw-lr1e-5/checkpoint-1563/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
3
+ size 15429
late/adamw-lr1e-5/checkpoint-1563/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
3
+ size 15429
late/adamw-lr1e-5/checkpoint-1563/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af413698366f79298aabb4c94c7e3fc93d30abe0d0ec47db82792d3b9401202
3
+ size 1465
late/adamw-lr1e-5/checkpoint-1563/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a45d88c064a8db979a3b9de116a2f148b8ebde1374dcd07cc27cae1e683786
3
+ size 5585
late/adamw-lr1e-5/checkpoint-2345/1_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:092640c253e1ea92f1d3437a7dc0fe961af7381441b128054b9cbc8f8d3aa713
3
+ size 9437360
late/adamw-lr1e-5/checkpoint-2345/2_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bdec6ac6da0f95e1496eed5da79481656220c0f3f515c5ecacfc88e49a33c2d
3
+ size 9437360
late/adamw-lr1e-5/checkpoint-2345/3_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b60006ac4eec2161b3d58b6ee792499dd80bf2c22fad3a736621f406049496
3
+ size 393304
late/adamw-lr1e-5/checkpoint-2345/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b8cab13c2a8f704be436eda2d1426a72779cd9e4023652961ccf413b907a65
3
+ size 596076280
late/adamw-lr1e-5/checkpoint-2345/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659b1cdee2219458dd84ce6a632a595465680b8080e5c44bd600ff97eca8d752
3
+ size 15429
late/adamw-lr1e-5/checkpoint-2345/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
3
+ size 15429
late/adamw-lr1e-5/checkpoint-2345/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
3
+ size 15429
late/adamw-lr1e-5/checkpoint-2345/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
3
+ size 15429
late/adamw-lr1e-5/checkpoint-2345/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ac461e90cf57a28f5f63a7b3257ef090f6f8b574e2861dbfcfe40faa813548
3
+ size 1465
late/adamw-lr1e-5/checkpoint-2345/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a45d88c064a8db979a3b9de116a2f148b8ebde1374dcd07cc27cae1e683786
3
+ size 5585
late/adamw-lr1e-5/checkpoint-3126/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659b1cdee2219458dd84ce6a632a595465680b8080e5c44bd600ff97eca8d752
3
+ size 15429
late/adamw-lr1e-5/checkpoint-3126/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
3
+ size 15429
late/adamw-lr1e-5/checkpoint-3126/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
3
+ size 15429
late/adamw-lr1e-5/checkpoint-3126/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
3
+ size 15429
late/adamw-lr1e-5/checkpoint-3126/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c754b6fa10962e30720506300187a492fe4b2c7ab00bf88266a6cdcc3f409967
3
+ size 1465
late/adamw-lr1e-5/checkpoint-3126/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a45d88c064a8db979a3b9de116a2f148b8ebde1374dcd07cc27cae1e683786
3
+ size 5585
late/adamw-lr1e-5/checkpoint-3907/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659b1cdee2219458dd84ce6a632a595465680b8080e5c44bd600ff97eca8d752
3
+ size 15429
late/adamw-lr1e-5/checkpoint-3907/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
3
+ size 15429
late/adamw-lr1e-5/checkpoint-3907/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
3
+ size 15429
late/adamw-lr1e-5/checkpoint-3907/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
3
+ size 15429
late/adamw-lr1e-5/checkpoint-3907/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12a3d5696ed93ceeef2a45ae6b28d3cb646399484d4f361ef2729ec51b57538
3
+ size 1465
late/adamw-lr1e-5/checkpoint-3907/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a45d88c064a8db979a3b9de116a2f148b8ebde1374dcd07cc27cae1e683786
3
+ size 5585
late/adamw-lr1e-5/checkpoint-782/1_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a9afec4f2642afd4ef901f0713f30b786819726de4cfc1b59fc1367ea3b4bd
3
+ size 9437360
late/adamw-lr1e-5/checkpoint-782/2_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0116b8d1795986be6b86c55e72a5932627c9ec46017f10c3f012538941605d73
3
+ size 9437360
late/adamw-lr1e-5/checkpoint-782/3_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d31eb333f84f524181b0acf07d05b8b470ebda6ed3fe11d3ba20af67c29ccf
3
+ size 393304
late/adamw-lr1e-5/checkpoint-782/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb7927097f3952772adff2a2b6d9bc722b04c64c3e08fed1c509aaedeb12ce49
3
+ size 596076280
late/adamw-lr1e-5/checkpoint-782/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659b1cdee2219458dd84ce6a632a595465680b8080e5c44bd600ff97eca8d752
3
+ size 15429
late/adamw-lr1e-5/checkpoint-782/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
3
+ size 15429
late/adamw-lr1e-5/checkpoint-782/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
3
+ size 15429
late/adamw-lr1e-5/checkpoint-782/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
3
+ size 15429
late/adamw-lr1e-5/checkpoint-782/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea37e26b25c2e44b7d75d5778b0342df8216a633d012a0bf6d6065adba28ec57
3
+ size 1465
late/adamw-lr1e-5/checkpoint-782/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a45d88c064a8db979a3b9de116a2f148b8ebde1374dcd07cc27cae1e683786
3
+ size 5585
late/adamw-lr1e-5/final/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a45d88c064a8db979a3b9de116a2f148b8ebde1374dcd07cc27cae1e683786
3
+ size 5585
late/muon-lr1e-4/checkpoint-1563/1_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6a4d4cc09c01d997fec21a567394d6469b9bc5b03fc3036a3b922ca93174fc2
3
+ size 9437360
late/muon-lr1e-4/checkpoint-1563/2_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5455c06c49f5e6f4b0929a87afd0c9e48701c1bef0565491ca2dd1576ebf7f4
3
+ size 9437360
late/muon-lr1e-4/checkpoint-1563/3_Dense/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e941009fb4e51be273035ece1c7fa72749f0d98610291c8c80d4c4e6c4da388e
3
+ size 393304
late/muon-lr1e-4/checkpoint-1563/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcebcc154fc8b52bcd9852313c9069a0f6210758338fee403b5623e18054a385
3
+ size 596076280
late/muon-lr1e-4/checkpoint-1563/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:102b0fe29247d963b15bf85eac35e4d9c7559a73776eccb9e67297e8b274b3ac
3
+ size 789544331
late/muon-lr1e-4/checkpoint-1563/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f91f87bd9a92e8739289f46162ef308559319763234c64c5b77db9ec569f87f
3
+ size 15429
late/muon-lr1e-4/checkpoint-1563/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7d39b8b541e3fd455fdaac992f8e531a8b6ecbd342d84bd34ce103caf8c4829
3
+ size 15429
late/muon-lr1e-4/checkpoint-1563/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff092a382271ec0416bca1eaebe1589a5c027148f661f515a99be89a41550e9
3
+ size 15429