jyliuAI commited on
Commit
7b229bc
·
verified ·
1 Parent(s): 33df9bc

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. .gitattributes +64 -0
  2. checkpoints/official/fmlm/lm1b/model.safetensors +3 -0
  3. checkpoints/reference_reproduction/_invalid/old_di4c_shape_skip_20260825_095622/duo_di4c_lm1b/inputs/teacher_adapted.ckpt +3 -0
  4. checkpoints/reference_reproduction/_invalid/old_di4c_shape_skip_20260825_095622/mdlm_di4c_lm1b/inputs/teacher_adapted.ckpt +3 -0
  5. checkpoints/reference_reproduction/duo_di4c/lm1b.failed-20260820-172600/inputs/teacher_adapted.ckpt +3 -0
  6. checkpoints/reference_reproduction/duo_di4c/lm1b.interrupted-20260820-174308/inputs/teacher_adapted.ckpt +3 -0
  7. checkpoints/reference_reproduction/duo_di4c/lm1b/checkpoints/0-10000.ckpt +3 -0
  8. checkpoints/reference_reproduction/duo_di4c/lm1b/checkpoints/0-20000.ckpt +3 -0
  9. checkpoints/reference_reproduction/duo_di4c/lm1b/checkpoints/last.ckpt +3 -0
  10. checkpoints/reference_reproduction/duo_di4c/lm1b/inputs/teacher_adapted.ckpt +3 -0
  11. checkpoints/reference_reproduction/duo_di4c/lm1b/student_checkpoints/20000.ckpt +3 -0
  12. checkpoints/reference_reproduction/mdlm_di4c/lm1b.failed-20260820-172600/inputs/teacher_adapted.ckpt +3 -0
  13. checkpoints/reference_reproduction/mdlm_di4c/lm1b/checkpoints/0-10000.ckpt +3 -0
  14. checkpoints/reference_reproduction/mdlm_di4c/lm1b/checkpoints/0-20000.ckpt +3 -0
  15. checkpoints/reference_reproduction/mdlm_di4c/lm1b/checkpoints/last.ckpt +3 -0
  16. checkpoints/reference_reproduction/mdlm_di4c/lm1b/inputs/teacher_adapted.ckpt +3 -0
  17. checkpoints/reference_reproduction/mdlm_di4c/lm1b/student_checkpoints/20000.ckpt +3 -0
  18. checkpoints/reference_reproduction/mdlm_sdtt/lm1b.failed_20260805_105838/inputs/teacher_adapted.ckpt +3 -0
  19. checkpoints/reference_reproduction/mdlm_sdtt/lm1b/inputs/teacher_adapted.ckpt +3 -0
  20. data/elf/snapshots/t5/df1b051c49625cf57a3d0d8d3863ed4d13564fe4/spiece.model +3 -0
  21. data/elf/snapshots/wmt14-official-validation/bcc92bda4b07c329354843724c9d9ea740f30685/data-00000-of-00001.arrow +3 -0
  22. data/elf/snapshots/wmt14-raw/b199e406369ec1b7634206d3ded5ba45de2fe696/de-en/test-00000-of-00001.parquet +3 -0
  23. data/elf/snapshots/wmt14-raw/b199e406369ec1b7634206d3ded5ba45de2fe696/de-en/validation-00000-of-00001.parquet +3 -0
  24. data/elf/snapshots/xsum-official-validation/b0b4f5de92434d308eceeb9e38fd3f8d7d2b6a9e/data-00000-of-00001.arrow +3 -0
  25. data/elf/snapshots/xsum-raw/7d4d486c2f8ef850b1a11aead99b894ff3dd7da9/data/test-00000-of-00001.parquet +3 -0
  26. data/elf/snapshots/xsum-raw/7d4d486c2f8ef850b1a11aead99b894ff3dd7da9/data/validation-00000-of-00001.parquet +3 -0
  27. data/elf/xsum-official-validation.jsonl +3 -0
  28. data/elf/xsum-test.jsonl +3 -0
  29. data/elf/xsum-validation.jsonl +3 -0
  30. data/processed/.builder-cache/lm1b/train/generator/default-3a58fdf789a93b0f/0.0.0/generator-train-00001-of-00004.arrow +3 -0
  31. data/processed/.builder-cache/lm1b/train/generator/default-3a58fdf789a93b0f/0.0.0/generator-train-00003-of-00004.arrow +3 -0
  32. data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00005-of-00036.arrow +3 -0
  33. data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00015-of-00036.arrow +3 -0
  34. data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00019-of-00036.arrow +3 -0
  35. data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00027-of-00036.arrow +3 -0
  36. data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00028-of-00036.arrow +3 -0
  37. data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00035-of-00036.arrow +3 -0
  38. data/processed/lm1b-bert-128/train/data-00003-of-00004.arrow +3 -0
  39. data/processed/owt-gpt2-1024/train/data-00002-of-00036.arrow +3 -0
  40. data/processed/owt-gpt2-1024/train/data-00005-of-00036.arrow +3 -0
  41. data/processed/owt-gpt2-1024/train/data-00007-of-00036.arrow +3 -0
  42. data/processed/owt-gpt2-1024/train/data-00013-of-00036.arrow +3 -0
  43. data/processed/owt-gpt2-1024/train/data-00017-of-00036.arrow +3 -0
  44. data/processed/owt-gpt2-1024/train/data-00019-of-00036.arrow +3 -0
  45. data/processed/owt-gpt2-1024/train/data-00021-of-00036.arrow +3 -0
  46. data/processed/owt-gpt2-1024/train/data-00025-of-00036.arrow +3 -0
  47. data/processed/owt-gpt2-1024/train/data-00027-of-00036.arrow +3 -0
  48. data/processed/owt-gpt2-1024/train/data-00028-of-00036.arrow +3 -0
  49. data/processed/owt-gpt2-1024/train/data-00033-of-00036.arrow +3 -0
  50. data/processed/owt-gpt2-1024/train/data-00035-of-00036.arrow +3 -0
.gitattributes CHANGED
@@ -61,3 +61,67 @@ data/raw/huggingface/hub/models--gpt2-large/blobs/71e91ce5f1120392f874e9dd6037c6
61
  data/raw/huggingface/hub/models--gpt2-large/blobs/4da5e3c0a8b10f3fecb775a1c312814d7f0b08699ca08b14f820801caf9ca42f filter=lfs diff=lfs merge=lfs -text
62
  data/elf/snapshots/wmt14/93ce98315a2dec985cdefb8d8e62ab618e896ec4/checkpoint_880600 filter=lfs diff=lfs merge=lfs -text
63
  data/raw/huggingface/hub/models--bert-base-uncased/blobs/ea201fabe466ef7182f1f687fb5be4b62a73d3a78883f11264ff7f682cdb54bf filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  data/raw/huggingface/hub/models--gpt2-large/blobs/4da5e3c0a8b10f3fecb775a1c312814d7f0b08699ca08b14f820801caf9ca42f filter=lfs diff=lfs merge=lfs -text
62
  data/elf/snapshots/wmt14/93ce98315a2dec985cdefb8d8e62ab618e896ec4/checkpoint_880600 filter=lfs diff=lfs merge=lfs -text
63
  data/raw/huggingface/hub/models--bert-base-uncased/blobs/ea201fabe466ef7182f1f687fb5be4b62a73d3a78883f11264ff7f682cdb54bf filter=lfs diff=lfs merge=lfs -text
64
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/9cfc6fdfe60508ae027c9816925849f61e3770ae01da93dc5940799b8c78c37c filter=lfs diff=lfs merge=lfs -text
65
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/4c47ce303bcc0fd023de934193d13087e14dad0ba481cbf152c49ed0ce839b4f filter=lfs diff=lfs merge=lfs -text
66
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/7d0023cbdbd8269228d5ebd5d246c1fb8412de416e0ed78828395a65617e2f8f filter=lfs diff=lfs merge=lfs -text
67
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/704224e42e9456ecdde537c3b0b99d06dfc9bafeb7692af1c1cc7d71c861f0a6 filter=lfs diff=lfs merge=lfs -text
68
+ data/raw/huggingface/hub/datasets--billion-word-benchmark--lm1b/blobs/64f47e426cdb51fc5224d4215c1ef0eb77ea7fbe6f5381872da8644da5ce2316 filter=lfs diff=lfs merge=lfs -text
69
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/5df2fa1d916f4e694459883427118fc55128556b1c11104232f21939cc39f1d5 filter=lfs diff=lfs merge=lfs -text
70
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/9966d1e626d50f2887c4278a767b7e8ad58ba3f1c5762122fa21546f02022db9 filter=lfs diff=lfs merge=lfs -text
71
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/52c0b7a307c640c3462dfb4e426b0a70ff6414201a311678e62048961f057972 filter=lfs diff=lfs merge=lfs -text
72
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/04fdda74e280da50f9b5b964cabf6c38ff6731262d5f46082e17c258c425a70d filter=lfs diff=lfs merge=lfs -text
73
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/0c8bd91a2f7430c427f92858ff9cb7102cf3a29105f7c7e189b3e8aeddb7559f filter=lfs diff=lfs merge=lfs -text
74
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/a5def3ac614d54e3635405f00e69b2f102fcd834ffeda5aa1075fef2b606f937 filter=lfs diff=lfs merge=lfs -text
75
+ data/raw/huggingface/xet/logs/xet_20260801T234209568+0800_140160.log filter=lfs diff=lfs merge=lfs -text
76
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/c1b4e8f48e90b1fcf0f217a0219a295c955198675ee63dbf60168318e2f1b3c5 filter=lfs diff=lfs merge=lfs -text
77
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/80f15bb3dc64287827248d2a7a999ec986ecf15f07a79ed8c2e2b366e8046ae2 filter=lfs diff=lfs merge=lfs -text
78
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/8fe82ccc4e0416eeb7c200fef05aaecd90dff3558bfe1edf1fc2e5f0c131e83b filter=lfs diff=lfs merge=lfs -text
79
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/7e39ac5eeaba27261f9d9a982f4fde5c7644a5ed78c84f52692d52940b82dd7f filter=lfs diff=lfs merge=lfs -text
80
+ data/elf/xsum-test.jsonl filter=lfs diff=lfs merge=lfs -text
81
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/be17a4d0d9857b36ea4b6ae443ef97d0a0c9070b5141874d5edfaebb2418697d filter=lfs diff=lfs merge=lfs -text
82
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/74ad93e145256407598680cff83f2d253d9d805c4d25af3de83be53eb5f00472 filter=lfs diff=lfs merge=lfs -text
83
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/9a1d38ef640bb226056ac37fbb578ce2a6bb716bc05c33915dad84f72c51e2bf filter=lfs diff=lfs merge=lfs -text
84
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/56c815d2c34b3bdf9ae729896222a0cdfa62a7adbf2f85e8f7bb0a129353dc05 filter=lfs diff=lfs merge=lfs -text
85
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/699a4f4fc791d4ba9e6487ca91b63faa59a831cd5975aeaf8260451af9bb432f filter=lfs diff=lfs merge=lfs -text
86
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/7b3cef26e2d4e2b041e6e13a0102cb4d03277e8c6418b8ff1b865544a4695de3 filter=lfs diff=lfs merge=lfs -text
87
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/0d02a67f73464d383c8df2059f27b36b4b1652c855051be3c65930baef12bd2d filter=lfs diff=lfs merge=lfs -text
88
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/570ad87929c5449efba8db1137b6efddd73499049b97058b4d06b34b3c3b1304 filter=lfs diff=lfs merge=lfs -text
89
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/3e64db103898d8e5bf2225c206576758d426770b735ec35787017d45bbc94384 filter=lfs diff=lfs merge=lfs -text
90
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/8262d2586ef6af6f2319e83463521bf278dc4e15714b4d8664da0a381f0fc170 filter=lfs diff=lfs merge=lfs -text
91
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/3e3acca2f8f0b37b47ac0ddbb762e37f9223aadc4e91957366560aba79741fc3 filter=lfs diff=lfs merge=lfs -text
92
+ data/raw/huggingface/hub/datasets--billion-word-benchmark--lm1b/blobs/dcee53f0569a09ddee8d0e89b8f21aed0f0c2e29dee371ddcb11448717ff622e filter=lfs diff=lfs merge=lfs -text
93
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/abe14dcdfabde5e47472e138a26e89cd8e16ffac5e1d0b9066bd062e32cdbfea filter=lfs diff=lfs merge=lfs -text
94
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/2d3200a936b021c9abafdda6714e4d678387e8854e56abaac5d2b62882fc6044 filter=lfs diff=lfs merge=lfs -text
95
+ data/elf/xsum-validation.jsonl filter=lfs diff=lfs merge=lfs -text
96
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/099428a47b200b9d7e1bcad9334e8b3973de51b001f941cafde4cb097720b0d6 filter=lfs diff=lfs merge=lfs -text
97
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/f4e524295f0b9c63c1a066a690dac01b848b221471a84324c105d9b14b4fee80 filter=lfs diff=lfs merge=lfs -text
98
+ data/elf/xsum-official-validation.jsonl filter=lfs diff=lfs merge=lfs -text
99
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/3dbdb282711d4be26bbf4b3c5b397978a591769c287b6e0e6bcbee04482688e4 filter=lfs diff=lfs merge=lfs -text
100
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/94bfc490d98194371ce2df2b2a00e20aa6eec03f463aad09bd7e92e08cbf7ad8 filter=lfs diff=lfs merge=lfs -text
101
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/c4a698160ec63abf8c622177547535c91a6d45fefa540640482cb4bca5279ba2 filter=lfs diff=lfs merge=lfs -text
102
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/e1c54ab75be2c5ca6ed81313eade1615c478cbb2236cf0ddc86b29a3ac93fec1 filter=lfs diff=lfs merge=lfs -text
103
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/4043c16aca1e799d84169967e2a6b97d94a8c63a5636ed507a10c20a5a90f29a filter=lfs diff=lfs merge=lfs -text
104
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/76c0b96ce0250c3a32f2e8878172a4b79ac7970fede78edfcfc4d98d87ec5a6c filter=lfs diff=lfs merge=lfs -text
105
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/ec00afd59aa61c57f5fd2443bf8ab85badc4d96c346f54c017b387a2e339cf9e filter=lfs diff=lfs merge=lfs -text
106
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/3ab8f7271cb6e0c70e9353509d11438db2e2909e9a18a250bd0aeb296e786037 filter=lfs diff=lfs merge=lfs -text
107
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/671c9821a9543e1c6e88fa9833254cf4b635f333f2119c312428164f5a8015e5 filter=lfs diff=lfs merge=lfs -text
108
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/914b32dce0bbcaee7bb7d60558ce1e0b160b3de4a9c6e8d08d4161508764d56e filter=lfs diff=lfs merge=lfs -text
109
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/536acb55a30b72fdcd9553683c2682cd8f2e81bab1d59c9935789b923c11b5ae filter=lfs diff=lfs merge=lfs -text
110
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/2d3fba20b1fd0e5862f26d00633fd67156ff79776085780153feaa046119d19d filter=lfs diff=lfs merge=lfs -text
111
+ data/raw/huggingface/hub/datasets--billion-word-benchmark--lm1b/blobs/dee7ba04d5de30b43fe19f3f550734ae1569eead2d7fa191bf6df7e1ca1925b9 filter=lfs diff=lfs merge=lfs -text
112
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/d9f9d69343dde098d2eaa287e7c2d29bb25876dba7c8d8ae237d282fbcee0ccf filter=lfs diff=lfs merge=lfs -text
113
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/c34b7d448fd193eb2d9c8a6fbe4f775ef6cb65b4510b778007c8151a26b7f5a6 filter=lfs diff=lfs merge=lfs -text
114
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/009c4a7d2429deec0053787aa3f8f769c3248ebd6d5d53d496c99ac7235c403d filter=lfs diff=lfs merge=lfs -text
115
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/000ed7e725b5f188089dab955095a4f6ad3add69ed34c19df6856e896faea742 filter=lfs diff=lfs merge=lfs -text
116
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/b10d1896ca8fec37e98777f2f09fefb81c32636e7ece41d993fde31042d91be9 filter=lfs diff=lfs merge=lfs -text
117
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/9d738ba5d171bb2a0b28179f9a5335411c9846140086c4a1f170fb1fd0d86d12 filter=lfs diff=lfs merge=lfs -text
118
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/8725d264e78e56ca83a5c5bce604a31a564be7bae5a8d3c169749398cde1c4b9 filter=lfs diff=lfs merge=lfs -text
119
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/a4e81d0c4c28b3676563a04f0295fa0605d85de6822ac6ad130b19f35f74f9d8 filter=lfs diff=lfs merge=lfs -text
120
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/211136c34a2a036d4d3f22cb28b63677a412305a9803c00a9c0fa2b84a6e4592 filter=lfs diff=lfs merge=lfs -text
121
+ data/raw/huggingface/hub/datasets--billion-word-benchmark--lm1b/blobs/97fab3d8b9bc5b9f6098176fa95904a29bc05b8b6faa2ac02dbf4d43aa62640f filter=lfs diff=lfs merge=lfs -text
122
+ data/raw/huggingface/hub/datasets--billion-word-benchmark--lm1b/blobs/061ac22ad134866a72207670ed6f9707b96ddf684574b2554137140d261c6362 filter=lfs diff=lfs merge=lfs -text
123
+ data/raw/huggingface/hub/datasets--billion-word-benchmark--lm1b/blobs/50c84a090b0ed80c4f0adabdee9a7972918f8f0fe9e8f7a59bee776c0789b0a0 filter=lfs diff=lfs merge=lfs -text
124
+ data/raw/huggingface/hub/datasets--billion-word-benchmark--lm1b/blobs/f651b99a5bd73ef59c66bd76d246484d41d0b9b6ae61b8789931e0efde1d0d85 filter=lfs diff=lfs merge=lfs -text
125
+ data/raw/huggingface/hub/datasets--Skylion007--openwebtext/blobs/c5e950cdeb9a958580aa279dacd44a9a45507c8777a9105c89d0d605f8f01e11 filter=lfs diff=lfs merge=lfs -text
126
+ data/raw/huggingface/hub/models--bert-base-uncased/blobs/097417381d6c7230bd9e3557456d726de6e83245ec8b24f529f60198a67b203a filter=lfs diff=lfs merge=lfs -text
127
+ data/raw/huggingface/hub/datasets--billion-word-benchmark--lm1b/blobs/296845a45e5173422780b8b0ae845dc308ee3d98d3fd94228edf9a5ea8090374 filter=lfs diff=lfs merge=lfs -text
checkpoints/official/fmlm/lm1b/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574e5001d8ee6523b1b363cbd7055a3e3fe6d6f8dd7f796c4582548b9c728942
3
+ size 557382616
checkpoints/reference_reproduction/_invalid/old_di4c_shape_skip_20260825_095622/duo_di4c_lm1b/inputs/teacher_adapted.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff0a11c7218761bb6d266b61a352aff9d4cee72a2641ee7f987e03bb9624c5f
3
+ size 557220742
checkpoints/reference_reproduction/_invalid/old_di4c_shape_skip_20260825_095622/mdlm_di4c_lm1b/inputs/teacher_adapted.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e97e6db6a0fbe5ab0f7a86d1e6990664303755ca6eb60a0c7976ee88e78a3ec
3
+ size 557220742
checkpoints/reference_reproduction/duo_di4c/lm1b.failed-20260820-172600/inputs/teacher_adapted.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d076854b67c3e483e326887e1a05f6495bd2c0c1e342dfb43f2ef8615c194c2e
3
+ size 557220742
checkpoints/reference_reproduction/duo_di4c/lm1b.interrupted-20260820-174308/inputs/teacher_adapted.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ea78ad3a2ea64c0ceb8039818197fbf62656808168ff43d954c9a7d2be2d7d
3
+ size 557220742
checkpoints/reference_reproduction/duo_di4c/lm1b/checkpoints/0-10000.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a1c20895ab664320a26c54b2052445ee6423ce6af2e4b3ffb283e09092c9d5
3
+ size 1309944970
checkpoints/reference_reproduction/duo_di4c/lm1b/checkpoints/0-20000.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212c0ee4ad726089dc72b947dc6c0cd852469ddfcc5cb5dea8794d19db2644b5
3
+ size 1309945034
checkpoints/reference_reproduction/duo_di4c/lm1b/checkpoints/last.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212c0ee4ad726089dc72b947dc6c0cd852469ddfcc5cb5dea8794d19db2644b5
3
+ size 1309945034
checkpoints/reference_reproduction/duo_di4c/lm1b/inputs/teacher_adapted.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9300e7045c4f07c5c9acfec5335ebd54e7790691d07d1eb73751ec8aeefdc5b5
3
+ size 557220607
checkpoints/reference_reproduction/duo_di4c/lm1b/student_checkpoints/20000.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212c0ee4ad726089dc72b947dc6c0cd852469ddfcc5cb5dea8794d19db2644b5
3
+ size 1309945034
checkpoints/reference_reproduction/mdlm_di4c/lm1b.failed-20260820-172600/inputs/teacher_adapted.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d722e4f26cc2601dd15dab79c7e8587b11400773895dcf8f606e1edeac60c9
3
+ size 557220742
checkpoints/reference_reproduction/mdlm_di4c/lm1b/checkpoints/0-10000.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d8ef1f8523b2115a3d762c205b1265a05f42d3b0892ebb8e603bef2ab47e05
3
+ size 1309944970
checkpoints/reference_reproduction/mdlm_di4c/lm1b/checkpoints/0-20000.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12789637e04df039d9a3f69471ac94b9dff5100621c8f5c22fef8f04714ccd27
3
+ size 1309945034
checkpoints/reference_reproduction/mdlm_di4c/lm1b/checkpoints/last.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12789637e04df039d9a3f69471ac94b9dff5100621c8f5c22fef8f04714ccd27
3
+ size 1309945034
checkpoints/reference_reproduction/mdlm_di4c/lm1b/inputs/teacher_adapted.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aed298ee4d84bee1a0348cef8edab79364aedadd9cdc623b1a0470c6f6f6c5c
3
+ size 557220607
checkpoints/reference_reproduction/mdlm_di4c/lm1b/student_checkpoints/20000.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12789637e04df039d9a3f69471ac94b9dff5100621c8f5c22fef8f04714ccd27
3
+ size 1309945034
checkpoints/reference_reproduction/mdlm_sdtt/lm1b.failed_20260805_105838/inputs/teacher_adapted.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3250f8fb70e3dd999e56679a593328505d173537149765f601b76320dfc2013e
3
+ size 557220742
checkpoints/reference_reproduction/mdlm_sdtt/lm1b/inputs/teacher_adapted.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c993bc94927eb2e676d166324258f5dbffa84234da0d2eb88ed1aaf731fbb3
3
+ size 557220742
data/elf/snapshots/t5/df1b051c49625cf57a3d0d8d3863ed4d13564fe4/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
data/elf/snapshots/wmt14-official-validation/bcc92bda4b07c329354843724c9d9ea740f30685/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd26e8d20fb89d70283450ecda1635fb832f9cb42b713b1ac9c491f464cbd1e
3
+ size 1985240
data/elf/snapshots/wmt14-raw/b199e406369ec1b7634206d3ded5ba45de2fe696/de-en/test-00000-of-00001.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3baab716f14f8abfa63e54995e31f035bb78b20c7943de72f3e1110b7ff35bb
3
+ size 508753
data/elf/snapshots/wmt14-raw/b199e406369ec1b7634206d3ded5ba45de2fe696/de-en/validation-00000-of-00001.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a2a0e3b3e472f97f4eceb6d06724571f5390ac705768a02c1a9ad5c3d675ea
3
+ size 473798
data/elf/snapshots/xsum-official-validation/b0b4f5de92434d308eceeb9e38fd3f8d7d2b6a9e/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375d55bc9d0872ff172e0f5cff4e8bd1757fb61efd8a1c0d94c05713bdd901d8
3
+ size 74746048
data/elf/snapshots/xsum-raw/7d4d486c2f8ef850b1a11aead99b894ff3dd7da9/data/test-00000-of-00001.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:224e9dbc6fed987759c1954603b43cb280b8d475d78893779130aa707d967ed7
3
+ size 16731226
data/elf/snapshots/xsum-raw/7d4d486c2f8ef850b1a11aead99b894ff3dd7da9/data/validation-00000-of-00001.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7fc808c2dd3d1340349481aeef489e6eb8c22ff5739d8bce6d0f99e5ef8044d
3
+ size 16447668
data/elf/xsum-official-validation.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8086fbc2f0643bef8beb527007eb50de8b6e27a4cbc8b09e7bdd1bcc563ea049
3
+ size 55037360
data/elf/xsum-test.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0c5775bd72675bda7f1e7b42c929735265fd6f10e3140287211acb36468bc6
3
+ size 27278797
data/elf/xsum-validation.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d21431c1df775e0f5585f509fa5d412b64e43b7a04db08e8f458c301c110ed
3
+ size 26810179
data/processed/.builder-cache/lm1b/train/generator/default-3a58fdf789a93b0f/0.0.0/generator-train-00001-of-00004.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38124f7d15786ae115a2a07289f0f62790c569d6286ef225a6773c412694135
3
+ size 500568272
data/processed/.builder-cache/lm1b/train/generator/default-3a58fdf789a93b0f/0.0.0/generator-train-00003-of-00004.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0817f3145052a2d85e489a9bbcd258c2db6263b90c8e9268f4d63134f99c110
3
+ size 317877408
data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00005-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ac0e207db435a87aa4e6d77c148881d56844c487881a9fb383a67ab2ecad59
3
+ size 501803488
data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00015-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2c6e32e1622e3bd1ed2821b14d3db2cdd9383ca609ba06e5603d9f86dca7c3
3
+ size 501803488
data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00019-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf17d0dfb2087b7331987cd1a64f4d4de58cc9f8021334cf2a373336059f1ac
3
+ size 501803488
data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00027-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889e49b7cf23fda1a0b51b75e7fb6c01dd4f508d1e92a1d94d88cc99df1a371a
3
+ size 501803488
data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00028-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca23b2d092cc3ac6f1802f4ecea88fdb1c4d1a626729500f661400269ed6a9c
3
+ size 501803488
data/processed/.builder-cache/owt/train/generator/default-b8b56016fa13f36d/0.0.0/generator-train-00035-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfabef99b5488970378eb1416db581f613733a087d523b3742c719c8716b4282
3
+ size 327497584
data/processed/lm1b-bert-128/train/data-00003-of-00004.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2272f8e8d83a5189d0a2d39e0010949f2b7914aae4f9e5cb2316f392fc699e56
3
+ size 454895472
data/processed/owt-gpt2-1024/train/data-00002-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9979a451c3ea761665a9c705fee27e108fa7c0644f9778c7f9df959cc50b9d0c
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00005-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc2b617bf418c871105f1d6ad248aa7828b51f8a3c47676a7e63d2a33a12895
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00007-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:611562e240dda9bf31f596fa34e6e44fe3edb3c52011514ad3fb8b647dcc010f
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00013-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124d2f2d567251e6cfc30280c19e45542402fd437b7f27b3f6434926b2ead2c8
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00017-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b117094ee89d8812b7513b7fb35fa468ffcfe8ded4f231f2b98024e8fe39e93
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00019-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b3a9276caa65ec5ce955fdaf42151b8ba626887281d69d54c1750baae4fddeb
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00021-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63cf9f35df6a254e3981745d6b5d6f76a6aeffa1ffe41eb100812329fac4a53e
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00025-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8e5868f4c9e0aac16d5a5dec1dcef19e307550038e0162614deb00eca73e6a
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00027-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5434b60b31c999b94676a72875ae4424f79f094db8f06608408915638ac21758
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00028-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14ed5e57ab4dde321695484b389ec6768bf352212f39e570b93524d3f2ef86b
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00033-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c45c498a626dc0d23e20ade6f67387700eed878b3aaa3ee2c88632496ea34ff
3
+ size 496961664
data/processed/owt-gpt2-1024/train/data-00035-of-00036.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a137f7c047131f1d9d7c7cce9c821addaae68e0cee53ced766e1c3a76b21c3
3
+ size 496961664