kacperwikiel commited on
Commit
9f4ad75
·
verified ·
1 Parent(s): 6ca817c

Update experiment measurements and status

Browse files
reports/sources/cosmopedia/manifest.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "repo": "HuggingFaceTB/smollm-corpus",
3
+ "revision": "3ba9d605774198c5868892d7a8deda78031a781f",
4
+ "files": [
5
+ "cosmopedia-v2/train-00000-of-00104.parquet",
6
+ "cosmopedia-v2/train-00001-of-00104.parquet",
7
+ "cosmopedia-v2/train-00002-of-00104.parquet",
8
+ "cosmopedia-v2/train-00003-of-00104.parquet",
9
+ "cosmopedia-v2/train-00004-of-00104.parquet",
10
+ "cosmopedia-v2/train-00005-of-00104.parquet",
11
+ "cosmopedia-v2/train-00006-of-00104.parquet",
12
+ "cosmopedia-v2/train-00007-of-00104.parquet",
13
+ "cosmopedia-v2/train-00008-of-00104.parquet",
14
+ "cosmopedia-v2/train-00009-of-00104.parquet",
15
+ "cosmopedia-v2/train-00010-of-00104.parquet",
16
+ "cosmopedia-v2/train-00011-of-00104.parquet",
17
+ "cosmopedia-v2/train-00012-of-00104.parquet",
18
+ "cosmopedia-v2/train-00013-of-00104.parquet",
19
+ "cosmopedia-v2/train-00014-of-00104.parquet",
20
+ "cosmopedia-v2/train-00015-of-00104.parquet",
21
+ "cosmopedia-v2/train-00016-of-00104.parquet",
22
+ "cosmopedia-v2/train-00017-of-00104.parquet",
23
+ "cosmopedia-v2/train-00018-of-00104.parquet",
24
+ "cosmopedia-v2/train-00019-of-00104.parquet",
25
+ "cosmopedia-v2/train-00020-of-00104.parquet",
26
+ "cosmopedia-v2/train-00021-of-00104.parquet",
27
+ "cosmopedia-v2/train-00022-of-00104.parquet",
28
+ "cosmopedia-v2/train-00023-of-00104.parquet",
29
+ "cosmopedia-v2/train-00024-of-00104.parquet",
30
+ "cosmopedia-v2/train-00025-of-00104.parquet",
31
+ "cosmopedia-v2/train-00026-of-00104.parquet",
32
+ "cosmopedia-v2/train-00027-of-00104.parquet",
33
+ "cosmopedia-v2/train-00028-of-00104.parquet",
34
+ "cosmopedia-v2/train-00029-of-00104.parquet",
35
+ "cosmopedia-v2/train-00030-of-00104.parquet",
36
+ "cosmopedia-v2/train-00031-of-00104.parquet",
37
+ "cosmopedia-v2/train-00032-of-00104.parquet",
38
+ "cosmopedia-v2/train-00033-of-00104.parquet",
39
+ "cosmopedia-v2/train-00034-of-00104.parquet",
40
+ "cosmopedia-v2/train-00035-of-00104.parquet",
41
+ "cosmopedia-v2/train-00036-of-00104.parquet",
42
+ "cosmopedia-v2/train-00037-of-00104.parquet",
43
+ "cosmopedia-v2/train-00038-of-00104.parquet",
44
+ "cosmopedia-v2/train-00039-of-00104.parquet",
45
+ "cosmopedia-v2/train-00040-of-00104.parquet",
46
+ "cosmopedia-v2/train-00041-of-00104.parquet",
47
+ "cosmopedia-v2/train-00042-of-00104.parquet",
48
+ "cosmopedia-v2/train-00043-of-00104.parquet",
49
+ "cosmopedia-v2/train-00044-of-00104.parquet",
50
+ "cosmopedia-v2/train-00045-of-00104.parquet",
51
+ "cosmopedia-v2/train-00046-of-00104.parquet",
52
+ "cosmopedia-v2/train-00047-of-00104.parquet",
53
+ "cosmopedia-v2/train-00048-of-00104.parquet",
54
+ "cosmopedia-v2/train-00049-of-00104.parquet",
55
+ "cosmopedia-v2/train-00050-of-00104.parquet",
56
+ "cosmopedia-v2/train-00051-of-00104.parquet",
57
+ "cosmopedia-v2/train-00052-of-00104.parquet",
58
+ "cosmopedia-v2/train-00053-of-00104.parquet",
59
+ "cosmopedia-v2/train-00054-of-00104.parquet",
60
+ "cosmopedia-v2/train-00055-of-00104.parquet",
61
+ "cosmopedia-v2/train-00056-of-00104.parquet",
62
+ "cosmopedia-v2/train-00057-of-00104.parquet",
63
+ "cosmopedia-v2/train-00058-of-00104.parquet",
64
+ "cosmopedia-v2/train-00059-of-00104.parquet",
65
+ "cosmopedia-v2/train-00060-of-00104.parquet",
66
+ "cosmopedia-v2/train-00061-of-00104.parquet",
67
+ "cosmopedia-v2/train-00062-of-00104.parquet",
68
+ "cosmopedia-v2/train-00063-of-00104.parquet",
69
+ "cosmopedia-v2/train-00064-of-00104.parquet",
70
+ "cosmopedia-v2/train-00065-of-00104.parquet",
71
+ "cosmopedia-v2/train-00066-of-00104.parquet",
72
+ "cosmopedia-v2/train-00067-of-00104.parquet",
73
+ "cosmopedia-v2/train-00068-of-00104.parquet",
74
+ "cosmopedia-v2/train-00069-of-00104.parquet",
75
+ "cosmopedia-v2/train-00070-of-00104.parquet",
76
+ "cosmopedia-v2/train-00071-of-00104.parquet",
77
+ "cosmopedia-v2/train-00072-of-00104.parquet",
78
+ "cosmopedia-v2/train-00073-of-00104.parquet",
79
+ "cosmopedia-v2/train-00074-of-00104.parquet",
80
+ "cosmopedia-v2/train-00075-of-00104.parquet",
81
+ "cosmopedia-v2/train-00076-of-00104.parquet",
82
+ "cosmopedia-v2/train-00077-of-00104.parquet",
83
+ "cosmopedia-v2/train-00078-of-00104.parquet",
84
+ "cosmopedia-v2/train-00079-of-00104.parquet",
85
+ "cosmopedia-v2/train-00080-of-00104.parquet",
86
+ "cosmopedia-v2/train-00081-of-00104.parquet",
87
+ "cosmopedia-v2/train-00082-of-00104.parquet",
88
+ "cosmopedia-v2/train-00083-of-00104.parquet",
89
+ "cosmopedia-v2/train-00084-of-00104.parquet",
90
+ "cosmopedia-v2/train-00085-of-00104.parquet",
91
+ "cosmopedia-v2/train-00086-of-00104.parquet",
92
+ "cosmopedia-v2/train-00087-of-00104.parquet",
93
+ "cosmopedia-v2/train-00088-of-00104.parquet",
94
+ "cosmopedia-v2/train-00089-of-00104.parquet",
95
+ "cosmopedia-v2/train-00090-of-00104.parquet",
96
+ "cosmopedia-v2/train-00091-of-00104.parquet",
97
+ "cosmopedia-v2/train-00092-of-00104.parquet",
98
+ "cosmopedia-v2/train-00093-of-00104.parquet",
99
+ "cosmopedia-v2/train-00094-of-00104.parquet",
100
+ "cosmopedia-v2/train-00095-of-00104.parquet",
101
+ "cosmopedia-v2/train-00096-of-00104.parquet",
102
+ "cosmopedia-v2/train-00097-of-00104.parquet",
103
+ "cosmopedia-v2/train-00098-of-00104.parquet",
104
+ "cosmopedia-v2/train-00099-of-00104.parquet",
105
+ "cosmopedia-v2/train-00100-of-00104.parquet",
106
+ "cosmopedia-v2/train-00101-of-00104.parquet",
107
+ "cosmopedia-v2/train-00102-of-00104.parquet",
108
+ "cosmopedia-v2/train-00103-of-00104.parquet"
109
+ ],
110
+ "license": "odc-by",
111
+ "used_files": [
112
+ {
113
+ "file": "cosmopedia-v2/train-00102-of-00104.parquet",
114
+ "sha256": "6493d76632745f86c8407593bb07724f88422a3aeace3599758f8e6fd80341f1"
115
+ }
116
+ ],
117
+ "train_tokens": 120052030,
118
+ "validation_tokens": 201183,
119
+ "accepted_documents": 139655,
120
+ "rejected_overlap": 5,
121
+ "train_sha256": "62365adb6efe7c69bf39f91d8d0291bbda094ab8220b85fbe67f8404febe67ba",
122
+ "validation_sha256": "c483db9d7c8b84b39f5a3d6de5d564200b44c3232cbf7b2d16ea672d385a7bac",
123
+ "audit": "normalized 13-word exact overlap plus full short sentences; not semantic decontamination; legacy ARC-MIX was not re-audited here"
124
+ }