meihant commited on
Commit
798df49
·
verified ·
1 Parent(s): 665e72e

Add datasets/FCP-20B artifacts 488-495

Browse files
datasets/FCP-20B/packing/source2b/pack_ids.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4eaddd4247a59f5f2be82fc42b33b63957ace0c5c2f751b3eb3464b9abff5a2
3
+ size 393051776
datasets/FCP-20B/packing/source2b/pack_starts.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e66804a4b7bb745ceea6669babf4e481e9c41cb0e6518ab502118433f4a860
3
+ size 97437888
datasets/FCP-20B/packing/source2b/packing_READY.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "passed": true,
3
+ "rows": 49131472,
4
+ "packs": 12179735,
5
+ "sha256": "67e66804a4b7bb745ceea6669babf4e481e9c41cb0e6518ab502118433f4a860",
6
+ "member_sha256": "b4eaddd4247a59f5f2be82fc42b33b63957ace0c5c2f751b3eb3464b9abff5a2",
7
+ "code_hashes": {
8
+ "bfd.py": "ba37e45bfe6882b7c1747bfaafbaf55611f0cdfa2971ad16cd58d88a4009640d",
9
+ "config.py": "6b617d0a45048a8851b617f29608602dc7e290166749dd1551433033c44ec214",
10
+ "encoding.py": "3aed0431713870e35595f922f22be6a4cce123877f493de5bb1f848809683ab4",
11
+ "fcp_format.py": "bef4a540107f949af0e9a2149419ea05cdc4f52385b66eaed84ef25dc40a8305",
12
+ "gate.py": "6c862bfac6e1bd38988cd161804ff9ecb16418e08a031992dfa2f1f78a99ef37",
13
+ "layout.py": "f30a8a77cb97a4bf8d33248a14bbc9112c358b0a0162255d7a77abb15f8f7e2b",
14
+ "model.py": "f0fb8a8789fbf0cd2d7033cf813fa40dc4ebf47617f1f3b70dafa419842eeb5e",
15
+ "prepare_packs.py": "9111f8372105c8381c3b46cd6f31e38ba8d0c4a2c7afde28f4b5a8215c0a813e",
16
+ "runtime.py": "628f7ab759bc4e1047e86dbe71f143fdffa54f16ed498217e7abe82c114c1f7a",
17
+ "train.py": "ea3a7991373ca107118011db93c15e3c18d8f94695909ec26d686ab228e292b3",
18
+ "upload.py": "747a9bce54eafc35b1fa14ba5aa653908bf8f81f24b5e526bce9c947b4ef3182",
19
+ "validate_data.py": "f8dec33d7fc01b54b562ede8cfb87ecbf529dd68be8b48cf9147e6bd3a9324fa",
20
+ "verify.py": "cec4349e3b7d5adcab0f4377b0416cc87b6d810c749833e7b455dbd7e9462a97",
21
+ "checkpoint_files.py": "3a4cd9b1cc858e9c48dc5c00b92a1d4e86330643d03fdb9df361c6ed85788155"
22
+ },
23
+ "algorithm": "BFD",
24
+ "buffer_records": 1000,
25
+ "global_packs_per_update": 128,
26
+ "segments": [
27
+ {
28
+ "segment": 0,
29
+ "end_row": 4898104,
30
+ "source_tokens": 2000000031,
31
+ "target_tokens": 2000000000,
32
+ "start_pack": 0,
33
+ "end_pack": 1218688
34
+ },
35
+ {
36
+ "segment": 1,
37
+ "end_row": 9802903,
38
+ "source_tokens": 4000000388,
39
+ "target_tokens": 4000000000,
40
+ "start_pack": 1218688,
41
+ "end_pack": 2437128
42
+ },
43
+ {
44
+ "segment": 2,
45
+ "end_row": 14714284,
46
+ "source_tokens": 6000000190,
47
+ "target_tokens": 6000000000,
48
+ "start_pack": 2437128,
49
+ "end_pack": 3655801
50
+ },
51
+ {
52
+ "segment": 3,
53
+ "end_row": 19637704,
54
+ "source_tokens": 8000000397,
55
+ "target_tokens": 8000000000,
56
+ "start_pack": 3655801,
57
+ "end_pack": 4874591
58
+ },
59
+ {
60
+ "segment": 4,
61
+ "end_row": 24567228,
62
+ "source_tokens": 10000000091,
63
+ "target_tokens": 10000000000,
64
+ "start_pack": 4874591,
65
+ "end_pack": 6092853
66
+ },
67
+ {
68
+ "segment": 5,
69
+ "end_row": 29489067,
70
+ "source_tokens": 12000000382,
71
+ "target_tokens": 12000000000,
72
+ "start_pack": 6092853,
73
+ "end_pack": 7310504
74
+ },
75
+ {
76
+ "segment": 6,
77
+ "end_row": 34384959,
78
+ "source_tokens": 14000000003,
79
+ "target_tokens": 14000000000,
80
+ "start_pack": 7310504,
81
+ "end_pack": 8527473
82
+ },
83
+ {
84
+ "segment": 7,
85
+ "end_row": 39291912,
86
+ "source_tokens": 16000000433,
87
+ "target_tokens": 16000000000,
88
+ "start_pack": 8527473,
89
+ "end_pack": 9745065
90
+ },
91
+ {
92
+ "segment": 8,
93
+ "end_row": 44208957,
94
+ "source_tokens": 18000000424,
95
+ "target_tokens": 18000000000,
96
+ "start_pack": 9745065,
97
+ "end_pack": 10962290
98
+ },
99
+ {
100
+ "segment": 9,
101
+ "end_row": 49131472,
102
+ "source_tokens": 20000000040,
103
+ "target_tokens": 20000000000,
104
+ "start_pack": 10962290,
105
+ "end_pack": 12179735
106
+ }
107
+ ],
108
+ "source_manifest_sha256": "3467ec6846c9a44f645a2d387ed158f5f5f8f1898e5e5945a318f829037ee6f0",
109
+ "updates": 95158
110
+ }