tensorboy commited on
Commit
0efe1a4
·
verified ·
1 Parent(s): 85fa5a8

Upload folder using huggingface_hub

Browse files
0.codes.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f27bcf32b0e79773e066d82b6a5f4f3d34b0551104cb5d9aac90dfd020d9b1bf
3
+ size 90780
0.metadata.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "passage_offset": 0,
3
+ "num_passages": 118,
4
+ "num_embeddings": 22415,
5
+ "embedding_offset": 0
6
+ }
0.residuals.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b876452226ae62169f26c0e5dfcffef420b19b780c6632b003d8d4c8ab14d78
3
+ size 1077104
1.codes.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60e829934884274c939b41c450ab89ec4f59ae6d3b753714198b08eefd1f8282
3
+ size 79196
1.metadata.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "passage_offset": 118,
3
+ "num_passages": 116,
4
+ "num_embeddings": 19508,
5
+ "embedding_offset": 22415
6
+ }
1.residuals.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb0fc6649fa181655fe6d689b7e1df971b00cf89e2ccf484eb5739d9d7d19fd
3
+ size 937584
avg_residual.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff64ae78ff732e590c04740ce2cac3e5600342eaf0e09442e81900f40778fc5
3
+ size 1205
buckets.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9b5a037e63754067d63e0dfc2d6baaaf00b1f193eee491f7a94e841dd75f72
3
+ size 1432
centroids.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a9482a16887e01f55dcfe9571f3b3f5bc5ee8d29e8c833a6fbeda96681bdfb
3
+ size 394406
collection.json ADDED
The diff for this file is too large to render. See raw diff
 
doclens.0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ [246,100,218,113,158,131,195,312,151,108,416,147,227,353,278,260,108,324,174,146,221,192,367,121,228,141,256,317,125,133,182,217,204,122,218,363,164,210,112,279,211,145,134,174,142,149,233,166,180,181,135,331,177,118,133,57,205,129,131,246,119,155,51,107,129,75,21,22,105,162,204,241,208,196,101,154,69,139,170,199,394,247,203,131,149,165,140,169,149,371,294,224,414,396,353,156,212,158,205,154,183,200,210,154,149,164,145,146,163,131,103,182,280,129,408,405,148,90]
doclens.1.json ADDED
@@ -0,0 +1 @@
 
 
1
+ [109,234,316,354,97,182,265,115,121,208,345,132,239,136,212,107,289,344,163,389,194,71,152,196,222,273,153,371,95,156,357,75,369,190,144,170,117,383,63,216,336,232,321,242,102,194,394,109,116,50,196,269,348,188,109,298,274,255,202,407,202,191,198,348,115,219,86,70,74,98,47,68,167,120,88,66,170,90,148,24,420,155,337,183,308,234,143,368,58,59,73,67,70,159,21,227,96,48,81,72,131,94,96,30,31,16,26,5,25,4,76,15,52,10,158,5]
ivf.pid.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2201c6af14a215b6ebdf391172104ad4f8c9902c7fff89ea3e9e37064c5ead4b
3
+ size 88280
metadata.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config":{
3
+ "query_token_id":"[unused0]",
4
+ "doc_token_id":"[unused1]",
5
+ "query_token":"[Q]",
6
+ "doc_token":"[D]",
7
+ "ncells":null,
8
+ "centroid_score_threshold":null,
9
+ "ndocs":null,
10
+ "load_index_with_mmap":false,
11
+ "index_path":null,
12
+ "index_bsize":32,
13
+ "nbits":4,
14
+ "kmeans_niters":20,
15
+ "resume":false,
16
+ "similarity":"cosine",
17
+ "bsize":64,
18
+ "accumsteps":1,
19
+ "lr":0.000005,
20
+ "maxsteps":500000,
21
+ "save_every":9,
22
+ "warmup":9,
23
+ "warmup_bert":null,
24
+ "relu":false,
25
+ "nway":2,
26
+ "use_ib_negatives":true,
27
+ "reranker":false,
28
+ "distillation_alpha":1.0,
29
+ "ignore_scores":false,
30
+ "model_name":"chunks_colbert_small",
31
+ "query_maxlen":32,
32
+ "attend_to_mask_tokens":false,
33
+ "interaction":"colbert",
34
+ "dim":96,
35
+ "doc_maxlen":512,
36
+ "mask_punctuation":true,
37
+ "checkpoint":".ragatouille/colbert/none/2024-09/26/17.49.22/checkpoints/colbert",
38
+ "triples":"/root/.cache/huggingface/hub/datasets--tensorboy--chunks_dataset/snapshots/11809bcb1a7e9317516339776279907b82ffa630/train/triples.train.colbert.jsonl",
39
+ "collection":[
40
+ "list with 234 elements starting with...",
41
+ [
42
+ "'Probation \\\\\\\\nEvery new team member will be put on probation for the first 3 months of their service in the \\\\\\\\norganization counted from the date of joining. At the end of the third month, the team member will be \\\\\\\\ninformed whether or not s/he has successfully crossed the probation period based on his/her \\\\\\\\nperformance. \\\\\\\\nThe team member can take upto 3 leaves during the probation period, the remaining leaves will be \\\\\\\\naccrued and can be availed post the probation. The 3 leaves will include planned / emergency/ sick \\\\\\\\nleaves etc but will not include wedding/maternity/paternity leaves. Leaves are to be planned in advance \\\\\\\\nin consultation with the concerned manager to the extent possible. Leave encashment is not applicable if \\\\\\\\nexit takes place within the probation period. \\\\\\\\nIncase of termination or resignation during/at the end of probation period, the applicable notice period \\\\\\\\nwill be of 1 week (5 working days). No leaves will be permitted during notice period.' /n/nLink to policy document: https://docs.google.com/document/d/1Fqa1FBqUVFJGq0uDqwFqF3rW_t7_zu4xXC9KMKY_lIM/edit#heading=h.5kumi7cfdp5o.'",
43
+ "'1. Self-initiated: The team member voluntarily resigns from the organization. \\\\\\\\n2. Firm-initiated: The firm initiates the termination of a team member on account of \\\\\\\\nnon-performance, unauthorized absence (absconding) or on behavioral grounds.' /n/nLink to policy document: https://docs.google.com/document/d/1Fqa1FBqUVFJGq0uDqwFqF3rW_t7_zu4xXC9KMKY_lIM/edit#heading=h.5kumi7cfdp5o.'",
44
+ "'Eligibility for Year-end Appraisal\\\\\\\\nIn case of self-initiated exit, team members who resign on or before 31st March will not be eligible for\\\\\\\\nyear-end appraisal & bonus (profit sharing in case of Sr Consultant & above).\\\\\\\\nFor those availing the Vidya program, team members whose date of leaving is before 1st March will not\\\\\\\\nbe eligible for year-end appraisal & bonus (profit sharing in case of Sr Consultant & above).\\\\\\\\n\\\\\\\\nEligibility for Mid-year Appraisal\\\\\\\\nIn case of self-initiated exit, team members who resign on or before 30th September will not be eligible \\\\\\\\nfor mid-point appraisal. \\\\\\\\nFor those availing the Vidya program, team members whose date of leaving is before 1st September will \\\\\\\\nnot be eligible for year-end appraisal & bonus (profit sharing in case of Sr Consultant & above).' /n/nLink to policy document: https://docs.google.com/document/d/1Fqa1FBqUVFJGq0uDqwFqF3rW_t7_zu4xXC9KMKY_lIM/edit#heading=h.5kumi7cfdp5o.'"
45
+ ]
46
+ ],
47
+ "queries":"/root/.cache/huggingface/hub/datasets--tensorboy--chunks_dataset/snapshots/11809bcb1a7e9317516339776279907b82ffa630/train/queries.train.colbert.tsv",
48
+ "index_name":"chunks_small_eps_3000",
49
+ "overwrite":false,
50
+ "root":".ragatouille/",
51
+ "experiment":"colbert",
52
+ "index_root":null,
53
+ "name":"2024-09/26/18.02.51",
54
+ "rank":0,
55
+ "nranks":2,
56
+ "amp":true,
57
+ "gpus":2,
58
+ "avoid_fork_if_possible":false
59
+ },
60
+ "num_chunks":2,
61
+ "num_partitions":2048,
62
+ "num_embeddings":41923,
63
+ "avg_doclen":179.1581196581,
64
+ "RAGatouille":{
65
+ "index_config":{
66
+ "index_type":"PLAID",
67
+ "index_name":"chunks_small_eps_3000"
68
+ }
69
+ }
70
+ }
pid_docid_map.json ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0":"0",
3
+ "1":"1",
4
+ "2":"2",
5
+ "3":"3",
6
+ "4":"4",
7
+ "5":"5",
8
+ "6":"6",
9
+ "7":"7",
10
+ "8":"7",
11
+ "9":"8",
12
+ "10":"9",
13
+ "11":"9",
14
+ "12":"10",
15
+ "13":"10",
16
+ "14":"10",
17
+ "15":"11",
18
+ "16":"12",
19
+ "17":"13",
20
+ "18":"14",
21
+ "19":"15",
22
+ "20":"16",
23
+ "21":"17",
24
+ "22":"18",
25
+ "23":"19",
26
+ "24":"20",
27
+ "25":"21",
28
+ "26":"22",
29
+ "27":"23",
30
+ "28":"24",
31
+ "29":"25",
32
+ "30":"26",
33
+ "31":"27",
34
+ "32":"28",
35
+ "33":"29",
36
+ "34":"30",
37
+ "35":"31",
38
+ "36":"32",
39
+ "37":"33",
40
+ "38":"34",
41
+ "39":"35",
42
+ "40":"36",
43
+ "41":"37",
44
+ "42":"38",
45
+ "43":"39",
46
+ "44":"40",
47
+ "45":"41",
48
+ "46":"42",
49
+ "47":"43",
50
+ "48":"44",
51
+ "49":"45",
52
+ "50":"46",
53
+ "51":"47",
54
+ "52":"48",
55
+ "53":"49",
56
+ "54":"50",
57
+ "55":"51",
58
+ "56":"52",
59
+ "57":"53",
60
+ "58":"54",
61
+ "59":"55",
62
+ "60":"56",
63
+ "61":"57",
64
+ "62":"58",
65
+ "63":"59",
66
+ "64":"60",
67
+ "65":"61",
68
+ "66":"62",
69
+ "67":"63",
70
+ "68":"64",
71
+ "69":"65",
72
+ "70":"66",
73
+ "71":"67",
74
+ "72":"68",
75
+ "73":"69",
76
+ "74":"70",
77
+ "75":"71",
78
+ "76":"72",
79
+ "77":"73",
80
+ "78":"74",
81
+ "79":"75",
82
+ "80":"76",
83
+ "81":"76",
84
+ "82":"77",
85
+ "83":"78",
86
+ "84":"79",
87
+ "85":"80",
88
+ "86":"81",
89
+ "87":"82",
90
+ "88":"83",
91
+ "89":"84",
92
+ "90":"84",
93
+ "91":"85",
94
+ "92":"86",
95
+ "93":"87",
96
+ "94":"88",
97
+ "95":"89",
98
+ "96":"90",
99
+ "97":"91",
100
+ "98":"92",
101
+ "99":"93",
102
+ "100":"94",
103
+ "101":"95",
104
+ "102":"96",
105
+ "103":"97",
106
+ "104":"98",
107
+ "105":"99",
108
+ "106":"100",
109
+ "107":"101",
110
+ "108":"102",
111
+ "109":"103",
112
+ "110":"104",
113
+ "111":"105",
114
+ "112":"106",
115
+ "113":"107",
116
+ "114":"108",
117
+ "115":"108",
118
+ "116":"108",
119
+ "117":"109",
120
+ "118":"110",
121
+ "119":"111",
122
+ "120":"112",
123
+ "121":"113",
124
+ "122":"113",
125
+ "123":"114",
126
+ "124":"115",
127
+ "125":"115",
128
+ "126":"116",
129
+ "127":"117",
130
+ "128":"118",
131
+ "129":"118",
132
+ "130":"119",
133
+ "131":"120",
134
+ "132":"121",
135
+ "133":"122",
136
+ "134":"123",
137
+ "135":"124",
138
+ "136":"124",
139
+ "137":"125",
140
+ "138":"125",
141
+ "139":"126",
142
+ "140":"127",
143
+ "141":"128",
144
+ "142":"129",
145
+ "143":"130",
146
+ "144":"131",
147
+ "145":"132",
148
+ "146":"132",
149
+ "147":"133",
150
+ "148":"134",
151
+ "149":"135",
152
+ "150":"136",
153
+ "151":"137",
154
+ "152":"138",
155
+ "153":"139",
156
+ "154":"140",
157
+ "155":"141",
158
+ "156":"142",
159
+ "157":"143",
160
+ "158":"143",
161
+ "159":"144",
162
+ "160":"145",
163
+ "161":"146",
164
+ "162":"147",
165
+ "163":"148",
166
+ "164":"149",
167
+ "165":"150",
168
+ "166":"151",
169
+ "167":"152",
170
+ "168":"153",
171
+ "169":"154",
172
+ "170":"155",
173
+ "171":"156",
174
+ "172":"157",
175
+ "173":"158",
176
+ "174":"159",
177
+ "175":"160",
178
+ "176":"161",
179
+ "177":"162",
180
+ "178":"163",
181
+ "179":"164",
182
+ "180":"165",
183
+ "181":"166",
184
+ "182":"167",
185
+ "183":"168",
186
+ "184":"169",
187
+ "185":"170",
188
+ "186":"171",
189
+ "187":"172",
190
+ "188":"173",
191
+ "189":"174",
192
+ "190":"175",
193
+ "191":"176",
194
+ "192":"177",
195
+ "193":"178",
196
+ "194":"179",
197
+ "195":"180",
198
+ "196":"181",
199
+ "197":"182",
200
+ "198":"183",
201
+ "199":"183",
202
+ "200":"184",
203
+ "201":"185",
204
+ "202":"186",
205
+ "203":"187",
206
+ "204":"188",
207
+ "205":"189",
208
+ "206":"190",
209
+ "207":"191",
210
+ "208":"192",
211
+ "209":"193",
212
+ "210":"194",
213
+ "211":"195",
214
+ "212":"196",
215
+ "213":"197",
216
+ "214":"198",
217
+ "215":"199",
218
+ "216":"200",
219
+ "217":"201",
220
+ "218":"202",
221
+ "219":"203",
222
+ "220":"204",
223
+ "221":"205",
224
+ "222":"206",
225
+ "223":"207",
226
+ "224":"208",
227
+ "225":"209",
228
+ "226":"210",
229
+ "227":"211",
230
+ "228":"212",
231
+ "229":"213",
232
+ "230":"214",
233
+ "231":"215",
234
+ "232":"216",
235
+ "233":"217"
236
+ }
plan.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "query_token_id": "[unused0]",
4
+ "doc_token_id": "[unused1]",
5
+ "query_token": "[Q]",
6
+ "doc_token": "[D]",
7
+ "ncells": null,
8
+ "centroid_score_threshold": null,
9
+ "ndocs": null,
10
+ "load_index_with_mmap": false,
11
+ "index_path": null,
12
+ "index_bsize": 32,
13
+ "nbits": 4,
14
+ "kmeans_niters": 20,
15
+ "resume": false,
16
+ "similarity": "cosine",
17
+ "bsize": 64,
18
+ "accumsteps": 1,
19
+ "lr": 5e-6,
20
+ "maxsteps": 500000,
21
+ "save_every": 9,
22
+ "warmup": 9,
23
+ "warmup_bert": null,
24
+ "relu": false,
25
+ "nway": 2,
26
+ "use_ib_negatives": true,
27
+ "reranker": false,
28
+ "distillation_alpha": 1.0,
29
+ "ignore_scores": false,
30
+ "model_name": "chunks_colbert_small",
31
+ "query_maxlen": 32,
32
+ "attend_to_mask_tokens": false,
33
+ "interaction": "colbert",
34
+ "dim": 96,
35
+ "doc_maxlen": 512,
36
+ "mask_punctuation": true,
37
+ "checkpoint": ".ragatouille\/colbert\/none\/2024-09\/26\/17.49.22\/checkpoints\/colbert",
38
+ "triples": "\/root\/.cache\/huggingface\/hub\/datasets--tensorboy--chunks_dataset\/snapshots\/11809bcb1a7e9317516339776279907b82ffa630\/train\/triples.train.colbert.jsonl",
39
+ "collection": [
40
+ "list with 234 elements starting with...",
41
+ [
42
+ "'Probation \\\\\\\\nEvery new team member will be put on probation for the first 3 months of their service in the \\\\\\\\norganization counted from the date of joining. At the end of the third month, the team member will be \\\\\\\\ninformed whether or not s\/he has successfully crossed the probation period based on his\/her \\\\\\\\nperformance. \\\\\\\\nThe team member can take upto 3 leaves during the probation period, the remaining leaves will be \\\\\\\\naccrued and can be availed post the probation. The 3 leaves will include planned \/ emergency\/ sick \\\\\\\\nleaves etc but will not include wedding\/maternity\/paternity leaves. Leaves are to be planned in advance \\\\\\\\nin consultation with the concerned manager to the extent possible. Leave encashment is not applicable if \\\\\\\\nexit takes place within the probation period. \\\\\\\\nIncase of termination or resignation during\/at the end of probation period, the applicable notice period \\\\\\\\nwill be of 1 week (5 working days). No leaves will be permitted during notice period.' \/n\/nLink to policy document: https:\/\/docs.google.com\/document\/d\/1Fqa1FBqUVFJGq0uDqwFqF3rW_t7_zu4xXC9KMKY_lIM\/edit#heading=h.5kumi7cfdp5o.'",
43
+ "'1. Self-initiated: The team member voluntarily resigns from the organization. \\\\\\\\n2. Firm-initiated: The firm initiates the termination of a team member on account of \\\\\\\\nnon-performance, unauthorized absence (absconding) or on behavioral grounds.' \/n\/nLink to policy document: https:\/\/docs.google.com\/document\/d\/1Fqa1FBqUVFJGq0uDqwFqF3rW_t7_zu4xXC9KMKY_lIM\/edit#heading=h.5kumi7cfdp5o.'",
44
+ "'Eligibility for Year-end Appraisal\\\\\\\\nIn case of self-initiated exit, team members who resign on or before 31st March will not be eligible for\\\\\\\\nyear-end appraisal & bonus (profit sharing in case of Sr Consultant & above).\\\\\\\\nFor those availing the Vidya program, team members whose date of leaving is before 1st March will not\\\\\\\\nbe eligible for year-end appraisal & bonus (profit sharing in case of Sr Consultant & above).\\\\\\\\n\\\\\\\\nEligibility for Mid-year Appraisal\\\\\\\\nIn case of self-initiated exit, team members who resign on or before 30th September will not be eligible \\\\\\\\nfor mid-point appraisal. \\\\\\\\nFor those availing the Vidya program, team members whose date of leaving is before 1st September will \\\\\\\\nnot be eligible for year-end appraisal & bonus (profit sharing in case of Sr Consultant & above).' \/n\/nLink to policy document: https:\/\/docs.google.com\/document\/d\/1Fqa1FBqUVFJGq0uDqwFqF3rW_t7_zu4xXC9KMKY_lIM\/edit#heading=h.5kumi7cfdp5o.'"
45
+ ]
46
+ ],
47
+ "queries": "\/root\/.cache\/huggingface\/hub\/datasets--tensorboy--chunks_dataset\/snapshots\/11809bcb1a7e9317516339776279907b82ffa630\/train\/queries.train.colbert.tsv",
48
+ "index_name": "chunks_small_eps_3000",
49
+ "overwrite": false,
50
+ "root": ".ragatouille\/",
51
+ "experiment": "colbert",
52
+ "index_root": null,
53
+ "name": "2024-09\/26\/18.02.51",
54
+ "rank": 0,
55
+ "nranks": 2,
56
+ "amp": true,
57
+ "gpus": 2,
58
+ "avoid_fork_if_possible": false
59
+ },
60
+ "num_chunks": 2,
61
+ "num_partitions": 2048,
62
+ "num_embeddings_est": 41901.2141418457,
63
+ "avg_doclen_est": 179.0650177001953
64
+ }