RishuD7 commited on
Commit
475365b
1 Parent(s): c684b44

Add new SentenceTransformer model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,938 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BAAI/bge-base-en
3
+ language:
4
+ - en
5
+ library_name: sentence-transformers
6
+ license: apache-2.0
7
+ metrics:
8
+ - cosine_accuracy@1
9
+ - cosine_accuracy@3
10
+ - cosine_accuracy@5
11
+ - cosine_accuracy@10
12
+ - cosine_precision@1
13
+ - cosine_precision@3
14
+ - cosine_precision@5
15
+ - cosine_precision@10
16
+ - cosine_recall@1
17
+ - cosine_recall@3
18
+ - cosine_recall@5
19
+ - cosine_recall@10
20
+ - cosine_ndcg@10
21
+ - cosine_mrr@10
22
+ - cosine_map@100
23
+ pipeline_tag: sentence-similarity
24
+ tags:
25
+ - sentence-transformers
26
+ - sentence-similarity
27
+ - feature-extraction
28
+ - generated_from_trainer
29
+ - dataset_size:4894
30
+ - loss:MatryoshkaLoss
31
+ - loss:MultipleNegativesRankingLoss
32
+ widget:
33
+ - source_sentence: "This Agreement shall be in force for 24 months after the Effective\
34
+ \ Date, unless terminated in advance by either Party with thirty (30) days’ written\
35
+ \ notice. However, the obligation of confidentiality and non-use shall survive\
36
+ \ the termination or expiration of this Agreement for five (5) years, with exception\
37
+ \ of trade secrets, which shall be confidential for an unlimited period of time.\
38
+ \ 4. Return and Destruction of Confidential Information 4.1. Recipient will at\
39
+ \ the written request of Discloser promptly return or destroy all the Confidential.\n\
40
+ \ Information and copies (save for one copy for record purposes and securely\
41
+ \ stored Confidential\n.\n Information that is created during automatic system\
42
+ \ back-up) to Discloser and immediately cease using\n the same. Recipient\
43
+ \ shall provide a written certification to Discloser regarding such destruction\
44
+ \ of\n\nRecipient agrees that Discloser will, in addition to any other remedies\
45
+ \ available to it at law or equity, be entitled to seek equitable relief, including\
46
+ \ injunctive relief and specific performance to enforce the terms hereof. 7.3.\
47
+ \ The terms and conditions herein constitute the entire agreement and understanding\
48
+ \ of the Parties and shall supersede all communications, negotiations, arrangements\
49
+ \ and agreements, either oral or written, with respect to the subject matter hereof.\
50
+ \ No amendments to or modifications of this Agree- ment shall be effective unless\
51
+ \ reduced to writing and executed by the Parties hereto."
52
+ sentences:
53
+ - Absolute Maximum Amount of Liability
54
+ - Termination for Convenience
55
+ - Third Party Beneficiary
56
+ - source_sentence: " 19.7 Force Majeure. No liability hereunder shall result to\
57
+ \ a Party by reason of delay in\n performance caused by force majeure, that is\
58
+ \ circumstances beyond the reasonable control of\n the Party, including, without\
59
+ \ limitation, acts of God, fire, flood, war, terrorism, civil unrest, labor.\n\
60
+ \ unrest, or shortage of or inability to obtain material or equipment.\n.\n \
61
+ \ 19.8 Section and Paragraph Headings. The section and paragraph headings\
62
+ \ used in this\n into any interpretation of the Agreement..\n.\n 19.9\n \
63
+ \ Entire Agreement..The terms and conditions herein constitute the entire\n\
64
+ \n electronic, oral or written, between the Parties hereto with respect to the\
65
+ \ subject matter hereof.\n\nLICENSEE shall provide to BCM copies of certificates\
66
+ \ of insurance demonstrating its additional insured status within [***] days after\
67
+ \ execution of this Agreement. Upon request by BCM, LICENsEE shall provide to\
68
+ \ BCM copies of said policies of insurance. It is the intention of the Parties\
69
+ \ hereto that LiCENsEE shall throughout the Term of this Agreement, continuously\
70
+ \ and without interruption, maintain in force the required insurance coverages\
71
+ \ set forth in this -14- ------- of LICENSEE allowing BCM, at its option, to immediately\
72
+ \ terminate this Agreement. (ili) BcM reserves the right to request additional\
73
+ \ policies of insurance which are appropriate and reasonable in light of LICENSEE's\
74
+ \ business operations and availability of coverage..\n 17. WARRANTIES\n 17.1 Each\
75
+ \ of BCM and LICENsEE represents and warrants to the other that it has full authority\n\
76
+ \ to execute the license and undertake the obligations therein.\n.\n 17.2 Each\
77
+ \ of BcM and LICeNsEE represents and warrants to the other that the execution,\n\
78
+ \ delivery and performance of this Agreement by such Party does not create a breach\
79
+ \ or default\n under any other agreement to which it is a party or by which it\
80
+ \ is bound.\n.\n 17.3 bcM represents that Bcm is not aware of any claims pending,\
81
+ \ asserted, or threatened\n challenging BCM's ownership or control of the Patent\
82
+ \ Rights.\n"
83
+ sentences:
84
+ - Absolute Maximum Amount of Liability
85
+ - Absolute Maximum Amount of Liability
86
+ - Force Majeure
87
+ - source_sentence: 'The liability of a party (''Party A") to the other party to this
88
+ Agreement ("Party B") in tort (including negligence), contract, statute or otherwise
89
+ for any loss, damage, cost or expense incurred by Party B or a third party in
90
+ connection with any act or omission by Party A: (a) is limited under or in relation
91
+ to this Agreement, to USD$500,000 per event or series of related events; and (b)
92
+ the aggregate liability of Party A to Party B under this Agreement for all such
93
+ claims by Party B which arise during each 12 month period (commencing on the Start
94
+ Date) is limited to USD$1,000,000.'
95
+ sentences:
96
+ - Absolute Maximum Amount of Liability
97
+ - Absolute Maximum Amount of Liability
98
+ - Governing Law
99
+ - source_sentence: " WAIVER OF RIGHTS\n 21.9 A right created\
100
+ \ by this Agreement may only be waived in writing by the party giving the waiver,\
101
+ \ and the\n failure to exercise or any delay in exercising\
102
+ \ a right or remedy provided by this Agreement or by law\n \
103
+ \ does not waive the right or remedy.\n.\n 21.10 A waiver of a breach\
104
+ \ of this Agreement does not waive any other breach.\n.\n WARRANTIES\n\
105
+ \ 21.11 Each party warrants to the other that entering into and performing\
106
+ \ its obligations under this Agreement\n does not breach any\
107
+ \ of its contractual obligations to any other person.\n.\n 21.12 \
108
+ \ You warrant that you have not relied on any representations or warranties by\
109
+ \ us other than those in this\n Agreement.\n.\n ASSIGNMENT\
110
+ \ AND AGENCY\n 21.13 A party must not assign its rights or novate\
111
+ \ its obligations under this Agreement without the other\n \
112
+ \ party’s prior written consent, which must not be unreasonably withheld.\n.\n\
113
+ \ 21.14 You may appoint a third party to act on your behalf in relation\
114
+ \ to this Agreement with our prior written\n consent, which\
115
+ \ will not be unreasonably withheld. We may withdraw our consent on reasonable\n\
116
+ \ grounds relating to the conduct of the third party.\n\n \
117
+ \ 17.2 A party must not disclose the other party’s confidential information\
118
+ \ to any person except:\n TELSTRA CORPORATION LIMITED (ABN 33 051 775\
119
+ \ 556) | PAGE 6 OF 12\n\
120
+ DocuSign Envelope ID: 139730BE-3D26-4345-B2B4-0D606F8D4CEA\n \
121
+ \ (a) to its employees, professional advisors and our Personnel on a ‘need\
122
+ \ to know’ basis provided\n those persons first agree\
123
+ \ to observe the confidentiality of the information;\n (b)\
124
+ \ with the other party’s prior written consent;\n (c)\
125
+ \ if required by law, any regulatory authority or stock exchange; or\n \
126
+ \ (d) if it is in the public domain.\n"
127
+ sentences:
128
+ - Assignment
129
+ - Absolute Maximum Amount of Liability
130
+ - Third Party Beneficiary
131
+ - source_sentence: "13.2 We accept liability to the extent arising from our negligence,\
132
+ \ breach of contract or nbn™ Activities: (a) for any personal injury or death\
133
+ \ to you or your Personnel resulting from the supply of the Services; (b) for\
134
+ \ any damage to your real or tangible property resulting from the supply of the\
135
+ \ Services, but we limit our liability to our choice of repairing or replacing\
136
+ \ the property or paying the cost of repairing or replacing it; or (c) unless\
137
+ \ clause 13.1 applies, for any other cost or expense you reasonably incur that\
138
+ \ is a direct result of and flows naturally from, our breach of contract, negligence\
139
+ \ or nbn™ Activities (but TELSTRA CORPORATION LIMITED (ABN 33 051 775 556) | PAGE\
140
+ \ 6 OF 25 DocuSign Envelope ID: 3EE2487C-8AA0-42DB-8C95-FD658789EC41 CONFIDENTIAL\
141
+ \ excluding loss of profits, revenue, business opportunities, likely savings and\
142
+ \ data), and our liability under this clause is limited for all claims in aggregate\
143
+ \ to the total amount payable to us under this Agreement during the first year\
144
+ \ of this Agreement.\n Intellectual Property Rights means\
145
+ \ all current and future registered rights in respect of copyright,\n \
146
+ \ designs, circuit layouts, trademarks, trade secrets, domain names,\
147
+ \ database rights, know-how and\n confidential information\
148
+ \ and any other intellectual property rights as defined by Article 2 of the World\n\
149
+ \ Intellectual Property Organisation Convention of July 1967,\
150
+ \ excluding patents.\n nbn™ means nbn co limited (ABN 86\
151
+ \ 136 533 741), as that company exists from time to time.\n \
152
+ \ nbn™ Activities means nbn™ Equipment and nbn™’s negligent or wilful acts\
153
+ \ or omissions in\n connection with the Services.\n \
154
+ \ nbn™ Equipment means any equipment that is owned, operated or\
155
+ \ controlled by nbn™.\n nbn™ Service means a Service that\
156
+ \ is supplied by or using nbn™ or nbn™ Equipment.\n.\n Our\
157
+ \ Customer Terms means the Standard Form of Agreement formulated by Telstra for\
158
+ \ the purposes\n of Part 23 of the Act, as amended by us\
159
+ \ from time to time in accordance with the Act.\n.\n Personnel\
160
+ \ means a person’s officers, employees, agents, contractors and sub-contractors\
161
+ \ and in our\n case includes our Related Bodies Corporate.\n\
162
+ .\n Planned Maintenance has the meaning in clause 10.1.\n\
163
+ .\n Related Bodies Corporate has the meaning given under\
164
+ \ the Corporations Act 2001 (Cth).\n.\n Service means a service\
165
+ \ under this Agreement set out or referred to in a Service Schedule or an\n \
166
+ \ agreed statement of work, and includes any individual service\
167
+ \ or component which constitutes the\n service.\n.\n \
168
+ \ Service Order Form means an agreed:\n \
169
+ \ (a) application or order form for a new Service or to vary, reconfigure,\
170
+ \ renew, reconfigure or\n cancel an existing\
171
+ \ Service; or\n (b) statement of work between the\
172
+ \ parties for services under a Service Schedule or otherwise.\n.\n TELSTRA\
173
+ \ CORPORATION LIMITED (ABN 33 051 775 556) | \
174
+ \ PAGE 10 OF 25\nDocuSign Envelope ID: 3EE2487C-8AA0-42DB-8C95-FD658789EC41\n\
175
+ \ \
176
+ \ CONFIDENTIAL\n \
177
+ \ Service Schedules means the Schedules attached or added to these Agreement\
178
+ \ Terms for a\n Service.\n"
179
+ sentences:
180
+ - Non Solicitation
181
+ - Late Payment Charges
182
+ - Absolute Maximum Amount of Liability
183
+ model-index:
184
+ - name: BGE base En version 1
185
+ results:
186
+ - task:
187
+ type: information-retrieval
188
+ name: Information Retrieval
189
+ dataset:
190
+ name: dim 768
191
+ type: dim_768
192
+ metrics:
193
+ - type: cosine_accuracy@1
194
+ value: 0.0077777777777777776
195
+ name: Cosine Accuracy@1
196
+ - type: cosine_accuracy@3
197
+ value: 0.01888888888888889
198
+ name: Cosine Accuracy@3
199
+ - type: cosine_accuracy@5
200
+ value: 0.03
201
+ name: Cosine Accuracy@5
202
+ - type: cosine_accuracy@10
203
+ value: 0.052222222222222225
204
+ name: Cosine Accuracy@10
205
+ - type: cosine_precision@1
206
+ value: 0.0077777777777777776
207
+ name: Cosine Precision@1
208
+ - type: cosine_precision@3
209
+ value: 0.0062962962962962955
210
+ name: Cosine Precision@3
211
+ - type: cosine_precision@5
212
+ value: 0.006
213
+ name: Cosine Precision@5
214
+ - type: cosine_precision@10
215
+ value: 0.005222222222222224
216
+ name: Cosine Precision@10
217
+ - type: cosine_recall@1
218
+ value: 0.0077777777777777776
219
+ name: Cosine Recall@1
220
+ - type: cosine_recall@3
221
+ value: 0.01888888888888889
222
+ name: Cosine Recall@3
223
+ - type: cosine_recall@5
224
+ value: 0.03
225
+ name: Cosine Recall@5
226
+ - type: cosine_recall@10
227
+ value: 0.052222222222222225
228
+ name: Cosine Recall@10
229
+ - type: cosine_ndcg@10
230
+ value: 0.025243913600660865
231
+ name: Cosine Ndcg@10
232
+ - type: cosine_mrr@10
233
+ value: 0.017227954144620812
234
+ name: Cosine Mrr@10
235
+ - type: cosine_map@100
236
+ value: 0.031210795353020366
237
+ name: Cosine Map@100
238
+ - task:
239
+ type: information-retrieval
240
+ name: Information Retrieval
241
+ dataset:
242
+ name: dim 512
243
+ type: dim_512
244
+ metrics:
245
+ - type: cosine_accuracy@1
246
+ value: 0.006666666666666667
247
+ name: Cosine Accuracy@1
248
+ - type: cosine_accuracy@3
249
+ value: 0.02
250
+ name: Cosine Accuracy@3
251
+ - type: cosine_accuracy@5
252
+ value: 0.028888888888888888
253
+ name: Cosine Accuracy@5
254
+ - type: cosine_accuracy@10
255
+ value: 0.05555555555555555
256
+ name: Cosine Accuracy@10
257
+ - type: cosine_precision@1
258
+ value: 0.006666666666666667
259
+ name: Cosine Precision@1
260
+ - type: cosine_precision@3
261
+ value: 0.006666666666666667
262
+ name: Cosine Precision@3
263
+ - type: cosine_precision@5
264
+ value: 0.005777777777777778
265
+ name: Cosine Precision@5
266
+ - type: cosine_precision@10
267
+ value: 0.005555555555555556
268
+ name: Cosine Precision@10
269
+ - type: cosine_recall@1
270
+ value: 0.006666666666666667
271
+ name: Cosine Recall@1
272
+ - type: cosine_recall@3
273
+ value: 0.02
274
+ name: Cosine Recall@3
275
+ - type: cosine_recall@5
276
+ value: 0.028888888888888888
277
+ name: Cosine Recall@5
278
+ - type: cosine_recall@10
279
+ value: 0.05555555555555555
280
+ name: Cosine Recall@10
281
+ - type: cosine_ndcg@10
282
+ value: 0.025745053671774584
283
+ name: Cosine Ndcg@10
284
+ - type: cosine_mrr@10
285
+ value: 0.016883597883597883
286
+ name: Cosine Mrr@10
287
+ - type: cosine_map@100
288
+ value: 0.03050307044901035
289
+ name: Cosine Map@100
290
+ - task:
291
+ type: information-retrieval
292
+ name: Information Retrieval
293
+ dataset:
294
+ name: dim 256
295
+ type: dim_256
296
+ metrics:
297
+ - type: cosine_accuracy@1
298
+ value: 0.006666666666666667
299
+ name: Cosine Accuracy@1
300
+ - type: cosine_accuracy@3
301
+ value: 0.017777777777777778
302
+ name: Cosine Accuracy@3
303
+ - type: cosine_accuracy@5
304
+ value: 0.027777777777777776
305
+ name: Cosine Accuracy@5
306
+ - type: cosine_accuracy@10
307
+ value: 0.05444444444444444
308
+ name: Cosine Accuracy@10
309
+ - type: cosine_precision@1
310
+ value: 0.006666666666666667
311
+ name: Cosine Precision@1
312
+ - type: cosine_precision@3
313
+ value: 0.005925925925925926
314
+ name: Cosine Precision@3
315
+ - type: cosine_precision@5
316
+ value: 0.005555555555555556
317
+ name: Cosine Precision@5
318
+ - type: cosine_precision@10
319
+ value: 0.0054444444444444445
320
+ name: Cosine Precision@10
321
+ - type: cosine_recall@1
322
+ value: 0.006666666666666667
323
+ name: Cosine Recall@1
324
+ - type: cosine_recall@3
325
+ value: 0.017777777777777778
326
+ name: Cosine Recall@3
327
+ - type: cosine_recall@5
328
+ value: 0.027777777777777776
329
+ name: Cosine Recall@5
330
+ - type: cosine_recall@10
331
+ value: 0.05444444444444444
332
+ name: Cosine Recall@10
333
+ - type: cosine_ndcg@10
334
+ value: 0.02548153155657326
335
+ name: Cosine Ndcg@10
336
+ - type: cosine_mrr@10
337
+ value: 0.016899029982363308
338
+ name: Cosine Mrr@10
339
+ - type: cosine_map@100
340
+ value: 0.031417373909796646
341
+ name: Cosine Map@100
342
+ - task:
343
+ type: information-retrieval
344
+ name: Information Retrieval
345
+ dataset:
346
+ name: dim 128
347
+ type: dim_128
348
+ metrics:
349
+ - type: cosine_accuracy@1
350
+ value: 0.0033333333333333335
351
+ name: Cosine Accuracy@1
352
+ - type: cosine_accuracy@3
353
+ value: 0.017777777777777778
354
+ name: Cosine Accuracy@3
355
+ - type: cosine_accuracy@5
356
+ value: 0.027777777777777776
357
+ name: Cosine Accuracy@5
358
+ - type: cosine_accuracy@10
359
+ value: 0.06333333333333334
360
+ name: Cosine Accuracy@10
361
+ - type: cosine_precision@1
362
+ value: 0.0033333333333333335
363
+ name: Cosine Precision@1
364
+ - type: cosine_precision@3
365
+ value: 0.005925925925925926
366
+ name: Cosine Precision@3
367
+ - type: cosine_precision@5
368
+ value: 0.005555555555555556
369
+ name: Cosine Precision@5
370
+ - type: cosine_precision@10
371
+ value: 0.006333333333333335
372
+ name: Cosine Precision@10
373
+ - type: cosine_recall@1
374
+ value: 0.0033333333333333335
375
+ name: Cosine Recall@1
376
+ - type: cosine_recall@3
377
+ value: 0.017777777777777778
378
+ name: Cosine Recall@3
379
+ - type: cosine_recall@5
380
+ value: 0.027777777777777776
381
+ name: Cosine Recall@5
382
+ - type: cosine_recall@10
383
+ value: 0.06333333333333334
384
+ name: Cosine Recall@10
385
+ - type: cosine_ndcg@10
386
+ value: 0.026882550651169755
387
+ name: Cosine Ndcg@10
388
+ - type: cosine_mrr@10
389
+ value: 0.01613403880070546
390
+ name: Cosine Mrr@10
391
+ - type: cosine_map@100
392
+ value: 0.030061745612125636
393
+ name: Cosine Map@100
394
+ - task:
395
+ type: information-retrieval
396
+ name: Information Retrieval
397
+ dataset:
398
+ name: dim 64
399
+ type: dim_64
400
+ metrics:
401
+ - type: cosine_accuracy@1
402
+ value: 0.0044444444444444444
403
+ name: Cosine Accuracy@1
404
+ - type: cosine_accuracy@3
405
+ value: 0.022222222222222223
406
+ name: Cosine Accuracy@3
407
+ - type: cosine_accuracy@5
408
+ value: 0.03222222222222222
409
+ name: Cosine Accuracy@5
410
+ - type: cosine_accuracy@10
411
+ value: 0.058888888888888886
412
+ name: Cosine Accuracy@10
413
+ - type: cosine_precision@1
414
+ value: 0.0044444444444444444
415
+ name: Cosine Precision@1
416
+ - type: cosine_precision@3
417
+ value: 0.007407407407407408
418
+ name: Cosine Precision@3
419
+ - type: cosine_precision@5
420
+ value: 0.006444444444444445
421
+ name: Cosine Precision@5
422
+ - type: cosine_precision@10
423
+ value: 0.005888888888888889
424
+ name: Cosine Precision@10
425
+ - type: cosine_recall@1
426
+ value: 0.0044444444444444444
427
+ name: Cosine Recall@1
428
+ - type: cosine_recall@3
429
+ value: 0.022222222222222223
430
+ name: Cosine Recall@3
431
+ - type: cosine_recall@5
432
+ value: 0.03222222222222222
433
+ name: Cosine Recall@5
434
+ - type: cosine_recall@10
435
+ value: 0.058888888888888886
436
+ name: Cosine Recall@10
437
+ - type: cosine_ndcg@10
438
+ value: 0.026545597896367828
439
+ name: Cosine Ndcg@10
440
+ - type: cosine_mrr@10
441
+ value: 0.01687301587301587
442
+ name: Cosine Mrr@10
443
+ - type: cosine_map@100
444
+ value: 0.03124441518498264
445
+ name: Cosine Map@100
446
+ ---
447
+
448
+ # BGE base En version 1
449
+
450
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
451
+
452
+ ## Model Details
453
+
454
+ ### Model Description
455
+ - **Model Type:** Sentence Transformer
456
+ - **Base model:** [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) <!-- at revision b737bf5dcc6ee8bdc530531266b4804a5d77b5d8 -->
457
+ - **Maximum Sequence Length:** 512 tokens
458
+ - **Output Dimensionality:** 768 tokens
459
+ - **Similarity Function:** Cosine Similarity
460
+ <!-- - **Training Dataset:** Unknown -->
461
+ - **Language:** en
462
+ - **License:** apache-2.0
463
+
464
+ ### Model Sources
465
+
466
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
467
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
468
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
469
+
470
+ ### Full Model Architecture
471
+
472
+ ```
473
+ SentenceTransformer(
474
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
475
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
476
+ (2): Normalize()
477
+ )
478
+ ```
479
+
480
+ ## Usage
481
+
482
+ ### Direct Usage (Sentence Transformers)
483
+
484
+ First install the Sentence Transformers library:
485
+
486
+ ```bash
487
+ pip install -U sentence-transformers
488
+ ```
489
+
490
+ Then you can load this model and run inference.
491
+ ```python
492
+ from sentence_transformers import SentenceTransformer
493
+
494
+ # Download from the 🤗 Hub
495
+ model = SentenceTransformer("RishuD7/bge-base-en-41-keys-phase-2-v1")
496
+ # Run inference
497
+ sentences = [
498
+ '13.2 We accept liability to the extent arising from our negligence, breach of contract or nbn™ Activities: (a) for any personal injury or death to you or your Personnel resulting from the supply of the Services; (b) for any damage to your real or tangible property resulting from the supply of the Services, but we limit our liability to our choice of repairing or replacing the property or paying the cost of repairing or replacing it; or (c) unless clause 13.1 applies, for any other cost or expense you reasonably incur that is a direct result of and flows naturally from, our breach of contract, negligence or nbn™ Activities (but TELSTRA CORPORATION LIMITED (ABN 33 051 775 556) | PAGE 6 OF 25 DocuSign Envelope ID: 3EE2487C-8AA0-42DB-8C95-FD658789EC41 CONFIDENTIAL excluding loss of profits, revenue, business opportunities, likely savings and data), and our liability under this clause is limited for all claims in aggregate to the total amount payable to us under this Agreement during the first year of this Agreement.\n Intellectual Property Rights means all current and future registered rights in respect of copyright,\n designs, circuit layouts, trademarks, trade secrets, domain names, database rights, know-how and\n confidential information and any other intellectual property rights as defined by Article 2 of the World\n Intellectual Property Organisation Convention of July 1967, excluding patents.\n nbn™ means nbn co limited (ABN 86 136 533 741), as that company exists from time to time.\n nbn™ Activities means nbn™ Equipment and nbn™’s negligent or wilful acts or omissions in\n connection with the Services.\n nbn™ Equipment means any equipment that is owned, operated or controlled by nbn™.\n nbn™ Service means a Service that is supplied by or using nbn™ or nbn™ Equipment.\n.\n Our Customer Terms means the Standard Form of Agreement formulated by Telstra for the purposes\n of Part 23 of the Act, as amended by us from time to time in accordance with the Act.\n.\n Personnel means a person’s officers, employees, agents, contractors and sub-contractors and in our\n case includes our Related Bodies Corporate.\n.\n Planned Maintenance has the meaning in clause 10.1.\n.\n Related Bodies Corporate has the meaning given under the Corporations Act 2001 (Cth).\n.\n Service means a service under this Agreement set out or referred to in a Service Schedule or an\n agreed statement of work, and includes any individual service or component which constitutes the\n service.\n.\n Service Order Form means an agreed:\n (a) application or order form for a new Service or to vary, reconfigure, renew, reconfigure or\n cancel an existing Service; or\n (b) statement of work between the parties for services under a Service Schedule or otherwise.\n.\n TELSTRA CORPORATION LIMITED (ABN 33 051 775 556) | PAGE 10 OF 25\nDocuSign Envelope ID: 3EE2487C-8AA0-42DB-8C95-FD658789EC41\n CONFIDENTIAL\n Service Schedules means the Schedules attached or added to these Agreement Terms for a\n Service.\n',
499
+ 'Absolute Maximum Amount of Liability',
500
+ 'Late Payment Charges',
501
+ ]
502
+ embeddings = model.encode(sentences)
503
+ print(embeddings.shape)
504
+ # [3, 768]
505
+
506
+ # Get the similarity scores for the embeddings
507
+ similarities = model.similarity(embeddings, embeddings)
508
+ print(similarities.shape)
509
+ # [3, 3]
510
+ ```
511
+
512
+ <!--
513
+ ### Direct Usage (Transformers)
514
+
515
+ <details><summary>Click to see the direct usage in Transformers</summary>
516
+
517
+ </details>
518
+ -->
519
+
520
+ <!--
521
+ ### Downstream Usage (Sentence Transformers)
522
+
523
+ You can finetune this model on your own dataset.
524
+
525
+ <details><summary>Click to expand</summary>
526
+
527
+ </details>
528
+ -->
529
+
530
+ <!--
531
+ ### Out-of-Scope Use
532
+
533
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
534
+ -->
535
+
536
+ ## Evaluation
537
+
538
+ ### Metrics
539
+
540
+ #### Information Retrieval
541
+ * Dataset: `dim_768`
542
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
543
+
544
+ | Metric | Value |
545
+ |:--------------------|:-----------|
546
+ | cosine_accuracy@1 | 0.0078 |
547
+ | cosine_accuracy@3 | 0.0189 |
548
+ | cosine_accuracy@5 | 0.03 |
549
+ | cosine_accuracy@10 | 0.0522 |
550
+ | cosine_precision@1 | 0.0078 |
551
+ | cosine_precision@3 | 0.0063 |
552
+ | cosine_precision@5 | 0.006 |
553
+ | cosine_precision@10 | 0.0052 |
554
+ | cosine_recall@1 | 0.0078 |
555
+ | cosine_recall@3 | 0.0189 |
556
+ | cosine_recall@5 | 0.03 |
557
+ | cosine_recall@10 | 0.0522 |
558
+ | cosine_ndcg@10 | 0.0252 |
559
+ | cosine_mrr@10 | 0.0172 |
560
+ | **cosine_map@100** | **0.0312** |
561
+
562
+ #### Information Retrieval
563
+ * Dataset: `dim_512`
564
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
565
+
566
+ | Metric | Value |
567
+ |:--------------------|:-----------|
568
+ | cosine_accuracy@1 | 0.0067 |
569
+ | cosine_accuracy@3 | 0.02 |
570
+ | cosine_accuracy@5 | 0.0289 |
571
+ | cosine_accuracy@10 | 0.0556 |
572
+ | cosine_precision@1 | 0.0067 |
573
+ | cosine_precision@3 | 0.0067 |
574
+ | cosine_precision@5 | 0.0058 |
575
+ | cosine_precision@10 | 0.0056 |
576
+ | cosine_recall@1 | 0.0067 |
577
+ | cosine_recall@3 | 0.02 |
578
+ | cosine_recall@5 | 0.0289 |
579
+ | cosine_recall@10 | 0.0556 |
580
+ | cosine_ndcg@10 | 0.0257 |
581
+ | cosine_mrr@10 | 0.0169 |
582
+ | **cosine_map@100** | **0.0305** |
583
+
584
+ #### Information Retrieval
585
+ * Dataset: `dim_256`
586
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
587
+
588
+ | Metric | Value |
589
+ |:--------------------|:-----------|
590
+ | cosine_accuracy@1 | 0.0067 |
591
+ | cosine_accuracy@3 | 0.0178 |
592
+ | cosine_accuracy@5 | 0.0278 |
593
+ | cosine_accuracy@10 | 0.0544 |
594
+ | cosine_precision@1 | 0.0067 |
595
+ | cosine_precision@3 | 0.0059 |
596
+ | cosine_precision@5 | 0.0056 |
597
+ | cosine_precision@10 | 0.0054 |
598
+ | cosine_recall@1 | 0.0067 |
599
+ | cosine_recall@3 | 0.0178 |
600
+ | cosine_recall@5 | 0.0278 |
601
+ | cosine_recall@10 | 0.0544 |
602
+ | cosine_ndcg@10 | 0.0255 |
603
+ | cosine_mrr@10 | 0.0169 |
604
+ | **cosine_map@100** | **0.0314** |
605
+
606
+ #### Information Retrieval
607
+ * Dataset: `dim_128`
608
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
609
+
610
+ | Metric | Value |
611
+ |:--------------------|:-----------|
612
+ | cosine_accuracy@1 | 0.0033 |
613
+ | cosine_accuracy@3 | 0.0178 |
614
+ | cosine_accuracy@5 | 0.0278 |
615
+ | cosine_accuracy@10 | 0.0633 |
616
+ | cosine_precision@1 | 0.0033 |
617
+ | cosine_precision@3 | 0.0059 |
618
+ | cosine_precision@5 | 0.0056 |
619
+ | cosine_precision@10 | 0.0063 |
620
+ | cosine_recall@1 | 0.0033 |
621
+ | cosine_recall@3 | 0.0178 |
622
+ | cosine_recall@5 | 0.0278 |
623
+ | cosine_recall@10 | 0.0633 |
624
+ | cosine_ndcg@10 | 0.0269 |
625
+ | cosine_mrr@10 | 0.0161 |
626
+ | **cosine_map@100** | **0.0301** |
627
+
628
+ #### Information Retrieval
629
+ * Dataset: `dim_64`
630
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
631
+
632
+ | Metric | Value |
633
+ |:--------------------|:-----------|
634
+ | cosine_accuracy@1 | 0.0044 |
635
+ | cosine_accuracy@3 | 0.0222 |
636
+ | cosine_accuracy@5 | 0.0322 |
637
+ | cosine_accuracy@10 | 0.0589 |
638
+ | cosine_precision@1 | 0.0044 |
639
+ | cosine_precision@3 | 0.0074 |
640
+ | cosine_precision@5 | 0.0064 |
641
+ | cosine_precision@10 | 0.0059 |
642
+ | cosine_recall@1 | 0.0044 |
643
+ | cosine_recall@3 | 0.0222 |
644
+ | cosine_recall@5 | 0.0322 |
645
+ | cosine_recall@10 | 0.0589 |
646
+ | cosine_ndcg@10 | 0.0265 |
647
+ | cosine_mrr@10 | 0.0169 |
648
+ | **cosine_map@100** | **0.0312** |
649
+
650
+ <!--
651
+ ## Bias, Risks and Limitations
652
+
653
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
654
+ -->
655
+
656
+ <!--
657
+ ### Recommendations
658
+
659
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
660
+ -->
661
+
662
+ ## Training Details
663
+
664
+ ### Training Dataset
665
+
666
+ #### Unnamed Dataset
667
+
668
+
669
+ * Size: 4,894 training samples
670
+ * Columns: <code>positive</code> and <code>anchor</code>
671
+ * Approximate statistics based on the first 1000 samples:
672
+ | | positive | anchor |
673
+ |:--------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
674
+ | type | string | string |
675
+ | details | <ul><li>min: 123 tokens</li><li>mean: 353.07 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.37 tokens</li><li>max: 8 tokens</li></ul> |
676
+ * Samples:
677
+ | positive | anchor |
678
+ |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------|
679
+ | <code>In no event shall CBRE, Client, or their respective affiliates incur liability under this agreement or otherwise relating to the Services beyond the insurance proceeds available with respect to the particular matter under the Insurance Policies required to be carried by CBRE AND Client under Article 6 above including, if applicable, proceeds of self-insurance. Each party shall and shall cause its affiliates to look solely to such insurance proceeds (and any such proceeds paid through self-insurance) to satisfy its claims against the released parties and agrees that it shall have no right of recovery beyond such proceeds; provided, however, that if insurance proceeds under such policies are not paid because a party has failed to maintain such policies, comply with policy requirements or, in the case of self-insurance, unreasonably denied a claim, such party shall be liable for the amounts that otherwise would have been payable under such policies had such party maintained such policies, complied with the policy requirement or not unreasonably denied such claim, as the case may be.</code> | <code>Absolute Maximum Amount of Liability</code> |
680
+ | <code>4. Rent. <br>4.01 From and after the Commencement Date, Tenant shall pay Landlord, without any<br>setoff or deduction, unless expressly set forth in this Lease, all Base Rent and Additional Rent<br>due for the Term (collectively referred to as "Rent"). "Additional Rent" means all sums<br>(exclusive of Base Rent) that Tenant is required to pay Landlord under this Lease. Tenant shall<br>pay and be liable for all rental, sales and use taxes (but excluding income taxes), if any,<br>imposed upon or measured by Rent. Base Rent and recurring monthly charges of Additional<br>Rent shall be due and payable in advance on the first day of each calendar month without<br>notice or demand, provided that the installment of Base Rent attributable to the first (1st) full<br>calendar month of the Term following the Abatement Period shall be due concurrently with the<br>execution of this Lease by Tenant. All other items of Rent shall be due and payable on or<br>before thirty (30) days after billing by Landlord. Rent shall be made payable to the entity, and<br>sent to the address, that Landlord designates and shall be made by good and sufficient check or<br>by other means acceptable to Landlord. Landlord may return to Tenant, at any time within<br>fifteen (15) days after receiving same, any payment of Rent (a) made following any Default<br>(irrespective of whether Landlord has commenced the exercise of any remedy), or (b) that is<br>less than the amount due. Each such returned payment (whether made by returning Tenant's<br>actual check, or by issuing a refund in the event Tenant's check was deposited) shall be<br>conclusively presumed not to have been received or approved by Landlord. If Tenant does not<br>pay any Rent when due hereunder, Tenant shall pay Landlord an administration fee in the<br>amount of five percent (5%) of the past due amount. In addition, past due Rent shall accrue<br>interest at a rate equal to the lesser of (i) twelve percent (12%) per annum or (ii) the maximum<br>legal rate, and Tenant shall pay Landlord a fee for any checks returned by Tenant's bank for<br>any reason. Notwithstanding the foregoing, no such late charge or of interest shall be imposed<br>with respect to the first (1st) late payment in any calendar year, but not with respect to more<br>than three (3) such late payments during the initial Term of this Lease. </code> | <code>Late Payment Charges</code> |
681
+ | <code>Term This Agreement shall come into force and shall last unlimited from such date. Either Party may however terminate this Agreement at any time by giving upon thirty (30) days' written notice to the other Party. The Receiving Party's obligations contained in this Agreement to keep confidential and restrict use of the Disclosing Party's Confidential Information shall sur- vive for a period of five (5) years from the date of its termination for any reason whatsoever. lX. Contractual penalty<br>For the purposes of this Non-Disclosure Agreement, " Confidential Information" includes all technical and/or commercial and/or financial information in the field designated in section 1., which a contracting Party (hereinafter referred to as the "EQ€i1gPedy") makes, or has made, accessible to the other contracting Party (hereinafter referred to as the ".&eiyi!g Partv") in oral, written, tangible or other form (e.9. disk, data carrier) directly or indirectly, in- cluding but not limited to, drawings, models, components, and other material. Confidential In- formation is to be identified as such. Orally communicated or visually, information having been designated as confidential at the time of disclosure will be confirmed as such in writing by the Disclosing Party within 30 (thirty) days from such disclosure being understood thatlhe ./A information will be considered Confidential Information during that period of 30 (thirty) days. /L t'-4 PF 0233 (September 2016) page 1 of 5 ä =.<br> PFEIFFER F<br>.<br> F<br>.<br> VACUUM<br></code> | <code>Termination for Convenience</code> |
682
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
683
+ ```json
684
+ {
685
+ "loss": "MultipleNegativesRankingLoss",
686
+ "matryoshka_dims": [
687
+ 768,
688
+ 512,
689
+ 256,
690
+ 128,
691
+ 64
692
+ ],
693
+ "matryoshka_weights": [
694
+ 1,
695
+ 1,
696
+ 1,
697
+ 1,
698
+ 1
699
+ ],
700
+ "n_dims_per_step": -1
701
+ }
702
+ ```
703
+
704
+ ### Training Hyperparameters
705
+ #### Non-Default Hyperparameters
706
+
707
+ - `eval_strategy`: epoch
708
+ - `per_device_train_batch_size`: 32
709
+ - `per_device_eval_batch_size`: 16
710
+ - `gradient_accumulation_steps`: 16
711
+ - `learning_rate`: 2e-05
712
+ - `num_train_epochs`: 30
713
+ - `lr_scheduler_type`: cosine
714
+ - `warmup_ratio`: 0.1
715
+ - `tf32`: False
716
+ - `load_best_model_at_end`: True
717
+ - `optim`: adamw_torch_fused
718
+ - `batch_sampler`: no_duplicates
719
+
720
+ #### All Hyperparameters
721
+ <details><summary>Click to expand</summary>
722
+
723
+ - `overwrite_output_dir`: False
724
+ - `do_predict`: False
725
+ - `eval_strategy`: epoch
726
+ - `prediction_loss_only`: True
727
+ - `per_device_train_batch_size`: 32
728
+ - `per_device_eval_batch_size`: 16
729
+ - `per_gpu_train_batch_size`: None
730
+ - `per_gpu_eval_batch_size`: None
731
+ - `gradient_accumulation_steps`: 16
732
+ - `eval_accumulation_steps`: None
733
+ - `learning_rate`: 2e-05
734
+ - `weight_decay`: 0.0
735
+ - `adam_beta1`: 0.9
736
+ - `adam_beta2`: 0.999
737
+ - `adam_epsilon`: 1e-08
738
+ - `max_grad_norm`: 1.0
739
+ - `num_train_epochs`: 30
740
+ - `max_steps`: -1
741
+ - `lr_scheduler_type`: cosine
742
+ - `lr_scheduler_kwargs`: {}
743
+ - `warmup_ratio`: 0.1
744
+ - `warmup_steps`: 0
745
+ - `log_level`: passive
746
+ - `log_level_replica`: warning
747
+ - `log_on_each_node`: True
748
+ - `logging_nan_inf_filter`: True
749
+ - `save_safetensors`: True
750
+ - `save_on_each_node`: False
751
+ - `save_only_model`: False
752
+ - `restore_callback_states_from_checkpoint`: False
753
+ - `no_cuda`: False
754
+ - `use_cpu`: False
755
+ - `use_mps_device`: False
756
+ - `seed`: 42
757
+ - `data_seed`: None
758
+ - `jit_mode_eval`: False
759
+ - `use_ipex`: False
760
+ - `bf16`: False
761
+ - `fp16`: False
762
+ - `fp16_opt_level`: O1
763
+ - `half_precision_backend`: auto
764
+ - `bf16_full_eval`: False
765
+ - `fp16_full_eval`: False
766
+ - `tf32`: False
767
+ - `local_rank`: 0
768
+ - `ddp_backend`: None
769
+ - `tpu_num_cores`: None
770
+ - `tpu_metrics_debug`: False
771
+ - `debug`: []
772
+ - `dataloader_drop_last`: False
773
+ - `dataloader_num_workers`: 0
774
+ - `dataloader_prefetch_factor`: None
775
+ - `past_index`: -1
776
+ - `disable_tqdm`: False
777
+ - `remove_unused_columns`: True
778
+ - `label_names`: None
779
+ - `load_best_model_at_end`: True
780
+ - `ignore_data_skip`: False
781
+ - `fsdp`: []
782
+ - `fsdp_min_num_params`: 0
783
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
784
+ - `fsdp_transformer_layer_cls_to_wrap`: None
785
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
786
+ - `deepspeed`: None
787
+ - `label_smoothing_factor`: 0.0
788
+ - `optim`: adamw_torch_fused
789
+ - `optim_args`: None
790
+ - `adafactor`: False
791
+ - `group_by_length`: False
792
+ - `length_column_name`: length
793
+ - `ddp_find_unused_parameters`: None
794
+ - `ddp_bucket_cap_mb`: None
795
+ - `ddp_broadcast_buffers`: False
796
+ - `dataloader_pin_memory`: True
797
+ - `dataloader_persistent_workers`: False
798
+ - `skip_memory_metrics`: True
799
+ - `use_legacy_prediction_loop`: False
800
+ - `push_to_hub`: False
801
+ - `resume_from_checkpoint`: None
802
+ - `hub_model_id`: None
803
+ - `hub_strategy`: every_save
804
+ - `hub_private_repo`: False
805
+ - `hub_always_push`: False
806
+ - `gradient_checkpointing`: False
807
+ - `gradient_checkpointing_kwargs`: None
808
+ - `include_inputs_for_metrics`: False
809
+ - `eval_do_concat_batches`: True
810
+ - `fp16_backend`: auto
811
+ - `push_to_hub_model_id`: None
812
+ - `push_to_hub_organization`: None
813
+ - `mp_parameters`:
814
+ - `auto_find_batch_size`: False
815
+ - `full_determinism`: False
816
+ - `torchdynamo`: None
817
+ - `ray_scope`: last
818
+ - `ddp_timeout`: 1800
819
+ - `torch_compile`: False
820
+ - `torch_compile_backend`: None
821
+ - `torch_compile_mode`: None
822
+ - `dispatch_batches`: None
823
+ - `split_batches`: None
824
+ - `include_tokens_per_second`: False
825
+ - `include_num_input_tokens_seen`: False
826
+ - `neftune_noise_alpha`: None
827
+ - `optim_target_modules`: None
828
+ - `batch_eval_metrics`: False
829
+ - `batch_sampler`: no_duplicates
830
+ - `multi_dataset_batch_sampler`: proportional
831
+
832
+ </details>
833
+
834
+ ### Training Logs
835
+ | Epoch | Step | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
836
+ |:----------:|:-------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
837
+ | 1.0458 | 10 | 12.4978 | - | - | - | - | - |
838
+ | 2.0915 | 20 | 2.7268 | - | - | - | - | - |
839
+ | 3.1373 | 30 | 0.4086 | - | - | - | - | - |
840
+ | 4.1830 | 40 | 0.0 | - | - | - | - | - |
841
+ | 5.0196 | 48 | - | 0.0241 | 0.0239 | 0.0253 | 0.0230 | 0.0262 |
842
+ | 1.1830 | 50 | 2.0561 | - | - | - | - | - |
843
+ | 2.2288 | 60 | 6.2679 | - | - | - | - | - |
844
+ | 3.2745 | 70 | 0.3579 | - | - | - | - | - |
845
+ | 4.3203 | 80 | 0.0246 | - | - | - | - | - |
846
+ | 5.3660 | 90 | 0.0 | - | - | - | - | - |
847
+ | 5.9935 | 96 | - | 0.0281 | 0.0267 | 0.0274 | 0.0285 | 0.0266 |
848
+ | 2.3660 | 100 | 2.5882 | - | - | - | - | - |
849
+ | 3.4118 | 110 | 2.67 | - | - | - | - | - |
850
+ | 4.4575 | 120 | 0.0818 | - | - | - | - | - |
851
+ | 5.5033 | 130 | 0.0023 | - | - | - | - | - |
852
+ | 6.5490 | 140 | 0.0 | - | - | - | - | - |
853
+ | **6.9673** | **144** | **-** | **0.0329** | **0.0302** | **0.0283** | **0.0326** | **0.0285** |
854
+ | 3.5490 | 150 | 2.7505 | - | - | - | - | - |
855
+ | 4.5948 | 160 | 1.1704 | - | - | - | - | - |
856
+ | 5.6405 | 170 | 0.0078 | - | - | - | - | - |
857
+ | 6.6863 | 180 | 0.0 | - | - | - | - | - |
858
+ | 7.7320 | 190 | 0.0 | - | - | - | - | - |
859
+ | 8.0458 | 193 | - | 0.0313 | 0.0297 | 0.0299 | 0.0299 | 0.0303 |
860
+ | 4.7320 | 200 | 2.8942 | - | - | - | - | - |
861
+ | 5.7778 | 210 | 0.3858 | - | - | - | - | - |
862
+ | 6.8235 | 220 | 0.0008 | - | - | - | - | - |
863
+ | 7.8693 | 230 | 0.0 | - | - | - | - | - |
864
+ | 8.9150 | 240 | 0.0 | - | - | - | - | - |
865
+ | 9.0196 | 241 | - | 0.0307 | 0.0307 | 0.0299 | 0.0311 | 0.0313 |
866
+ | 5.9150 | 250 | 3.0125 | - | - | - | - | - |
867
+ | 6.9608 | 260 | 0.0374 | - | - | - | - | - |
868
+ | 8.0065 | 270 | 0.0002 | 0.0301 | 0.0314 | 0.0305 | 0.0312 | 0.0312 |
869
+
870
+ * The bold row denotes the saved checkpoint.
871
+
872
+ ### Framework Versions
873
+ - Python: 3.10.12
874
+ - Sentence Transformers: 3.1.1
875
+ - Transformers: 4.41.2
876
+ - PyTorch: 2.1.2+cu121
877
+ - Accelerate: 0.34.2
878
+ - Datasets: 2.19.1
879
+ - Tokenizers: 0.19.1
880
+
881
+ ## Citation
882
+
883
+ ### BibTeX
884
+
885
+ #### Sentence Transformers
886
+ ```bibtex
887
+ @inproceedings{reimers-2019-sentence-bert,
888
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
889
+ author = "Reimers, Nils and Gurevych, Iryna",
890
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
891
+ month = "11",
892
+ year = "2019",
893
+ publisher = "Association for Computational Linguistics",
894
+ url = "https://arxiv.org/abs/1908.10084",
895
+ }
896
+ ```
897
+
898
+ #### MatryoshkaLoss
899
+ ```bibtex
900
+ @misc{kusupati2024matryoshka,
901
+ title={Matryoshka Representation Learning},
902
+ author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
903
+ year={2024},
904
+ eprint={2205.13147},
905
+ archivePrefix={arXiv},
906
+ primaryClass={cs.LG}
907
+ }
908
+ ```
909
+
910
+ #### MultipleNegativesRankingLoss
911
+ ```bibtex
912
+ @misc{henderson2017efficient,
913
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
914
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
915
+ year={2017},
916
+ eprint={1705.00652},
917
+ archivePrefix={arXiv},
918
+ primaryClass={cs.CL}
919
+ }
920
+ ```
921
+
922
+ <!--
923
+ ## Glossary
924
+
925
+ *Clearly define terms in order to be accessible across audiences.*
926
+ -->
927
+
928
+ <!--
929
+ ## Model Card Authors
930
+
931
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
932
+ -->
933
+
934
+ <!--
935
+ ## Model Card Contact
936
+
937
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
938
+ -->
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BAAI/bge-base-en",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.41.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30522
32
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.1.1",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.1.2+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4befeaadea8bc1f8462be74b398354c88a2d2e54778b649da104781c6ac372bb
3
+ size 437951328
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": true
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff