IoannisKat1 commited on
Commit
3d08814
·
verified ·
1 Parent(s): 6a74bd2

Add finetuned model

Browse files
README.md CHANGED
The diff for this file is too large to render. See raw diff
 
checkpoint-98/1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
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
+ }
checkpoint-98/README.md ADDED
@@ -0,0 +1,1539 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - sentence-transformers
7
+ - sentence-similarity
8
+ - feature-extraction
9
+ - dense
10
+ - generated_from_trainer
11
+ - dataset_size:391
12
+ - loss:MatryoshkaLoss
13
+ - loss:MultipleNegativesRankingLoss
14
+ base_model: nomic-ai/modernbert-embed-base
15
+ widget:
16
+ - source_sentence: What does 'personal data breach' entail?
17
+ sentences:
18
+ - '1.Processing of personal data revealing racial or ethnic origin, political opinions,
19
+ religious or philosophical beliefs, or trade union membership, and the processing
20
+ of genetic data, biometric data for the purpose of uniquely identifying a natural
21
+ person, data concerning health or data concerning a natural person''s sex life
22
+ or sexual orientation shall be prohibited.
23
+
24
+ 2.Paragraph 1 shall not apply if one of the following applies: (a) the data subject
25
+ has given explicit consent to the processing of those personal data for one or
26
+ more specified purposes, except where Union or Member State law provide that the
27
+ prohibition referred to in paragraph 1 may not be lifted by the data subject;
28
+ (b) processing is necessary for the purposes of carrying out the obligations
29
+ and exercising specific rights of the controller or of the data subject in the
30
+ field of employment and social security and social protection law in so far as
31
+ it is authorised by Union or Member State law or a collective agreement pursuant
32
+ to Member State law providing for appropriate safeguards for the fundamental rights
33
+ and the interests of the data subject; (c) processing is necessary to protect
34
+ the vital interests of the data subject or of another natural person where the
35
+ data subject is physically or legally incapable of giving consent; (d) processing
36
+ is carried out in the course of its legitimate activities with appropriate safeguards
37
+ by a foundation, association or any other not-for-profit body with a political,
38
+ philosophical, religious or trade union aim and on condition that the processing
39
+ relates solely to the members or to former members of the body or to persons who
40
+ have regular contact with it in connection with its purposes and that the personal
41
+ data are not disclosed outside that body without the consent of the data subjects;
42
+ (e) processing relates to personal data which are manifestly made public by the
43
+ data subject; (f) processing is necessary for the establishment, exercise or
44
+ defence of legal claims or whenever courts are acting in their judicial capacity;
45
+ (g) processing is necessary for reasons of substantial public interest, on the
46
+ basis of Union or Member State law which shall be proportionate to the aim pursued,
47
+ respect the essence of the right to data protection and provide for suitable and
48
+ specific measures to safeguard the fundamental rights and the interests of the
49
+ data subject; (h) processing is necessary for the purposes of preventive or occupational
50
+ medicine, for the assessment of the working capacity of the employee, medical
51
+ diagnosis, the provision of health or social care or treatment or the management
52
+ of health or social care systems and services on the basis of Union or Member
53
+ State law or pursuant to contract with a health professional and subject to the
54
+ conditions and safeguards referred to in paragraph 3; (i) processing is necessary
55
+ for reasons of public interest in the area of public health, such as protecting
56
+ against serious cross-border threats to health or ensuring high standards of quality
57
+ and safety of health care and of medicinal products or medical devices, on the
58
+ basis of Union or Member State law which provides for suitable and specific measures
59
+ to safeguard the rights and freedoms of the data subject, in particular professional
60
+ secrecy; 4.5.2016 L 119/38 (j) processing is necessary for archiving purposes
61
+ in the public interest, scientific or historical research purposes or statistical
62
+ purposes in accordance with Article 89(1) based on Union or Member State law which
63
+ shall be proportionate to the aim pursued, respect the essence of the right to
64
+ data protection and provide for suitable and specific measures to safeguard the
65
+ fundamental rights and the interests of the data subject.
66
+
67
+ 3.Personal data referred to in paragraph 1 may be processed for the purposes referred
68
+ to in point (h) of paragraph 2 when those data are processed by or under the responsibility
69
+ of a professional subject to the obligation of professional secrecy under Union
70
+ or Member State law or rules established by national competent bodies or by another
71
+ person also subject to an obligation of secrecy under Union or Member State law
72
+ or rules established by national competent bodies.
73
+
74
+ 4.Member States may maintain or introduce further conditions, including limitations,
75
+ with regard to the processing of genetic data, biometric data or data concerning
76
+ health.'
77
+ - '1) ''personal data'' means any information relating to an identified or identifiable
78
+ natural person (''data subject''); an identifiable natural person is one who can
79
+ be identified, directly or indirectly, in particular by reference to an identifier
80
+ such as a name, an identification number, location data, an online identifier
81
+ or to one or more factors specific to the physical, physiological, genetic, mental,
82
+ economic, cultural or social identity of that natural person;
83
+
84
+ (2) ‘processing’ means any operation or set of operations which is performed on
85
+ personal data or on sets of personal data, whether or not by automated means,
86
+ such as collection, recording, organisation, structuring, storage, adaptation
87
+ or alteration, retrieval, consultation, use, disclosure by transmission, dissemination
88
+ or otherwise making available, alignment or combination, restriction, erasure
89
+ or destruction;
90
+
91
+ (3) ‘restriction of processing’ means the marking of stored personal data with
92
+ the aim of limiting their processing in the future;
93
+
94
+ (4) ‘profiling’ means any form of automated processing of personal data consisting
95
+ of the use of personal data to evaluate certain personal aspects relating to a
96
+ natural person, in particular to analyse or predict aspects concerning that natural
97
+ person''s performance at work, economic situation, health, personal preferences,
98
+ interests, reliability, behaviour, location or movements;
99
+
100
+ (5) ‘pseudonymisation’ means the processing of personal data in such a manner
101
+ that the personal data can no longer be attributed to a specific data subject
102
+ without the use of additional information, provided that such additional information
103
+ is kept separately and is subject to technical and organisational measures to
104
+ ensure that the personal data are not attributed to an identified or identifiable
105
+ natural person;
106
+
107
+ (6) ‘filing system’ means any structured set of personal data which are accessible
108
+ according to specific criteria, whether centralised, decentralised or dispersed
109
+ on a functional or geographical basis;
110
+
111
+ (7) ‘controller’ means the natural or legal person, public authority, agency or
112
+ other body which, alone or jointly with others, determines the purposes and means
113
+ of the processing of personal data; where the purposes and means of such processing
114
+ are determined by Union or Member State law, the controller or the specific criteria
115
+ for its nomination may be provided for by Union or Member State law;
116
+
117
+ (8) ‘processor’ means a natural or legal person, public authority, agency or other
118
+ body which processes personal data on behalf of the controller;
119
+
120
+ (9) ‘recipient’ means a natural or legal person, public authority, agency or another
121
+ body, to which the personal data are disclosed, whether a third party or not.
122
+ However, public authorities which may receive personal data in the framework of
123
+ a particular inquiry in accordance with Union or Member State law shall not be
124
+ regarded as recipients; the processing of those data by those public authorities
125
+ shall be in compliance with the applicable data protection rules according to
126
+ the purposes of the processing;
127
+
128
+ (10) ‘third party’ means a natural or legal person, public authority, agency or
129
+ body other than the data subject, controller, processor and persons who, under
130
+ the direct authority of the controller or processor, are authorised to process
131
+ personal data;
132
+
133
+ (11) ‘consent’ of the data subject means any freely given, specific, informed
134
+ and unambiguous indication of the data subject''s wishes by which he or she, by
135
+ a statement or by a clear affirmative action, signifies agreement to the processing
136
+ of personal data relating to him or her;
137
+
138
+ (12) ‘personal data breach’ means a breach of security leading to the accidental
139
+ or unlawful destruction, loss, alteration, unauthorised disclosure of, or access
140
+ to, personal data transmitted, stored or otherwise processed;
141
+
142
+ (13) ‘genetic data’ means personal data relating to the inherited or acquired
143
+ genetic characteristics of a natural person which give unique information about
144
+ the physiology or the health of that natural person and which result, in particular,
145
+ from an analysis of a biological sample from the natural person in question;
146
+
147
+ (14) ‘biometric data’ means personal data resulting from specific technical processing
148
+ relating to the physical, physiological or behavioural characteristics of a natural
149
+ person, which allow or confirm the unique identification of that natural person,
150
+ such as facial images or dactyloscopic data;
151
+
152
+ (15) ‘data concerning health’ means personal data related to the physical or mental
153
+ health of a natural person, including the provision of health care services, which
154
+ reveal information about his or her health status;
155
+
156
+ (16) ‘main establishment’ means: (a) as regards a controller with establishments
157
+ in more than one Member State, the place of its central administration in the
158
+ Union, unless the decisions on the purposes and means of the processing of personal
159
+ data are taken in another establishment of the controller in the Union and the
160
+ latter establishment has the power to have such decisions implemented, in which
161
+ case the establishment having taken such decisions is to be considered to be the
162
+ main establishment; (b) as regards a processor with establishments in more than
163
+ one Member State, the place of its central administration in the Union, or, if
164
+ the processor has no central administration in the Union, the establishment of
165
+ the processor in the Union where the main processing activities in the context
166
+ of the activities of an establishment of the processor take place to the extent
167
+ that the processor is subject to specific obligations under this Regulation;
168
+
169
+ (17) ‘representative’ means a natural or legal person established in the Union
170
+ who, designated by the controller or processor in writing pursuant to Article
171
+ 27, represents the controller or processor with regard to their respective obligations
172
+ under this Regulation;
173
+
174
+ (18) ‘enterprise’ means a natural or legal person engaged in an economic activity,
175
+ irrespective of its legal form, including partnerships or associations regularly
176
+ engaged in an economic activity;
177
+
178
+ (19) ‘group of undertakings’ means a controlling undertaking and its controlled
179
+ undertakings;
180
+
181
+ (20) ‘binding corporate rules’ means personal data protection policies which are
182
+ adhered to by a controller or processor established on the territory of a Member
183
+ State for transfers or a set of transfers of personal data to a controller or
184
+ processor in one or more third countries within a group of undertakings, or group
185
+ of enterprises engaged in a joint economic activity;
186
+
187
+ (21) ‘supervisory authority’ means an independent public authority which is established
188
+ by a Member State pursuant to Article 51;
189
+
190
+ (22) ‘supervisory authority concerned’ means a supervisory authority which is
191
+ concerned by the processing of personal data because: (a) the controller or processor
192
+ is established on the territory of the Member State of that supervisory authority;
193
+ (b) data subjects residing in the Member State of that supervisory authority are
194
+ substantially affected or likely to be substantially affected by the processing;
195
+ or (c) a complaint has been lodged with that supervisory authority;
196
+
197
+ (23) ‘cross-border processing’ means either: (a) processing of personal data which
198
+ takes place in the context of the activities of establishments in more than one
199
+ Member State of a controller or processor in the Union where the controller or
200
+ processor is established in more than one Member State; or (b) processing of personal
201
+ data which takes place in the context of the activities of a single establishment
202
+ of a controller or processor in the Union but which substantially affects or is
203
+ likely to substantially affect data subjects in more than one Member State.
204
+
205
+ (24) ‘relevant and reasoned objection’ means an objection to a draft decision
206
+ as to whether there is an infringement of this Regulation, or whether envisaged
207
+ action in relation to the controller or processor complies with this Regulation,
208
+ which clearly demonstrates the significance of the risks posed by the draft decision
209
+ as regards the fundamental rights and freedoms of data subjects and, where applicable,
210
+ the free flow of personal data within the Union;
211
+
212
+ (25) ‘information society service’ means a service as defined in point (b) of
213
+ Article 1(1) of Directive (EU) 2015/1535 of the European Parliament and of the
214
+ Council (1);
215
+
216
+ (26) ‘international organisation’ means an organisation and its subordinate bodies
217
+ governed by public international law, or any other body which is set up by, or
218
+ on the basis of, an agreement between two or more countries.'
219
+ - Any processing of personal data should be lawful and fair. It should be transparent
220
+ to natural persons that personal data concerning them are collected, used, consulted
221
+ or otherwise processed and to what extent the personal data are or will be processed.
222
+ The principle of transparency requires that any information and communication
223
+ relating to the processing of those personal data be easily accessible and easy
224
+ to understand, and that clear and plain language be used. That principle concerns,
225
+ in particular, information to the data subjects on the identity of the controller
226
+ and the purposes of the processing and further information to ensure fair and
227
+ transparent processing in respect of the natural persons concerned and their right
228
+ to obtain confirmation and communication of personal data concerning them which
229
+ are being processed. Natural persons should be made aware of risks, rules, safeguards
230
+ and rights in relation to the processing of personal data and how to exercise
231
+ their rights in relation to such processing. In particular, the specific purposes
232
+ for which personal data are processed should be explicit and legitimate and determined
233
+ at the time of the collection of the personal data. The personal data should be
234
+ adequate, relevant and limited to what is necessary for the purposes for which
235
+ they are processed. This requires, in particular, ensuring that the period for
236
+ which the personal data are stored is limited to a strict minimum. Personal data
237
+ should be processed only if the purpose of the processing could not reasonably
238
+ be fulfilled by other means. In order to ensure that the personal data are not
239
+ kept longer than necessary, time limits should be established by the controller
240
+ for erasure or for a periodic review. Every reasonable step should be taken to
241
+ ensure that personal data which are inaccurate are rectified or deleted. Personal
242
+ data should be processed in a manner that ensures appropriate security and confidentiality
243
+ of the personal data, including for preventing unauthorised access to or use of
244
+ personal data and the equipment used for the processing.
245
+ - source_sentence: In what situations could providing information to the data subject
246
+ be considered impossible or involve a disproportionate effort?
247
+ sentences:
248
+ - '1.The controller shall consult the supervisory authority prior to processing
249
+ where a data protection impact assessment under Article 35 indicates that the
250
+ processing would result in a high risk in the absence of measures taken by the
251
+ controller to mitigate the risk.
252
+
253
+ 2.Where the supervisory authority is of the opinion that the intended processing
254
+ referred to in paragraph 1 would infringe this Regulation, in particular where
255
+ the controller has insufficiently identified or mitigated the risk, the supervisory
256
+ authority shall, within period of up to eight weeks of receipt of the request
257
+ for consultation, provide written advice to the controller and, where applicable
258
+ to the processor, and may use any of its powers referred to in Article 58. That
259
+ period may be extended by six weeks, taking into account the complexity of the
260
+ intended processing. The supervisory authority shall inform the controller and,
261
+ where applicable, the processor, of any such extension within one month of receipt
262
+ of the request for consultation together with the reasons for the delay. Those
263
+ periods may be suspended until the supervisory authority has obtained information
264
+ it has requested for the purposes of the consultation.
265
+
266
+ 3.When consulting the supervisory authority pursuant to paragraph 1, the controller
267
+ shall provide the supervisory authority with: (a) where applicable, the respective
268
+ responsibilities of the controller, joint controllers and processors involved
269
+ in the processing, in particular for processing within a group of undertakings;
270
+ (b) the purposes and means of the intended processing; (c) the measures and
271
+ safeguards provided to protect the rights and freedoms of data subjects pursuant
272
+ to this Regulation; (d) where applicable, the contact details of the data protection
273
+ officer; 4.5.2016 L 119/54 (e) the data protection impact assessment provided
274
+ for in Article 35; and (f) any other information requested by the supervisory
275
+ authority.
276
+
277
+ 4.Member States shall consult the supervisory authority during the preparation
278
+ of a proposal for a legislative measure to be adopted by a national parliament,
279
+ or of a regulatory measure based on such a legislative measure, which relates
280
+ to processing.
281
+
282
+ 5.Notwithstanding paragraph 1, Member State law may require controllers to consult
283
+ with, and obtain prior authorisation from, the supervisory authority in relation
284
+ to processing by a controller for the performance of a task carried out by the
285
+ controller in the public interest, including processing in relation to social
286
+ protection and public health'
287
+ - "1.The Member States, the supervisory authorities, the Board and the Commission\
288
+ \ shall encourage, in particular at Union level, the establishment of data protection\
289
+ \ certification mechanisms and of data protection seals and marks, for the purpose\
290
+ \ of demonstrating compliance with this Regulation of processing operations by\
291
+ \ controllers and processors. The specific needs of micro, small and medium-sized\
292
+ \ enterprises shall be taken into account. 4.5.2016 L 119/58 \n2.In addition\
293
+ \ to adherence by controllers or processors subject to this Regulation, data protection\
294
+ \ certification mechanisms, seals or marks approved pursuant to paragraph 5 of\
295
+ \ this Article may be established for the purpose of demonstrating the existence\
296
+ \ of appropriate safeguards provided by controllers or processors that are not\
297
+ \ subject to this Regulation pursuant to Article 3 within the framework of personal\
298
+ \ data transfers to third countries or international organisations under the terms\
299
+ \ referred to in point (f) of Article 46(2). Such controllers or processors shall\
300
+ \ make binding and enforceable commitments, via contractual or other legally binding\
301
+ \ instruments, to apply those appropriate safeguards, including with regard to\
302
+ \ the rights of data subjects.\n3.The certification shall be voluntary and available\
303
+ \ via a process that is transparent.\n4.A certification pursuant to this Article\
304
+ \ does not reduce the responsibility of the controller or the processor for compliance\
305
+ \ with this Regulation and is without prejudice to the tasks and powers of the\
306
+ \ supervisory authorities which are competent pursuant to Article 55 or 56\n5.A\
307
+ \ certification pursuant to this Article shall be issued by the certification\
308
+ \ bodies referred to in Article 43 or by the competent supervisory authority,\
309
+ \ on the basis of criteria approved by that competent supervisory authority pursuant\
310
+ \ to Article 58(3) or by the Board pursuant to Article 63. Where the criteria\
311
+ \ are approved by the Board, this may result in a common certification, the European\
312
+ \ Data Protection Seal.\n6.The controller or processor which submits its processing\
313
+ \ to the certification mechanism shall provide the certification body referred\
314
+ \ to in Article 43, or where applicable, the competent supervisory authority,\
315
+ \ with all information and access to its processing activities which are necessary\
316
+ \ to conduct the certification procedure.\n7.Certification shall be issued to\
317
+ \ a controller or processor for a maximum period of three years and may be renewed,\
318
+ \ under the same conditions, provided that the relevant requirements continue\
319
+ \ to be met. Certification shall be withdrawn, as applicable, by the certification\
320
+ \ bodies referred to in Article 43 or by the competent supervisory authority where\
321
+ \ the requirements for the certification are not or are no longer met.\n8.The\
322
+ \ Board shall collate all certification mechanisms and data protection seals and\
323
+ \ marks in a register and shall make them publicly available by any appropriate\
324
+ \ means."
325
+ - However, it is not necessary to impose the obligation to provide information where
326
+ the data subject already possesses the information, where the recording or disclosure
327
+ of the personal data is expressly laid down by law or where the provision of information
328
+ to the data subject proves to be impossible or would involve a disproportionate
329
+ effort. The latter could in particular be the case where processing is carried
330
+ out for archiving purposes in the public interest, scientific or historical research
331
+ purposes or statistical purposes. In that regard, the number of data subjects,
332
+ the age of the data and any appropriate safeguards adopted should be taken into
333
+ consideration.
334
+ - source_sentence: What is the data subject provided with prior to further processing
335
+ of personal data?
336
+ sentences:
337
+ - '1.Where personal data relating to a data subject are collected from the data
338
+ subject, the controller shall, at the time when personal data are obtained, provide
339
+ the data subject with all of the following information: (a) the identity and
340
+ the contact details of the controller and, where applicable, of the controller''s
341
+ representative; (b) the contact details of the data protection officer, where
342
+ applicable; (c) the purposes of the processing for which the personal data are
343
+ intended as well as the legal basis for the processing; 4.5.2016 L 119/40 (d) where
344
+ the processing is based on point (f) of Article 6(1), the legitimate interests
345
+ pursued by the controller or by a third party; (e) the recipients or categories
346
+ of recipients of the personal data, if any; (f) where applicable, the fact that
347
+ the controller intends to transfer personal data to a third country or international
348
+ organisation and the existence or absence of an adequacy decision by the Commission,
349
+ or in the case of transfers referred to in Article 46 or 47, or the second subparagraph
350
+ of Article 49(1), reference to the appropriate or suitable safeguards and the
351
+ means by which to obtain a copy of them or where they have been made available.
352
+
353
+ 2.In addition to the information referred to in paragraph 1, the controller shall,
354
+ at the time when personal data are obtained, provide the data subject with the
355
+ following further information necessary to ensure fair and transparent processing:
356
+ (a) the period for which the personal data will be stored, or if that is not
357
+ possible, the criteria used to determine that period; (b) the existence of the
358
+ right to request from the controller access to and rectification or erasure of
359
+ personal data or restriction of processing concerning the data subject or to object
360
+ to processing as well as the right to data portability; (c) where the processing
361
+ is based on point (a) of Article 6(1) or point (a) of Article 9(2), the existence
362
+ of the right to withdraw consent at any time, without affecting the lawfulness
363
+ of processing based on consent before its withdrawal; (d) the right to lodge
364
+ a complaint with a supervisory authority; (e) whether the provision of personal
365
+ data is a statutory or contractual requirement, or a requirement necessary to
366
+ enter into a contract, as well as whether the data subject is obliged to provide
367
+ the personal data and of the possible consequences of failure to provide such
368
+ data; (f) the existence of automated decision-making, including profiling, referred
369
+ to in Article 22(1) and (4) and, at least in those cases, meaningful information
370
+ about the logic involved, as well as the significance and the envisaged consequences
371
+ of such processing for the data subject.
372
+
373
+ 3.Where the controller intends to further process the personal data for a purpose
374
+ other than that for which the personal data were collected, the controller shall
375
+ provide the data subject prior to that further processing with information on
376
+ that other purpose and with any relevant further information as referred to in
377
+ paragraph 2
378
+
379
+ 4.Paragraphs 1, 2 and 3 shall not apply where and insofar as the data subject
380
+ already has the information.'
381
+ - This Regulation respects and does not prejudice the status under existing constitutional
382
+ law of churches and religious associations or communities in the Member States,
383
+ as recognised in Article 17 TFEU.
384
+ - '1) ''personal data'' means any information relating to an identified or identifiable
385
+ natural person (''data subject''); an identifiable natural person is one who can
386
+ be identified, directly or indirectly, in particular by reference to an identifier
387
+ such as a name, an identification number, location data, an online identifier
388
+ or to one or more factors specific to the physical, physiological, genetic, mental,
389
+ economic, cultural or social identity of that natural person;
390
+
391
+ (2) ‘processing’ means any operation or set of operations which is performed on
392
+ personal data or on sets of personal data, whether or not by automated means,
393
+ such as collection, recording, organisation, structuring, storage, adaptation
394
+ or alteration, retrieval, consultation, use, disclosure by transmission, dissemination
395
+ or otherwise making available, alignment or combination, restriction, erasure
396
+ or destruction;
397
+
398
+ (3) ‘restriction of processing’ means the marking of stored personal data with
399
+ the aim of limiting their processing in the future;
400
+
401
+ (4) ‘profiling’ means any form of automated processing of personal data consisting
402
+ of the use of personal data to evaluate certain personal aspects relating to a
403
+ natural person, in particular to analyse or predict aspects concerning that natural
404
+ person''s performance at work, economic situation, health, personal preferences,
405
+ interests, reliability, behaviour, location or movements;
406
+
407
+ (5) ‘pseudonymisation’ means the processing of personal data in such a manner
408
+ that the personal data can no longer be attributed to a specific data subject
409
+ without the use of additional information, provided that such additional information
410
+ is kept separately and is subject to technical and organisational measures to
411
+ ensure that the personal data are not attributed to an identified or identifiable
412
+ natural person;
413
+
414
+ (6) ‘filing system’ means any structured set of personal data which are accessible
415
+ according to specific criteria, whether centralised, decentralised or dispersed
416
+ on a functional or geographical basis;
417
+
418
+ (7) ‘controller’ means the natural or legal person, public authority, agency or
419
+ other body which, alone or jointly with others, determines the purposes and means
420
+ of the processing of personal data; where the purposes and means of such processing
421
+ are determined by Union or Member State law, the controller or the specific criteria
422
+ for its nomination may be provided for by Union or Member State law;
423
+
424
+ (8) ‘processor’ means a natural or legal person, public authority, agency or other
425
+ body which processes personal data on behalf of the controller;
426
+
427
+ (9) ‘recipient’ means a natural or legal person, public authority, agency or another
428
+ body, to which the personal data are disclosed, whether a third party or not.
429
+ However, public authorities which may receive personal data in the framework of
430
+ a particular inquiry in accordance with Union or Member State law shall not be
431
+ regarded as recipients; the processing of those data by those public authorities
432
+ shall be in compliance with the applicable data protection rules according to
433
+ the purposes of the processing;
434
+
435
+ (10) ‘third party’ means a natural or legal person, public authority, agency or
436
+ body other than the data subject, controller, processor and persons who, under
437
+ the direct authority of the controller or processor, are authorised to process
438
+ personal data;
439
+
440
+ (11) ‘consent’ of the data subject means any freely given, specific, informed
441
+ and unambiguous indication of the data subject''s wishes by which he or she, by
442
+ a statement or by a clear affirmative action, signifies agreement to the processing
443
+ of personal data relating to him or her;
444
+
445
+ (12) ‘personal data breach’ means a breach of security leading to the accidental
446
+ or unlawful destruction, loss, alteration, unauthorised disclosure of, or access
447
+ to, personal data transmitted, stored or otherwise processed;
448
+
449
+ (13) ‘genetic data’ means personal data relating to the inherited or acquired
450
+ genetic characteristics of a natural person which give unique information about
451
+ the physiology or the health of that natural person and which result, in particular,
452
+ from an analysis of a biological sample from the natural person in question;
453
+
454
+ (14) ‘biometric data’ means personal data resulting from specific technical processing
455
+ relating to the physical, physiological or behavioural characteristics of a natural
456
+ person, which allow or confirm the unique identification of that natural person,
457
+ such as facial images or dactyloscopic data;
458
+
459
+ (15) ‘data concerning health’ means personal data related to the physical or mental
460
+ health of a natural person, including the provision of health care services, which
461
+ reveal information about his or her health status;
462
+
463
+ (16) ‘main establishment’ means: (a) as regards a controller with establishments
464
+ in more than one Member State, the place of its central administration in the
465
+ Union, unless the decisions on the purposes and means of the processing of personal
466
+ data are taken in another establishment of the controller in the Union and the
467
+ latter establishment has the power to have such decisions implemented, in which
468
+ case the establishment having taken such decisions is to be considered to be the
469
+ main establishment; (b) as regards a processor with establishments in more than
470
+ one Member State, the place of its central administration in the Union, or, if
471
+ the processor has no central administration in the Union, the establishment of
472
+ the processor in the Union where the main processing activities in the context
473
+ of the activities of an establishment of the processor take place to the extent
474
+ that the processor is subject to specific obligations under this Regulation;
475
+
476
+ (17) ‘representative’ means a natural or legal person established in the Union
477
+ who, designated by the controller or processor in writing pursuant to Article
478
+ 27, represents the controller or processor with regard to their respective obligations
479
+ under this Regulation;
480
+
481
+ (18) ‘enterprise’ means a natural or legal person engaged in an economic activity,
482
+ irrespective of its legal form, including partnerships or associations regularly
483
+ engaged in an economic activity;
484
+
485
+ (19) ‘group of undertakings’ means a controlling undertaking and its controlled
486
+ undertakings;
487
+
488
+ (20) ‘binding corporate rules’ means personal data protection policies which are
489
+ adhered to by a controller or processor established on the territory of a Member
490
+ State for transfers or a set of transfers of personal data to a controller or
491
+ processor in one or more third countries within a group of undertakings, or group
492
+ of enterprises engaged in a joint economic activity;
493
+
494
+ (21) ‘supervisory authority’ means an independent public authority which is established
495
+ by a Member State pursuant to Article 51;
496
+
497
+ (22) ‘supervisory authority concerned’ means a supervisory authority which is
498
+ concerned by the processing of personal data because: (a) the controller or processor
499
+ is established on the territory of the Member State of that supervisory authority;
500
+ (b) data subjects residing in the Member State of that supervisory authority are
501
+ substantially affected or likely to be substantially affected by the processing;
502
+ or (c) a complaint has been lodged with that supervisory authority;
503
+
504
+ (23) ‘cross-border processing’ means either: (a) processing of personal data which
505
+ takes place in the context of the activities of establishments in more than one
506
+ Member State of a controller or processor in the Union where the controller or
507
+ processor is established in more than one Member State; or (b) processing of personal
508
+ data which takes place in the context of the activities of a single establishment
509
+ of a controller or processor in the Union but which substantially affects or is
510
+ likely to substantially affect data subjects in more than one Member State.
511
+
512
+ (24) ‘relevant and reasoned objection’ means an objection to a draft decision
513
+ as to whether there is an infringement of this Regulation, or whether envisaged
514
+ action in relation to the controller or processor complies with this Regulation,
515
+ which clearly demonstrates the significance of the risks posed by the draft decision
516
+ as regards the fundamental rights and freedoms of data subjects and, where applicable,
517
+ the free flow of personal data within the Union;
518
+
519
+ (25) ‘information society service’ means a service as defined in point (b) of
520
+ Article 1(1) of Directive (EU) 2015/1535 of the European Parliament and of the
521
+ Council (1);
522
+
523
+ (26) ‘international organisation’ means an organisation and its subordinate bodies
524
+ governed by public international law, or any other body which is set up by, or
525
+ on the basis of, an agreement between two or more countries.'
526
+ - source_sentence: What type of data may be processed for purposes related to point
527
+ (h) of paragraph 2?
528
+ sentences:
529
+ - '1.Processing of personal data revealing racial or ethnic origin, political opinions,
530
+ religious or philosophical beliefs, or trade union membership, and the processing
531
+ of genetic data, biometric data for the purpose of uniquely identifying a natural
532
+ person, data concerning health or data concerning a natural person''s sex life
533
+ or sexual orientation shall be prohibited.
534
+
535
+ 2.Paragraph 1 shall not apply if one of the following applies: (a) the data subject
536
+ has given explicit consent to the processing of those personal data for one or
537
+ more specified purposes, except where Union or Member State law provide that the
538
+ prohibition referred to in paragraph 1 may not be lifted by the data subject;
539
+ (b) processing is necessary for the purposes of carrying out the obligations
540
+ and exercising specific rights of the controller or of the data subject in the
541
+ field of employment and social security and social protection law in so far as
542
+ it is authorised by Union or Member State law or a collective agreement pursuant
543
+ to Member State law providing for appropriate safeguards for the fundamental rights
544
+ and the interests of the data subject; (c) processing is necessary to protect
545
+ the vital interests of the data subject or of another natural person where the
546
+ data subject is physically or legally incapable of giving consent; (d) processing
547
+ is carried out in the course of its legitimate activities with appropriate safeguards
548
+ by a foundation, association or any other not-for-profit body with a political,
549
+ philosophical, religious or trade union aim and on condition that the processing
550
+ relates solely to the members or to former members of the body or to persons who
551
+ have regular contact with it in connection with its purposes and that the personal
552
+ data are not disclosed outside that body without the consent of the data subjects;
553
+ (e) processing relates to personal data which are manifestly made public by the
554
+ data subject; (f) processing is necessary for the establishment, exercise or
555
+ defence of legal claims or whenever courts are acting in their judicial capacity;
556
+ (g) processing is necessary for reasons of substantial public interest, on the
557
+ basis of Union or Member State law which shall be proportionate to the aim pursued,
558
+ respect the essence of the right to data protection and provide for suitable and
559
+ specific measures to safeguard the fundamental rights and the interests of the
560
+ data subject; (h) processing is necessary for the purposes of preventive or occupational
561
+ medicine, for the assessment of the working capacity of the employee, medical
562
+ diagnosis, the provision of health or social care or treatment or the management
563
+ of health or social care systems and services on the basis of Union or Member
564
+ State law or pursuant to contract with a health professional and subject to the
565
+ conditions and safeguards referred to in paragraph 3; (i) processing is necessary
566
+ for reasons of public interest in the area of public health, such as protecting
567
+ against serious cross-border threats to health or ensuring high standards of quality
568
+ and safety of health care and of medicinal products or medical devices, on the
569
+ basis of Union or Member State law which provides for suitable and specific measures
570
+ to safeguard the rights and freedoms of the data subject, in particular professional
571
+ secrecy; 4.5.2016 L 119/38 (j) processing is necessary for archiving purposes
572
+ in the public interest, scientific or historical research purposes or statistical
573
+ purposes in accordance with Article 89(1) based on Union or Member State law which
574
+ shall be proportionate to the aim pursued, respect the essence of the right to
575
+ data protection and provide for suitable and specific measures to safeguard the
576
+ fundamental rights and the interests of the data subject.
577
+
578
+ 3.Personal data referred to in paragraph 1 may be processed for the purposes referred
579
+ to in point (h) of paragraph 2 when those data are processed by or under the responsibility
580
+ of a professional subject to the obligation of professional secrecy under Union
581
+ or Member State law or rules established by national competent bodies or by another
582
+ person also subject to an obligation of secrecy under Union or Member State law
583
+ or rules established by national competent bodies.
584
+
585
+ 4.Member States may maintain or introduce further conditions, including limitations,
586
+ with regard to the processing of genetic data, biometric data or data concerning
587
+ health.'
588
+ - '1.The data protection officer shall have at least the following tasks: (a) to
589
+ inform and advise the controller or the processor and the employees who carry
590
+ out processing of their obligations pursuant to this Regulation and to other Union
591
+ or Member State data protection provisions; (b) to monitor compliance with this
592
+ Regulation, with other Union or Member State data protection provisions and with
593
+ the policies of the controller or processor in relation to the protection of personal
594
+ data, including the assignment of responsibilities, awareness-raising and training
595
+ of staff involved in processing operations, and the related audits; (c) to provide
596
+ advice where requested as regards the data protection impact assessment and monitor
597
+ its performance pursuant to Article 35; (d) to cooperate with the supervisory
598
+ authority; (e) to act as the contact point for the supervisory authority on issues
599
+ relating to processing, including the prior consultation referred to in Article
600
+ 36, and to consult, where appropriate, with regard to any other matter.
601
+
602
+ 2.The data protection officer shall in the performance of his or her tasks have
603
+ due regard to the risk associated with processing operations, taking into account
604
+ the nature, scope, context and purposes of processing. Section 5 Codes of conduct
605
+ and certification'
606
+ - Processing should be lawful where it is necessary in the context of a contract
607
+ or the intention to enter into a contract.
608
+ - source_sentence: What may impede authorities in the discharge of their responsibilities
609
+ under Union law?
610
+ sentences:
611
+ - '1.The controller and the processor shall designate a data protection officer
612
+ in any case where: (a) the processing is carried out by a public authority or
613
+ body, except for courts acting in their judicial capacity; (b) the core activities
614
+ of the controller or the processor consist of processing operations which, by
615
+ virtue of their nature, their scope and/or their purposes, require regular and
616
+ systematic monitoring of data subjects on a large scale; or (c) the core activities
617
+ of the controller or the processor consist of processing on a large scale of special
618
+ categories of data pursuant to Article 9 and personal data relating to criminal
619
+ convictions and offences referred to in Article 10
620
+
621
+ 2.A group of undertakings may appoint a single data protection officer provided
622
+ that a data protection officer is easily accessible from each establishment.
623
+
624
+ 3.Where the controller or the processor is a public authority or body, a single
625
+ data protection officer may be designated for several such authorities or bodies,
626
+ taking account of their organisational structure and size.
627
+
628
+ 4.In cases other than those referred to in paragraph 1, the controller or processor
629
+ or associations and other bodies representing categories of controllers or processors
630
+ may or, where required by Union or Member State law shall, designate a data protection
631
+ officer. The data protection officer may act for such associations and other bodies
632
+ representing controllers or processors.
633
+
634
+ 5.The data protection officer shall be designated on the basis of professional
635
+ qualities and, in particular, expert knowledge of data protection law and practices
636
+ and the ability to fulfil the tasks referred to in Article 39
637
+
638
+ 6.The data protection officer may be a staff member of the controller or processor,
639
+ or fulfil the tasks on the basis of a service contract.
640
+
641
+ 7.The controller or the processor shall publish the contact details of the data
642
+ protection officer and communicate them to the supervisory authority.'
643
+ - This Regulation is without prejudice to international agreements concluded between
644
+ the Union and third countries regulating the transfer of personal data including
645
+ appropriate safeguards for the data subjects. Member States may conclude international
646
+ agreements which involve the transfer of personal data to third countries or international
647
+ organisations, as far as such agreements do not affect this Regulation or any
648
+ other provisions of Union law and include an appropriate level of protection for
649
+ the fundamental rights of the data subjects.
650
+ - The objectives and principles of Directive 95/46/EC remain sound, but it has not
651
+ prevented fragmentation in the implementation of data protection across the Union,
652
+ legal uncertainty or a widespread public perception that there are significant
653
+ risks to the protection of natural persons, in particular with regard to online
654
+ activity. Differences in the level of protection of the rights and freedoms of
655
+ natural persons, in particular the right to the protection of personal data, with
656
+ regard to the processing of personal data in the Member States may prevent the
657
+ free flow of personal data throughout the Union. Those differences may therefore
658
+ constitute an obstacle to the pursuit of economic activities at the level of the
659
+ Union, distort competition and impede authorities in the discharge of their responsibilities
660
+ under Union law. Such a difference in levels of protection is due to the existence
661
+ of differences in the implementation and application of Directive 95/46/EC.
662
+ pipeline_tag: sentence-similarity
663
+ library_name: sentence-transformers
664
+ metrics:
665
+ - cosine_accuracy@1
666
+ - cosine_accuracy@3
667
+ - cosine_accuracy@5
668
+ - cosine_accuracy@10
669
+ - cosine_precision@1
670
+ - cosine_precision@3
671
+ - cosine_precision@5
672
+ - cosine_precision@10
673
+ - cosine_recall@1
674
+ - cosine_recall@3
675
+ - cosine_recall@5
676
+ - cosine_recall@10
677
+ - cosine_ndcg@10
678
+ - cosine_mrr@10
679
+ - cosine_map@100
680
+ model-index:
681
+ - name: modernbert-embed-base
682
+ results:
683
+ - task:
684
+ type: information-retrieval
685
+ name: Information Retrieval
686
+ dataset:
687
+ name: dim 768
688
+ type: dim_768
689
+ metrics:
690
+ - type: cosine_accuracy@1
691
+ value: 0.4026888604353393
692
+ name: Cosine Accuracy@1
693
+ - type: cosine_accuracy@3
694
+ value: 0.4065300896286812
695
+ name: Cosine Accuracy@3
696
+ - type: cosine_accuracy@5
697
+ value: 0.4359795134443022
698
+ name: Cosine Accuracy@5
699
+ - type: cosine_accuracy@10
700
+ value: 0.469270166453265
701
+ name: Cosine Accuracy@10
702
+ - type: cosine_precision@1
703
+ value: 0.4026888604353393
704
+ name: Cosine Precision@1
705
+ - type: cosine_precision@3
706
+ value: 0.4016218523260776
707
+ name: Cosine Precision@3
708
+ - type: cosine_precision@5
709
+ value: 0.3929577464788732
710
+ name: Cosine Precision@5
711
+ - type: cosine_precision@10
712
+ value: 0.36241997439180534
713
+ name: Cosine Precision@10
714
+ - type: cosine_recall@1
715
+ value: 0.042158204863822595
716
+ name: Cosine Recall@1
717
+ - type: cosine_recall@3
718
+ value: 0.12340911592737758
719
+ name: Cosine Recall@3
720
+ - type: cosine_recall@5
721
+ value: 0.18693795146685696
722
+ name: Cosine Recall@5
723
+ - type: cosine_recall@10
724
+ value: 0.28222410577862556
725
+ name: Cosine Recall@10
726
+ - type: cosine_ndcg@10
727
+ value: 0.42608814635365755
728
+ name: Cosine Ndcg@10
729
+ - type: cosine_mrr@10
730
+ value: 0.41397348738898004
731
+ name: Cosine Mrr@10
732
+ - type: cosine_map@100
733
+ value: 0.48436770951404184
734
+ name: Cosine Map@100
735
+ - task:
736
+ type: information-retrieval
737
+ name: Information Retrieval
738
+ dataset:
739
+ name: dim 512
740
+ type: dim_512
741
+ metrics:
742
+ - type: cosine_accuracy@1
743
+ value: 0.39500640204865556
744
+ name: Cosine Accuracy@1
745
+ - type: cosine_accuracy@3
746
+ value: 0.39884763124199746
747
+ name: Cosine Accuracy@3
748
+ - type: cosine_accuracy@5
749
+ value: 0.42509603072983354
750
+ name: Cosine Accuracy@5
751
+ - type: cosine_accuracy@10
752
+ value: 0.4532650448143406
753
+ name: Cosine Accuracy@10
754
+ - type: cosine_precision@1
755
+ value: 0.39500640204865556
756
+ name: Cosine Precision@1
757
+ - type: cosine_precision@3
758
+ value: 0.393939393939394
759
+ name: Cosine Precision@3
760
+ - type: cosine_precision@5
761
+ value: 0.3846350832266325
762
+ name: Cosine Precision@5
763
+ - type: cosine_precision@10
764
+ value: 0.35102432778489123
765
+ name: Cosine Precision@10
766
+ - type: cosine_recall@1
767
+ value: 0.04167554612344552
768
+ name: Cosine Recall@1
769
+ - type: cosine_recall@3
770
+ value: 0.12185555036210068
771
+ name: Cosine Recall@3
772
+ - type: cosine_recall@5
773
+ value: 0.18440910016156958
774
+ name: Cosine Recall@5
775
+ - type: cosine_recall@10
776
+ value: 0.27558399878065315
777
+ name: Cosine Recall@10
778
+ - type: cosine_ndcg@10
779
+ value: 0.4154101738314148
780
+ name: Cosine Ndcg@10
781
+ - type: cosine_mrr@10
782
+ value: 0.4048785135052737
783
+ name: Cosine Mrr@10
784
+ - type: cosine_map@100
785
+ value: 0.47311757377710084
786
+ name: Cosine Map@100
787
+ - task:
788
+ type: information-retrieval
789
+ name: Information Retrieval
790
+ dataset:
791
+ name: dim 256
792
+ type: dim_256
793
+ metrics:
794
+ - type: cosine_accuracy@1
795
+ value: 0.3873239436619718
796
+ name: Cosine Accuracy@1
797
+ - type: cosine_accuracy@3
798
+ value: 0.39244558258642764
799
+ name: Cosine Accuracy@3
800
+ - type: cosine_accuracy@5
801
+ value: 0.4206145966709347
802
+ name: Cosine Accuracy@5
803
+ - type: cosine_accuracy@10
804
+ value: 0.4494238156209987
805
+ name: Cosine Accuracy@10
806
+ - type: cosine_precision@1
807
+ value: 0.3873239436619718
808
+ name: Cosine Precision@1
809
+ - type: cosine_precision@3
810
+ value: 0.3868971404182671
811
+ name: Cosine Precision@3
812
+ - type: cosine_precision@5
813
+ value: 0.37912932138284255
814
+ name: Cosine Precision@5
815
+ - type: cosine_precision@10
816
+ value: 0.348527528809219
817
+ name: Cosine Precision@10
818
+ - type: cosine_recall@1
819
+ value: 0.04023203819999771
820
+ name: Cosine Recall@1
821
+ - type: cosine_recall@3
822
+ value: 0.1180462190143581
823
+ name: Cosine Recall@3
824
+ - type: cosine_recall@5
825
+ value: 0.17956095699785507
826
+ name: Cosine Recall@5
827
+ - type: cosine_recall@10
828
+ value: 0.27112137316286944
829
+ name: Cosine Recall@10
830
+ - type: cosine_ndcg@10
831
+ value: 0.40977946157999073
832
+ name: Cosine Ndcg@10
833
+ - type: cosine_mrr@10
834
+ value: 0.39812790886734506
835
+ name: Cosine Mrr@10
836
+ - type: cosine_map@100
837
+ value: 0.4661645952118268
838
+ name: Cosine Map@100
839
+ - task:
840
+ type: information-retrieval
841
+ name: Information Retrieval
842
+ dataset:
843
+ name: dim 128
844
+ type: dim_128
845
+ metrics:
846
+ - type: cosine_accuracy@1
847
+ value: 0.3559539052496799
848
+ name: Cosine Accuracy@1
849
+ - type: cosine_accuracy@3
850
+ value: 0.3617157490396927
851
+ name: Cosine Accuracy@3
852
+ - type: cosine_accuracy@5
853
+ value: 0.39244558258642764
854
+ name: Cosine Accuracy@5
855
+ - type: cosine_accuracy@10
856
+ value: 0.4186939820742638
857
+ name: Cosine Accuracy@10
858
+ - type: cosine_precision@1
859
+ value: 0.3559539052496799
860
+ name: Cosine Precision@1
861
+ - type: cosine_precision@3
862
+ value: 0.35552710200597526
863
+ name: Cosine Precision@3
864
+ - type: cosine_precision@5
865
+ value: 0.3490396927016646
866
+ name: Cosine Precision@5
867
+ - type: cosine_precision@10
868
+ value: 0.32131882202304735
869
+ name: Cosine Precision@10
870
+ - type: cosine_recall@1
871
+ value: 0.037575464818099744
872
+ name: Cosine Recall@1
873
+ - type: cosine_recall@3
874
+ value: 0.11032964908822472
875
+ name: Cosine Recall@3
876
+ - type: cosine_recall@5
877
+ value: 0.16793427308834435
878
+ name: Cosine Recall@5
879
+ - type: cosine_recall@10
880
+ value: 0.2541985714643628
881
+ name: Cosine Recall@10
882
+ - type: cosine_ndcg@10
883
+ value: 0.3790325714206647
884
+ name: Cosine Ndcg@10
885
+ - type: cosine_mrr@10
886
+ value: 0.3671173505680543
887
+ name: Cosine Mrr@10
888
+ - type: cosine_map@100
889
+ value: 0.43535825619272106
890
+ name: Cosine Map@100
891
+ - task:
892
+ type: information-retrieval
893
+ name: Information Retrieval
894
+ dataset:
895
+ name: dim 64
896
+ type: dim_64
897
+ metrics:
898
+ - type: cosine_accuracy@1
899
+ value: 0.31306017925736235
900
+ name: Cosine Accuracy@1
901
+ - type: cosine_accuracy@3
902
+ value: 0.31946222791293216
903
+ name: Cosine Accuracy@3
904
+ - type: cosine_accuracy@5
905
+ value: 0.34635083226632524
906
+ name: Cosine Accuracy@5
907
+ - type: cosine_accuracy@10
908
+ value: 0.3758002560819462
909
+ name: Cosine Accuracy@10
910
+ - type: cosine_precision@1
911
+ value: 0.31306017925736235
912
+ name: Cosine Precision@1
913
+ - type: cosine_precision@3
914
+ value: 0.313486982501067
915
+ name: Cosine Precision@3
916
+ - type: cosine_precision@5
917
+ value: 0.3075544174135723
918
+ name: Cosine Precision@5
919
+ - type: cosine_precision@10
920
+ value: 0.2819462227912932
921
+ name: Cosine Precision@10
922
+ - type: cosine_recall@1
923
+ value: 0.033872169883188745
924
+ name: Cosine Recall@1
925
+ - type: cosine_recall@3
926
+ value: 0.09984524687478234
927
+ name: Cosine Recall@3
928
+ - type: cosine_recall@5
929
+ value: 0.15245541388627262
930
+ name: Cosine Recall@5
931
+ - type: cosine_recall@10
932
+ value: 0.228651154461535
933
+ name: Cosine Recall@10
934
+ - type: cosine_ndcg@10
935
+ value: 0.33574924678086643
936
+ name: Cosine Ndcg@10
937
+ - type: cosine_mrr@10
938
+ value: 0.3240625571611481
939
+ name: Cosine Mrr@10
940
+ - type: cosine_map@100
941
+ value: 0.3923627170196659
942
+ name: Cosine Map@100
943
+ ---
944
+
945
+ # modernbert-embed-base
946
+
947
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base). 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.
948
+
949
+ ## Model Details
950
+
951
+ ### Model Description
952
+ - **Model Type:** Sentence Transformer
953
+ - **Base model:** [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) <!-- at revision d556a88e332558790b210f7bdbe87da2fa94a8d8 -->
954
+ - **Maximum Sequence Length:** 8192 tokens
955
+ - **Output Dimensionality:** 768 dimensions
956
+ - **Similarity Function:** Cosine Similarity
957
+ <!-- - **Training Dataset:** Unknown -->
958
+ - **Language:** en
959
+ - **License:** apache-2.0
960
+
961
+ ### Model Sources
962
+
963
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
964
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
965
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
966
+
967
+ ### Full Model Architecture
968
+
969
+ ```
970
+ SentenceTransformer(
971
+ (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
972
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
973
+ (2): Normalize()
974
+ )
975
+ ```
976
+
977
+ ## Usage
978
+
979
+ ### Direct Usage (Sentence Transformers)
980
+
981
+ First install the Sentence Transformers library:
982
+
983
+ ```bash
984
+ pip install -U sentence-transformers
985
+ ```
986
+
987
+ Then you can load this model and run inference.
988
+ ```python
989
+ from sentence_transformers import SentenceTransformer
990
+
991
+ # Download from the 🤗 Hub
992
+ model = SentenceTransformer("sentence_transformers_model_id")
993
+ # Run inference
994
+ sentences = [
995
+ 'What may impede authorities in the discharge of their responsibilities under Union law?',
996
+ 'The objectives and principles of Directive 95/46/EC remain sound, but it has not prevented fragmentation in the implementation of data protection across the Union, legal uncertainty or a widespread public perception that there are significant risks to the protection of natural persons, in particular with regard to online activity. Differences in the level of protection of the rights and freedoms of natural persons, in particular the right to the protection of personal data, with regard to the processing of personal data in the Member States may prevent the free flow of personal data throughout the Union. Those differences may therefore constitute an obstacle to the pursuit of economic activities at the level of the Union, distort competition and impede authorities in the discharge of their responsibilities under Union law. Such a difference in levels of protection is due to the existence of differences in the implementation and application of Directive 95/46/EC.',
997
+ 'This Regulation is without prejudice to international agreements concluded between the Union and third countries regulating the transfer of personal data including appropriate safeguards for the data subjects. Member States may conclude international agreements which involve the transfer of personal data to third countries or international organisations, as far as such agreements do not affect this Regulation or any other provisions of Union law and include an appropriate level of protection for the fundamental rights of the data subjects.',
998
+ ]
999
+ embeddings = model.encode(sentences)
1000
+ print(embeddings.shape)
1001
+ # [3, 768]
1002
+
1003
+ # Get the similarity scores for the embeddings
1004
+ similarities = model.similarity(embeddings, embeddings)
1005
+ print(similarities)
1006
+ # tensor([[1.0000, 0.5042, 0.0865],
1007
+ # [0.5042, 1.0000, 0.2632],
1008
+ # [0.0865, 0.2632, 1.0000]])
1009
+ ```
1010
+
1011
+ <!--
1012
+ ### Direct Usage (Transformers)
1013
+
1014
+ <details><summary>Click to see the direct usage in Transformers</summary>
1015
+
1016
+ </details>
1017
+ -->
1018
+
1019
+ <!--
1020
+ ### Downstream Usage (Sentence Transformers)
1021
+
1022
+ You can finetune this model on your own dataset.
1023
+
1024
+ <details><summary>Click to expand</summary>
1025
+
1026
+ </details>
1027
+ -->
1028
+
1029
+ <!--
1030
+ ### Out-of-Scope Use
1031
+
1032
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
1033
+ -->
1034
+
1035
+ ## Evaluation
1036
+
1037
+ ### Metrics
1038
+
1039
+ #### Information Retrieval
1040
+
1041
+ * Dataset: `dim_768`
1042
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
1043
+ ```json
1044
+ {
1045
+ "truncate_dim": 768
1046
+ }
1047
+ ```
1048
+
1049
+ | Metric | Value |
1050
+ |:--------------------|:-----------|
1051
+ | cosine_accuracy@1 | 0.4027 |
1052
+ | cosine_accuracy@3 | 0.4065 |
1053
+ | cosine_accuracy@5 | 0.436 |
1054
+ | cosine_accuracy@10 | 0.4693 |
1055
+ | cosine_precision@1 | 0.4027 |
1056
+ | cosine_precision@3 | 0.4016 |
1057
+ | cosine_precision@5 | 0.393 |
1058
+ | cosine_precision@10 | 0.3624 |
1059
+ | cosine_recall@1 | 0.0422 |
1060
+ | cosine_recall@3 | 0.1234 |
1061
+ | cosine_recall@5 | 0.1869 |
1062
+ | cosine_recall@10 | 0.2822 |
1063
+ | **cosine_ndcg@10** | **0.4261** |
1064
+ | cosine_mrr@10 | 0.414 |
1065
+ | cosine_map@100 | 0.4844 |
1066
+
1067
+ #### Information Retrieval
1068
+
1069
+ * Dataset: `dim_512`
1070
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
1071
+ ```json
1072
+ {
1073
+ "truncate_dim": 512
1074
+ }
1075
+ ```
1076
+
1077
+ | Metric | Value |
1078
+ |:--------------------|:-----------|
1079
+ | cosine_accuracy@1 | 0.395 |
1080
+ | cosine_accuracy@3 | 0.3988 |
1081
+ | cosine_accuracy@5 | 0.4251 |
1082
+ | cosine_accuracy@10 | 0.4533 |
1083
+ | cosine_precision@1 | 0.395 |
1084
+ | cosine_precision@3 | 0.3939 |
1085
+ | cosine_precision@5 | 0.3846 |
1086
+ | cosine_precision@10 | 0.351 |
1087
+ | cosine_recall@1 | 0.0417 |
1088
+ | cosine_recall@3 | 0.1219 |
1089
+ | cosine_recall@5 | 0.1844 |
1090
+ | cosine_recall@10 | 0.2756 |
1091
+ | **cosine_ndcg@10** | **0.4154** |
1092
+ | cosine_mrr@10 | 0.4049 |
1093
+ | cosine_map@100 | 0.4731 |
1094
+
1095
+ #### Information Retrieval
1096
+
1097
+ * Dataset: `dim_256`
1098
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
1099
+ ```json
1100
+ {
1101
+ "truncate_dim": 256
1102
+ }
1103
+ ```
1104
+
1105
+ | Metric | Value |
1106
+ |:--------------------|:-----------|
1107
+ | cosine_accuracy@1 | 0.3873 |
1108
+ | cosine_accuracy@3 | 0.3924 |
1109
+ | cosine_accuracy@5 | 0.4206 |
1110
+ | cosine_accuracy@10 | 0.4494 |
1111
+ | cosine_precision@1 | 0.3873 |
1112
+ | cosine_precision@3 | 0.3869 |
1113
+ | cosine_precision@5 | 0.3791 |
1114
+ | cosine_precision@10 | 0.3485 |
1115
+ | cosine_recall@1 | 0.0402 |
1116
+ | cosine_recall@3 | 0.118 |
1117
+ | cosine_recall@5 | 0.1796 |
1118
+ | cosine_recall@10 | 0.2711 |
1119
+ | **cosine_ndcg@10** | **0.4098** |
1120
+ | cosine_mrr@10 | 0.3981 |
1121
+ | cosine_map@100 | 0.4662 |
1122
+
1123
+ #### Information Retrieval
1124
+
1125
+ * Dataset: `dim_128`
1126
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
1127
+ ```json
1128
+ {
1129
+ "truncate_dim": 128
1130
+ }
1131
+ ```
1132
+
1133
+ | Metric | Value |
1134
+ |:--------------------|:----------|
1135
+ | cosine_accuracy@1 | 0.356 |
1136
+ | cosine_accuracy@3 | 0.3617 |
1137
+ | cosine_accuracy@5 | 0.3924 |
1138
+ | cosine_accuracy@10 | 0.4187 |
1139
+ | cosine_precision@1 | 0.356 |
1140
+ | cosine_precision@3 | 0.3555 |
1141
+ | cosine_precision@5 | 0.349 |
1142
+ | cosine_precision@10 | 0.3213 |
1143
+ | cosine_recall@1 | 0.0376 |
1144
+ | cosine_recall@3 | 0.1103 |
1145
+ | cosine_recall@5 | 0.1679 |
1146
+ | cosine_recall@10 | 0.2542 |
1147
+ | **cosine_ndcg@10** | **0.379** |
1148
+ | cosine_mrr@10 | 0.3671 |
1149
+ | cosine_map@100 | 0.4354 |
1150
+
1151
+ #### Information Retrieval
1152
+
1153
+ * Dataset: `dim_64`
1154
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
1155
+ ```json
1156
+ {
1157
+ "truncate_dim": 64
1158
+ }
1159
+ ```
1160
+
1161
+ | Metric | Value |
1162
+ |:--------------------|:-----------|
1163
+ | cosine_accuracy@1 | 0.3131 |
1164
+ | cosine_accuracy@3 | 0.3195 |
1165
+ | cosine_accuracy@5 | 0.3464 |
1166
+ | cosine_accuracy@10 | 0.3758 |
1167
+ | cosine_precision@1 | 0.3131 |
1168
+ | cosine_precision@3 | 0.3135 |
1169
+ | cosine_precision@5 | 0.3076 |
1170
+ | cosine_precision@10 | 0.2819 |
1171
+ | cosine_recall@1 | 0.0339 |
1172
+ | cosine_recall@3 | 0.0998 |
1173
+ | cosine_recall@5 | 0.1525 |
1174
+ | cosine_recall@10 | 0.2287 |
1175
+ | **cosine_ndcg@10** | **0.3357** |
1176
+ | cosine_mrr@10 | 0.3241 |
1177
+ | cosine_map@100 | 0.3924 |
1178
+
1179
+ <!--
1180
+ ## Bias, Risks and Limitations
1181
+
1182
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
1183
+ -->
1184
+
1185
+ <!--
1186
+ ### Recommendations
1187
+
1188
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
1189
+ -->
1190
+
1191
+ ## Training Details
1192
+
1193
+ ### Training Dataset
1194
+
1195
+ #### Unnamed Dataset
1196
+
1197
+ * Size: 391 training samples
1198
+ * Columns: <code>anchor</code> and <code>positive</code>
1199
+ * Approximate statistics based on the first 391 samples:
1200
+ | | anchor | positive |
1201
+ |:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
1202
+ | type | string | string |
1203
+ | details | <ul><li>min: 7 tokens</li><li>mean: 15.05 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 25 tokens</li><li>mean: 667.99 tokens</li><li>max: 2429 tokens</li></ul> |
1204
+ * Samples:
1205
+ | anchor | positive |
1206
+ |:-----------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
1207
+ | <code>On what date did the act occur?</code> | <code>Court (Civil/Criminal): Civil <br>Provisions: Directive 2015/366, Law 4537/2018 <br>Time of the act: 31.08.2022 <br>Outcome (not guilty, guilty): Partially accepts the claim. <br>Reasoning: The Athens Peace Court ordered the bank to return the amount that was withdrawn from the plaintiffs' account and to pay additional compensation for the moral damage they suffered. <br>Facts: The case concerns plaintiffs who fell victim to electronic fraud via phishing, resulting in the withdrawal of money from their bank account. The plaintiffs claimed that the bank did not take the necessary security measures to protect their accounts and sought compensation for the financial loss and moral damage they suffered. The court determined that the bank is responsible for the loss of the money, as it did not prove that the transactions were authorized by the plaintiffs. Furthermore, the court recognized that the bank's refusal to return the funds constitutes an infringement of the plaintiffs' personal rights, as it...</code> |
1208
+ | <code>For what purposes can more specific rules be provided regarding the employment context?</code> | <code>1.Member States may, by law or by collective agreements, provide for more specific rules to ensure the protection of the rights and freedoms in respect of the processing of employees' personal data in the employment context, in particular for the purposes of the recruitment, the performance of the contract of employment, including discharge of obligations laid down by law or by collective agreements, management, planning and organisation of work, equality and diversity in the workplace, health and safety at work, protection of employer's or customer's property and for the purposes of the exercise and enjoyment, on an individual or collective basis, of rights and benefits related to employment, and for the purpose of the termination of the employment relationship.<br>2.Those rules shall include suitable and specific measures to safeguard the data subject's human dignity, legitimate interests and fundamental rights, with particular regard to the transparency of processing, the transfer of p...</code> |
1209
+ | <code>On which date were transactions detailed in the provided text conducted?</code> | <code>**Court (Civil/Criminal): Civil**<br><br>**Provisions:**<br><br>**Time of commission of the act:**<br><br>**Outcome (not guilty, guilty):**<br><br>**Rationale:**<br><br>**Facts:**<br>The plaintiff holds credit card number ............ with the defendant banking corporation. Based on the application for alternative networks dated 19/7/2015 with number ......... submitted at a branch of the defendant, he was granted access to the electronic banking service (e-banking) to conduct banking transactions (debit, credit, updates, payments) remotely. On 30/11/2020, the plaintiff fell victim to electronic fraud through the "phishing" method, whereby an unknown perpetrator managed to withdraw a total amount of €3,121.75 from the aforementioned credit card. Specifically, the plaintiff received an email at 1:35 PM on 29/11/2020 from sender ...... with address ........, informing him that due to an impending system change, he needed to verify the mobile phone number linked to the credit card, urging him to complete the verification...</code> |
1210
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
1211
+ ```json
1212
+ {
1213
+ "loss": "MultipleNegativesRankingLoss",
1214
+ "matryoshka_dims": [
1215
+ 768,
1216
+ 512,
1217
+ 256,
1218
+ 128,
1219
+ 64
1220
+ ],
1221
+ "matryoshka_weights": [
1222
+ 1,
1223
+ 1,
1224
+ 1,
1225
+ 1,
1226
+ 1
1227
+ ],
1228
+ "n_dims_per_step": -1
1229
+ }
1230
+ ```
1231
+
1232
+ ### Training Hyperparameters
1233
+ #### Non-Default Hyperparameters
1234
+
1235
+ - `eval_strategy`: epoch
1236
+ - `per_device_train_batch_size`: 2
1237
+ - `per_device_eval_batch_size`: 2
1238
+ - `gradient_accumulation_steps`: 2
1239
+ - `learning_rate`: 2e-05
1240
+ - `num_train_epochs`: 20
1241
+ - `lr_scheduler_type`: cosine
1242
+ - `warmup_ratio`: 0.1
1243
+ - `bf16`: True
1244
+ - `load_best_model_at_end`: True
1245
+ - `optim`: adamw_torch_fused
1246
+ - `batch_sampler`: no_duplicates
1247
+
1248
+ #### All Hyperparameters
1249
+ <details><summary>Click to expand</summary>
1250
+
1251
+ - `overwrite_output_dir`: False
1252
+ - `do_predict`: False
1253
+ - `eval_strategy`: epoch
1254
+ - `prediction_loss_only`: True
1255
+ - `per_device_train_batch_size`: 2
1256
+ - `per_device_eval_batch_size`: 2
1257
+ - `per_gpu_train_batch_size`: None
1258
+ - `per_gpu_eval_batch_size`: None
1259
+ - `gradient_accumulation_steps`: 2
1260
+ - `eval_accumulation_steps`: None
1261
+ - `torch_empty_cache_steps`: None
1262
+ - `learning_rate`: 2e-05
1263
+ - `weight_decay`: 0.0
1264
+ - `adam_beta1`: 0.9
1265
+ - `adam_beta2`: 0.999
1266
+ - `adam_epsilon`: 1e-08
1267
+ - `max_grad_norm`: 1.0
1268
+ - `num_train_epochs`: 20
1269
+ - `max_steps`: -1
1270
+ - `lr_scheduler_type`: cosine
1271
+ - `lr_scheduler_kwargs`: {}
1272
+ - `warmup_ratio`: 0.1
1273
+ - `warmup_steps`: 0
1274
+ - `log_level`: passive
1275
+ - `log_level_replica`: warning
1276
+ - `log_on_each_node`: True
1277
+ - `logging_nan_inf_filter`: True
1278
+ - `save_safetensors`: True
1279
+ - `save_on_each_node`: False
1280
+ - `save_only_model`: False
1281
+ - `restore_callback_states_from_checkpoint`: False
1282
+ - `no_cuda`: False
1283
+ - `use_cpu`: False
1284
+ - `use_mps_device`: False
1285
+ - `seed`: 42
1286
+ - `data_seed`: None
1287
+ - `jit_mode_eval`: False
1288
+ - `use_ipex`: False
1289
+ - `bf16`: True
1290
+ - `fp16`: False
1291
+ - `fp16_opt_level`: O1
1292
+ - `half_precision_backend`: auto
1293
+ - `bf16_full_eval`: False
1294
+ - `fp16_full_eval`: False
1295
+ - `tf32`: None
1296
+ - `local_rank`: 0
1297
+ - `ddp_backend`: None
1298
+ - `tpu_num_cores`: None
1299
+ - `tpu_metrics_debug`: False
1300
+ - `debug`: []
1301
+ - `dataloader_drop_last`: False
1302
+ - `dataloader_num_workers`: 0
1303
+ - `dataloader_prefetch_factor`: None
1304
+ - `past_index`: -1
1305
+ - `disable_tqdm`: False
1306
+ - `remove_unused_columns`: True
1307
+ - `label_names`: None
1308
+ - `load_best_model_at_end`: True
1309
+ - `ignore_data_skip`: False
1310
+ - `fsdp`: []
1311
+ - `fsdp_min_num_params`: 0
1312
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
1313
+ - `tp_size`: 0
1314
+ - `fsdp_transformer_layer_cls_to_wrap`: None
1315
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
1316
+ - `deepspeed`: None
1317
+ - `label_smoothing_factor`: 0.0
1318
+ - `optim`: adamw_torch_fused
1319
+ - `optim_args`: None
1320
+ - `adafactor`: False
1321
+ - `group_by_length`: False
1322
+ - `length_column_name`: length
1323
+ - `ddp_find_unused_parameters`: None
1324
+ - `ddp_bucket_cap_mb`: None
1325
+ - `ddp_broadcast_buffers`: False
1326
+ - `dataloader_pin_memory`: True
1327
+ - `dataloader_persistent_workers`: False
1328
+ - `skip_memory_metrics`: True
1329
+ - `use_legacy_prediction_loop`: False
1330
+ - `push_to_hub`: False
1331
+ - `resume_from_checkpoint`: None
1332
+ - `hub_model_id`: None
1333
+ - `hub_strategy`: every_save
1334
+ - `hub_private_repo`: None
1335
+ - `hub_always_push`: False
1336
+ - `gradient_checkpointing`: False
1337
+ - `gradient_checkpointing_kwargs`: None
1338
+ - `include_inputs_for_metrics`: False
1339
+ - `include_for_metrics`: []
1340
+ - `eval_do_concat_batches`: True
1341
+ - `fp16_backend`: auto
1342
+ - `push_to_hub_model_id`: None
1343
+ - `push_to_hub_organization`: None
1344
+ - `mp_parameters`:
1345
+ - `auto_find_batch_size`: False
1346
+ - `full_determinism`: False
1347
+ - `torchdynamo`: None
1348
+ - `ray_scope`: last
1349
+ - `ddp_timeout`: 1800
1350
+ - `torch_compile`: False
1351
+ - `torch_compile_backend`: None
1352
+ - `torch_compile_mode`: None
1353
+ - `include_tokens_per_second`: False
1354
+ - `include_num_input_tokens_seen`: False
1355
+ - `neftune_noise_alpha`: None
1356
+ - `optim_target_modules`: None
1357
+ - `batch_eval_metrics`: False
1358
+ - `eval_on_start`: False
1359
+ - `use_liger_kernel`: False
1360
+ - `eval_use_gather_object`: False
1361
+ - `average_tokens_across_devices`: False
1362
+ - `prompts`: None
1363
+ - `batch_sampler`: no_duplicates
1364
+ - `multi_dataset_batch_sampler`: proportional
1365
+ - `router_mapping`: {}
1366
+ - `learning_rate_mapping`: {}
1367
+
1368
+ </details>
1369
+
1370
+ ### Training Logs
1371
+ | Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
1372
+ |:------:|:----:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
1373
+ | 0.0102 | 1 | 0.0001 | - | - | - | - | - |
1374
+ | 0.0204 | 2 | 0.001 | - | - | - | - | - |
1375
+ | 0.0306 | 3 | 0.0938 | - | - | - | - | - |
1376
+ | 0.0408 | 4 | 0.0084 | - | - | - | - | - |
1377
+ | 0.0510 | 5 | 0.0 | - | - | - | - | - |
1378
+ | 0.0612 | 6 | 0.0004 | - | - | - | - | - |
1379
+ | 0.0714 | 7 | 0.003 | - | - | - | - | - |
1380
+ | 0.0816 | 8 | 0.0012 | - | - | - | - | - |
1381
+ | 0.0918 | 9 | 0.0001 | - | - | - | - | - |
1382
+ | 0.1020 | 10 | 0.0053 | - | - | - | - | - |
1383
+ | 0.1122 | 11 | 0.0068 | - | - | - | - | - |
1384
+ | 0.1224 | 12 | 0.0006 | - | - | - | - | - |
1385
+ | 0.1327 | 13 | 0.0007 | - | - | - | - | - |
1386
+ | 0.1429 | 14 | 0.0003 | - | - | - | - | - |
1387
+ | 0.1531 | 15 | 0.0096 | - | - | - | - | - |
1388
+ | 0.1633 | 16 | 0.0004 | - | - | - | - | - |
1389
+ | 0.1735 | 17 | 0.016 | - | - | - | - | - |
1390
+ | 0.1837 | 18 | 0.0 | - | - | - | - | - |
1391
+ | 0.1939 | 19 | 0.0005 | - | - | - | - | - |
1392
+ | 0.2041 | 20 | 0.0 | - | - | - | - | - |
1393
+ | 0.2143 | 21 | 0.003 | - | - | - | - | - |
1394
+ | 0.2245 | 22 | 0.1395 | - | - | - | - | - |
1395
+ | 0.2347 | 23 | 0.3967 | - | - | - | - | - |
1396
+ | 0.2449 | 24 | 0.0023 | - | - | - | - | - |
1397
+ | 0.2551 | 25 | 0.0003 | - | - | - | - | - |
1398
+ | 0.2653 | 26 | 0.0027 | - | - | - | - | - |
1399
+ | 0.2755 | 27 | 0.0147 | - | - | - | - | - |
1400
+ | 0.2857 | 28 | 0.0522 | - | - | - | - | - |
1401
+ | 0.2959 | 29 | 0.0001 | - | - | - | - | - |
1402
+ | 0.3061 | 30 | 0.0008 | - | - | - | - | - |
1403
+ | 0.3163 | 31 | 0.0044 | - | - | - | - | - |
1404
+ | 0.3265 | 32 | 0.0 | - | - | - | - | - |
1405
+ | 0.3367 | 33 | 0.0028 | - | - | - | - | - |
1406
+ | 0.3469 | 34 | 0.0007 | - | - | - | - | - |
1407
+ | 0.3571 | 35 | 0.0002 | - | - | - | - | - |
1408
+ | 0.3673 | 36 | 0.0168 | - | - | - | - | - |
1409
+ | 0.3776 | 37 | 0.0023 | - | - | - | - | - |
1410
+ | 0.3878 | 38 | 0.0041 | - | - | - | - | - |
1411
+ | 0.3980 | 39 | 0.0081 | - | - | - | - | - |
1412
+ | 0.4082 | 40 | 0.0004 | - | - | - | - | - |
1413
+ | 0.4184 | 41 | 0.0 | - | - | - | - | - |
1414
+ | 0.4286 | 42 | 0.005 | - | - | - | - | - |
1415
+ | 0.4388 | 43 | 0.0031 | - | - | - | - | - |
1416
+ | 0.4490 | 44 | 0.0216 | - | - | - | - | - |
1417
+ | 0.4592 | 45 | 0.0004 | - | - | - | - | - |
1418
+ | 0.4694 | 46 | 0.0018 | - | - | - | - | - |
1419
+ | 0.4796 | 47 | 0.0 | - | - | - | - | - |
1420
+ | 0.4898 | 48 | 0.0044 | - | - | - | - | - |
1421
+ | 0.5 | 49 | 0.0004 | - | - | - | - | - |
1422
+ | 0.5102 | 50 | 0.0019 | - | - | - | - | - |
1423
+ | 0.5204 | 51 | 0.0005 | - | - | - | - | - |
1424
+ | 0.5306 | 52 | 0.0016 | - | - | - | - | - |
1425
+ | 0.5408 | 53 | 0.1806 | - | - | - | - | - |
1426
+ | 0.5510 | 54 | 0.0 | - | - | - | - | - |
1427
+ | 0.5612 | 55 | 0.0025 | - | - | - | - | - |
1428
+ | 0.5714 | 56 | 0.0002 | - | - | - | - | - |
1429
+ | 0.5816 | 57 | 0.0 | - | - | - | - | - |
1430
+ | 0.5918 | 58 | 0.0111 | - | - | - | - | - |
1431
+ | 0.6020 | 59 | 0.0011 | - | - | - | - | - |
1432
+ | 0.6122 | 60 | 0.0003 | - | - | - | - | - |
1433
+ | 0.6224 | 61 | 1.8072 | - | - | - | - | - |
1434
+ | 0.6327 | 62 | 0.0009 | - | - | - | - | - |
1435
+ | 0.6429 | 63 | 0.0011 | - | - | - | - | - |
1436
+ | 0.6531 | 64 | 0.0013 | - | - | - | - | - |
1437
+ | 0.6633 | 65 | 0.0 | - | - | - | - | - |
1438
+ | 0.6735 | 66 | 0.0007 | - | - | - | - | - |
1439
+ | 0.6837 | 67 | 0.4116 | - | - | - | - | - |
1440
+ | 0.6939 | 68 | 0.008 | - | - | - | - | - |
1441
+ | 0.7041 | 69 | 0.0009 | - | - | - | - | - |
1442
+ | 0.7143 | 70 | 0.0004 | - | - | - | - | - |
1443
+ | 0.7245 | 71 | 0.0019 | - | - | - | - | - |
1444
+ | 0.7347 | 72 | 0.0005 | - | - | - | - | - |
1445
+ | 0.7449 | 73 | 0.0004 | - | - | - | - | - |
1446
+ | 0.7551 | 74 | 0.0005 | - | - | - | - | - |
1447
+ | 0.7653 | 75 | 0.0001 | - | - | - | - | - |
1448
+ | 0.7755 | 76 | 0.0005 | - | - | - | - | - |
1449
+ | 0.7857 | 77 | 0.0 | - | - | - | - | - |
1450
+ | 0.7959 | 78 | 0.0001 | - | - | - | - | - |
1451
+ | 0.8061 | 79 | 0.0025 | - | - | - | - | - |
1452
+ | 0.8163 | 80 | 0.0 | - | - | - | - | - |
1453
+ | 0.8265 | 81 | 0.0012 | - | - | - | - | - |
1454
+ | 0.8367 | 82 | 0.0003 | - | - | - | - | - |
1455
+ | 0.8469 | 83 | 0.0002 | - | - | - | - | - |
1456
+ | 0.8571 | 84 | 0.0 | - | - | - | - | - |
1457
+ | 0.8673 | 85 | 0.0 | - | - | - | - | - |
1458
+ | 0.8776 | 86 | 0.0 | - | - | - | - | - |
1459
+ | 0.8878 | 87 | 0.0002 | - | - | - | - | - |
1460
+ | 0.8980 | 88 | 0.0009 | - | - | - | - | - |
1461
+ | 0.9082 | 89 | 0.0067 | - | - | - | - | - |
1462
+ | 0.9184 | 90 | 0.0 | - | - | - | - | - |
1463
+ | 0.9286 | 91 | 0.0001 | - | - | - | - | - |
1464
+ | 0.9388 | 92 | 0.0008 | - | - | - | - | - |
1465
+ | 0.9490 | 93 | 0.0031 | - | - | - | - | - |
1466
+ | 0.9592 | 94 | 0.0004 | - | - | - | - | - |
1467
+ | 0.9694 | 95 | 0.0004 | - | - | - | - | - |
1468
+ | 0.9796 | 96 | 0.0001 | - | - | - | - | - |
1469
+ | 0.9898 | 97 | 0.0004 | - | - | - | - | - |
1470
+ | 1.0 | 98 | 0.0005 | 0.4261 | 0.4154 | 0.4098 | 0.3790 | 0.3357 |
1471
+
1472
+
1473
+ ### Framework Versions
1474
+ - Python: 3.12.11
1475
+ - Sentence Transformers: 5.1.0
1476
+ - Transformers: 4.51.3
1477
+ - PyTorch: 2.8.0+cu126
1478
+ - Accelerate: 1.10.1
1479
+ - Datasets: 4.0.0
1480
+ - Tokenizers: 0.21.4
1481
+
1482
+ ## Citation
1483
+
1484
+ ### BibTeX
1485
+
1486
+ #### Sentence Transformers
1487
+ ```bibtex
1488
+ @inproceedings{reimers-2019-sentence-bert,
1489
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
1490
+ author = "Reimers, Nils and Gurevych, Iryna",
1491
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
1492
+ month = "11",
1493
+ year = "2019",
1494
+ publisher = "Association for Computational Linguistics",
1495
+ url = "https://arxiv.org/abs/1908.10084",
1496
+ }
1497
+ ```
1498
+
1499
+ #### MatryoshkaLoss
1500
+ ```bibtex
1501
+ @misc{kusupati2024matryoshka,
1502
+ title={Matryoshka Representation Learning},
1503
+ 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},
1504
+ year={2024},
1505
+ eprint={2205.13147},
1506
+ archivePrefix={arXiv},
1507
+ primaryClass={cs.LG}
1508
+ }
1509
+ ```
1510
+
1511
+ #### MultipleNegativesRankingLoss
1512
+ ```bibtex
1513
+ @misc{henderson2017efficient,
1514
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
1515
+ 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},
1516
+ year={2017},
1517
+ eprint={1705.00652},
1518
+ archivePrefix={arXiv},
1519
+ primaryClass={cs.CL}
1520
+ }
1521
+ ```
1522
+
1523
+ <!--
1524
+ ## Glossary
1525
+
1526
+ *Clearly define terms in order to be accessible across audiences.*
1527
+ -->
1528
+
1529
+ <!--
1530
+ ## Model Card Authors
1531
+
1532
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
1533
+ -->
1534
+
1535
+ <!--
1536
+ ## Model Card Contact
1537
+
1538
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
1539
+ -->
checkpoint-98/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": 50282,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 160000.0,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "initializer_cutoff_factor": 2.0,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 1152,
25
+ "layer_norm_eps": 1e-05,
26
+ "local_attention": 128,
27
+ "local_rope_theta": 10000.0,
28
+ "max_position_embeddings": 8192,
29
+ "mlp_bias": false,
30
+ "mlp_dropout": 0.0,
31
+ "model_type": "modernbert",
32
+ "norm_bias": false,
33
+ "norm_eps": 1e-05,
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 22,
36
+ "pad_token_id": 50283,
37
+ "position_embedding_type": "absolute",
38
+ "repad_logits_with_grad": false,
39
+ "sep_token_id": 50282,
40
+ "sparse_pred_ignore_index": -100,
41
+ "sparse_prediction": false,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.51.3",
44
+ "vocab_size": 50368
45
+ }
checkpoint-98/config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "5.1.0",
4
+ "transformers": "4.51.3",
5
+ "pytorch": "2.8.0+cu126"
6
+ },
7
+ "prompts": {
8
+ "query": "",
9
+ "document": ""
10
+ },
11
+ "default_prompt_name": null,
12
+ "similarity_fn_name": "cosine",
13
+ "model_type": "SentenceTransformer"
14
+ }
checkpoint-98/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5a818377bdcd1bbf4879eeeb4ba232b290e971113ba2fd94ca9587f19f3f3
3
+ size 596070136
checkpoint-98/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
+ ]
checkpoint-98/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b50ae83c1c72eec21aa046f0d7437f76e6ef8a2f0cc7e27e80abcc15585c4f86
3
+ size 1192229387
checkpoint-98/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec81fb8e7bc823bebbf4d8eb5d9328a37bdf71c84cdb11761304ca7f2076f67c
3
+ size 14645
checkpoint-98/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8050407fb4fa517140d91f016be515b027290100821411e470b937a3a98f10c3
3
+ size 1465
checkpoint-98/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
checkpoint-98/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": true,
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
+ }
checkpoint-98/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-98/tokenizer_config.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "max_length": 8192,
937
+ "model_input_names": [
938
+ "input_ids",
939
+ "attention_mask"
940
+ ],
941
+ "model_max_length": 8192,
942
+ "pad_to_multiple_of": null,
943
+ "pad_token": "[PAD]",
944
+ "pad_token_type_id": 0,
945
+ "padding_side": "right",
946
+ "sep_token": "[SEP]",
947
+ "stride": 0,
948
+ "tokenizer_class": "PreTrainedTokenizer",
949
+ "truncation_side": "right",
950
+ "truncation_strategy": "longest_first",
951
+ "unk_token": "[UNK]"
952
+ }
checkpoint-98/trainer_state.json ADDED
@@ -0,0 +1,812 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 98,
3
+ "best_metric": 0.3790325714206647,
4
+ "best_model_checkpoint": "nomic-ai/modernbert-embed-base/checkpoint-98",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 98,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01020408163265306,
14
+ "grad_norm": 0.014294901862740517,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.0001,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.02040816326530612,
21
+ "grad_norm": 0.1376705914735794,
22
+ "learning_rate": 1.0204081632653061e-07,
23
+ "loss": 0.001,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.030612244897959183,
28
+ "grad_norm": 11.743180274963379,
29
+ "learning_rate": 2.0408163265306121e-07,
30
+ "loss": 0.0938,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.04081632653061224,
35
+ "grad_norm": 0.7897523641586304,
36
+ "learning_rate": 3.0612244897959183e-07,
37
+ "loss": 0.0084,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.05102040816326531,
42
+ "grad_norm": 0.000707508996129036,
43
+ "learning_rate": 4.0816326530612243e-07,
44
+ "loss": 0.0,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.061224489795918366,
49
+ "grad_norm": 0.042860936373472214,
50
+ "learning_rate": 5.102040816326531e-07,
51
+ "loss": 0.0004,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.07142857142857142,
56
+ "grad_norm": 0.2763943076133728,
57
+ "learning_rate": 6.122448979591837e-07,
58
+ "loss": 0.003,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.08163265306122448,
63
+ "grad_norm": 0.15693208575248718,
64
+ "learning_rate": 7.142857142857143e-07,
65
+ "loss": 0.0012,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.09183673469387756,
70
+ "grad_norm": 0.04850756749510765,
71
+ "learning_rate": 8.163265306122449e-07,
72
+ "loss": 0.0001,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.10204081632653061,
77
+ "grad_norm": 0.9481569528579712,
78
+ "learning_rate": 9.183673469387756e-07,
79
+ "loss": 0.0053,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.11224489795918367,
84
+ "grad_norm": 0.9353957176208496,
85
+ "learning_rate": 1.0204081632653063e-06,
86
+ "loss": 0.0068,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.12244897959183673,
91
+ "grad_norm": 0.06643998622894287,
92
+ "learning_rate": 1.122448979591837e-06,
93
+ "loss": 0.0006,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.1326530612244898,
98
+ "grad_norm": 0.1136537492275238,
99
+ "learning_rate": 1.2244897959183673e-06,
100
+ "loss": 0.0007,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.14285714285714285,
105
+ "grad_norm": 0.019414478912949562,
106
+ "learning_rate": 1.3265306122448982e-06,
107
+ "loss": 0.0003,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.15306122448979592,
112
+ "grad_norm": 0.7712957859039307,
113
+ "learning_rate": 1.4285714285714286e-06,
114
+ "loss": 0.0096,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.16326530612244897,
119
+ "grad_norm": 0.04083826765418053,
120
+ "learning_rate": 1.5306122448979593e-06,
121
+ "loss": 0.0004,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.17346938775510204,
126
+ "grad_norm": 1.991432785987854,
127
+ "learning_rate": 1.6326530612244897e-06,
128
+ "loss": 0.016,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.1836734693877551,
133
+ "grad_norm": 0.0026387416291981936,
134
+ "learning_rate": 1.7346938775510206e-06,
135
+ "loss": 0.0,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.19387755102040816,
140
+ "grad_norm": 0.04518063738942146,
141
+ "learning_rate": 1.8367346938775512e-06,
142
+ "loss": 0.0005,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.20408163265306123,
147
+ "grad_norm": 0.0027923083398491144,
148
+ "learning_rate": 1.938775510204082e-06,
149
+ "loss": 0.0,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.21428571428571427,
154
+ "grad_norm": 0.225693017244339,
155
+ "learning_rate": 2.0408163265306125e-06,
156
+ "loss": 0.003,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.22448979591836735,
161
+ "grad_norm": 6.234318256378174,
162
+ "learning_rate": 2.1428571428571427e-06,
163
+ "loss": 0.1395,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.23469387755102042,
168
+ "grad_norm": 25.103811264038086,
169
+ "learning_rate": 2.244897959183674e-06,
170
+ "loss": 0.3967,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.24489795918367346,
175
+ "grad_norm": 0.15607698261737823,
176
+ "learning_rate": 2.3469387755102044e-06,
177
+ "loss": 0.0023,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.25510204081632654,
182
+ "grad_norm": 0.032192617654800415,
183
+ "learning_rate": 2.4489795918367347e-06,
184
+ "loss": 0.0003,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.2653061224489796,
189
+ "grad_norm": 0.22997426986694336,
190
+ "learning_rate": 2.5510204081632657e-06,
191
+ "loss": 0.0027,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.2755102040816326,
196
+ "grad_norm": 1.1110199689865112,
197
+ "learning_rate": 2.6530612244897964e-06,
198
+ "loss": 0.0147,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.2857142857142857,
203
+ "grad_norm": 3.659369945526123,
204
+ "learning_rate": 2.7551020408163266e-06,
205
+ "loss": 0.0522,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.29591836734693877,
210
+ "grad_norm": 0.005585783626884222,
211
+ "learning_rate": 2.8571428571428573e-06,
212
+ "loss": 0.0001,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.30612244897959184,
217
+ "grad_norm": 0.07389459758996964,
218
+ "learning_rate": 2.959183673469388e-06,
219
+ "loss": 0.0008,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.3163265306122449,
224
+ "grad_norm": 0.39431512355804443,
225
+ "learning_rate": 3.0612244897959185e-06,
226
+ "loss": 0.0044,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.32653061224489793,
231
+ "grad_norm": 0.0016656734514981508,
232
+ "learning_rate": 3.1632653061224496e-06,
233
+ "loss": 0.0,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.336734693877551,
238
+ "grad_norm": 0.20897622406482697,
239
+ "learning_rate": 3.2653061224489794e-06,
240
+ "loss": 0.0028,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.3469387755102041,
245
+ "grad_norm": 0.08076613396406174,
246
+ "learning_rate": 3.3673469387755105e-06,
247
+ "loss": 0.0007,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.35714285714285715,
252
+ "grad_norm": 0.022262288257479668,
253
+ "learning_rate": 3.469387755102041e-06,
254
+ "loss": 0.0002,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.3673469387755102,
259
+ "grad_norm": 1.9193856716156006,
260
+ "learning_rate": 3.5714285714285718e-06,
261
+ "loss": 0.0168,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.37755102040816324,
266
+ "grad_norm": 0.1695105880498886,
267
+ "learning_rate": 3.6734693877551024e-06,
268
+ "loss": 0.0023,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.3877551020408163,
273
+ "grad_norm": 0.5352568626403809,
274
+ "learning_rate": 3.7755102040816327e-06,
275
+ "loss": 0.0041,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.3979591836734694,
280
+ "grad_norm": 0.6937710642814636,
281
+ "learning_rate": 3.877551020408164e-06,
282
+ "loss": 0.0081,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.40816326530612246,
287
+ "grad_norm": 0.030398719012737274,
288
+ "learning_rate": 3.979591836734694e-06,
289
+ "loss": 0.0004,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.41836734693877553,
294
+ "grad_norm": 0.003243567654863,
295
+ "learning_rate": 4.081632653061225e-06,
296
+ "loss": 0.0,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.42857142857142855,
301
+ "grad_norm": 0.38866573572158813,
302
+ "learning_rate": 4.183673469387755e-06,
303
+ "loss": 0.005,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.4387755102040816,
308
+ "grad_norm": 0.3949674367904663,
309
+ "learning_rate": 4.2857142857142855e-06,
310
+ "loss": 0.0031,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.4489795918367347,
315
+ "grad_norm": 2.9631612300872803,
316
+ "learning_rate": 4.3877551020408165e-06,
317
+ "loss": 0.0216,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.45918367346938777,
322
+ "grad_norm": 0.03951283544301987,
323
+ "learning_rate": 4.489795918367348e-06,
324
+ "loss": 0.0004,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.46938775510204084,
329
+ "grad_norm": 0.14974893629550934,
330
+ "learning_rate": 4.591836734693878e-06,
331
+ "loss": 0.0018,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.47959183673469385,
336
+ "grad_norm": 0.0015900792786851525,
337
+ "learning_rate": 4.693877551020409e-06,
338
+ "loss": 0.0,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.4897959183673469,
343
+ "grad_norm": 0.28462550044059753,
344
+ "learning_rate": 4.795918367346939e-06,
345
+ "loss": 0.0044,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.5,
350
+ "grad_norm": 0.035834282636642456,
351
+ "learning_rate": 4.897959183673469e-06,
352
+ "loss": 0.0004,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.5102040816326531,
357
+ "grad_norm": 0.13105374574661255,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.0019,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.5204081632653061,
364
+ "grad_norm": 0.04286932945251465,
365
+ "learning_rate": 5.1020408163265315e-06,
366
+ "loss": 0.0005,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.5306122448979592,
371
+ "grad_norm": 0.14368070662021637,
372
+ "learning_rate": 5.204081632653062e-06,
373
+ "loss": 0.0016,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.5408163265306123,
378
+ "grad_norm": 15.608235359191895,
379
+ "learning_rate": 5.306122448979593e-06,
380
+ "loss": 0.1806,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.5510204081632653,
385
+ "grad_norm": 0.004551250953227282,
386
+ "learning_rate": 5.408163265306123e-06,
387
+ "loss": 0.0,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.5612244897959183,
392
+ "grad_norm": 0.2460200935602188,
393
+ "learning_rate": 5.510204081632653e-06,
394
+ "loss": 0.0025,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.5714285714285714,
399
+ "grad_norm": 0.022206343710422516,
400
+ "learning_rate": 5.6122448979591834e-06,
401
+ "loss": 0.0002,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.5816326530612245,
406
+ "grad_norm": 0.0030557001009583473,
407
+ "learning_rate": 5.7142857142857145e-06,
408
+ "loss": 0.0,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.5918367346938775,
413
+ "grad_norm": 1.3751850128173828,
414
+ "learning_rate": 5.816326530612246e-06,
415
+ "loss": 0.0111,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.6020408163265306,
420
+ "grad_norm": 0.11706340312957764,
421
+ "learning_rate": 5.918367346938776e-06,
422
+ "loss": 0.0011,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.6122448979591837,
427
+ "grad_norm": 0.027977069839835167,
428
+ "learning_rate": 6.020408163265307e-06,
429
+ "loss": 0.0003,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.6224489795918368,
434
+ "grad_norm": 125.90001678466797,
435
+ "learning_rate": 6.122448979591837e-06,
436
+ "loss": 1.8072,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.6326530612244898,
441
+ "grad_norm": 0.07176324725151062,
442
+ "learning_rate": 6.224489795918368e-06,
443
+ "loss": 0.0009,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.6428571428571429,
448
+ "grad_norm": 0.06726501137018204,
449
+ "learning_rate": 6.326530612244899e-06,
450
+ "loss": 0.0011,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.6530612244897959,
455
+ "grad_norm": 0.126393660902977,
456
+ "learning_rate": 6.4285714285714295e-06,
457
+ "loss": 0.0013,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.6632653061224489,
462
+ "grad_norm": 0.0025682460982352495,
463
+ "learning_rate": 6.530612244897959e-06,
464
+ "loss": 0.0,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.673469387755102,
469
+ "grad_norm": 0.05368286743760109,
470
+ "learning_rate": 6.63265306122449e-06,
471
+ "loss": 0.0007,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.6836734693877551,
476
+ "grad_norm": 13.678145408630371,
477
+ "learning_rate": 6.734693877551021e-06,
478
+ "loss": 0.4116,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.6938775510204082,
483
+ "grad_norm": 0.7735011577606201,
484
+ "learning_rate": 6.836734693877551e-06,
485
+ "loss": 0.008,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.7040816326530612,
490
+ "grad_norm": 0.07968823611736298,
491
+ "learning_rate": 6.938775510204082e-06,
492
+ "loss": 0.0009,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.7142857142857143,
497
+ "grad_norm": 0.03921031951904297,
498
+ "learning_rate": 7.0408163265306125e-06,
499
+ "loss": 0.0004,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.7244897959183674,
504
+ "grad_norm": 0.16386456787586212,
505
+ "learning_rate": 7.1428571428571436e-06,
506
+ "loss": 0.0019,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.7346938775510204,
511
+ "grad_norm": 0.055115193128585815,
512
+ "learning_rate": 7.244897959183675e-06,
513
+ "loss": 0.0005,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.7448979591836735,
518
+ "grad_norm": 0.029161576181650162,
519
+ "learning_rate": 7.346938775510205e-06,
520
+ "loss": 0.0004,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.7551020408163265,
525
+ "grad_norm": 0.03603975474834442,
526
+ "learning_rate": 7.448979591836736e-06,
527
+ "loss": 0.0005,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.7653061224489796,
532
+ "grad_norm": 0.008691967464983463,
533
+ "learning_rate": 7.551020408163265e-06,
534
+ "loss": 0.0001,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.7755102040816326,
539
+ "grad_norm": 0.05404982343316078,
540
+ "learning_rate": 7.653061224489796e-06,
541
+ "loss": 0.0005,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.7857142857142857,
546
+ "grad_norm": 0.00028783048037439585,
547
+ "learning_rate": 7.755102040816327e-06,
548
+ "loss": 0.0,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.7959183673469388,
553
+ "grad_norm": 0.011970845982432365,
554
+ "learning_rate": 7.857142857142858e-06,
555
+ "loss": 0.0001,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.8061224489795918,
560
+ "grad_norm": 0.37045904994010925,
561
+ "learning_rate": 7.959183673469388e-06,
562
+ "loss": 0.0025,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.8163265306122449,
567
+ "grad_norm": 0.00590208824723959,
568
+ "learning_rate": 8.06122448979592e-06,
569
+ "loss": 0.0,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.826530612244898,
574
+ "grad_norm": 0.1372489035129547,
575
+ "learning_rate": 8.16326530612245e-06,
576
+ "loss": 0.0012,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.8367346938775511,
581
+ "grad_norm": 0.024213174358010292,
582
+ "learning_rate": 8.26530612244898e-06,
583
+ "loss": 0.0003,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.8469387755102041,
588
+ "grad_norm": 0.023818498477339745,
589
+ "learning_rate": 8.36734693877551e-06,
590
+ "loss": 0.0002,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.8571428571428571,
595
+ "grad_norm": 0.003695722436532378,
596
+ "learning_rate": 8.469387755102042e-06,
597
+ "loss": 0.0,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.8673469387755102,
602
+ "grad_norm": 0.0007995363557711244,
603
+ "learning_rate": 8.571428571428571e-06,
604
+ "loss": 0.0,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.8775510204081632,
609
+ "grad_norm": 0.0013144081458449364,
610
+ "learning_rate": 8.673469387755103e-06,
611
+ "loss": 0.0,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.8877551020408163,
616
+ "grad_norm": 0.012435175478458405,
617
+ "learning_rate": 8.775510204081633e-06,
618
+ "loss": 0.0002,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.8979591836734694,
623
+ "grad_norm": 0.0652078241109848,
624
+ "learning_rate": 8.877551020408163e-06,
625
+ "loss": 0.0009,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.9081632653061225,
630
+ "grad_norm": 0.35363656282424927,
631
+ "learning_rate": 8.979591836734695e-06,
632
+ "loss": 0.0067,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.9183673469387755,
637
+ "grad_norm": 0.004570689518004656,
638
+ "learning_rate": 9.081632653061225e-06,
639
+ "loss": 0.0,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.9285714285714286,
644
+ "grad_norm": 0.0073068393394351006,
645
+ "learning_rate": 9.183673469387756e-06,
646
+ "loss": 0.0001,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.9387755102040817,
651
+ "grad_norm": 0.09485316276550293,
652
+ "learning_rate": 9.285714285714288e-06,
653
+ "loss": 0.0008,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.9489795918367347,
658
+ "grad_norm": 0.3648199141025543,
659
+ "learning_rate": 9.387755102040818e-06,
660
+ "loss": 0.0031,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.9591836734693877,
665
+ "grad_norm": 0.030145330354571342,
666
+ "learning_rate": 9.489795918367348e-06,
667
+ "loss": 0.0004,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.9693877551020408,
672
+ "grad_norm": 0.02468164637684822,
673
+ "learning_rate": 9.591836734693878e-06,
674
+ "loss": 0.0004,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.9795918367346939,
679
+ "grad_norm": 0.013045134954154491,
680
+ "learning_rate": 9.693877551020408e-06,
681
+ "loss": 0.0001,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.9897959183673469,
686
+ "grad_norm": 0.043702784925699234,
687
+ "learning_rate": 9.795918367346939e-06,
688
+ "loss": 0.0004,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 1.0,
693
+ "grad_norm": 0.04222981631755829,
694
+ "learning_rate": 9.89795918367347e-06,
695
+ "loss": 0.0005,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 1.0,
700
+ "eval_dim_128_cosine_accuracy@1": 0.3559539052496799,
701
+ "eval_dim_128_cosine_accuracy@10": 0.4186939820742638,
702
+ "eval_dim_128_cosine_accuracy@3": 0.3617157490396927,
703
+ "eval_dim_128_cosine_accuracy@5": 0.39244558258642764,
704
+ "eval_dim_128_cosine_map@100": 0.43535825619272106,
705
+ "eval_dim_128_cosine_mrr@10": 0.3671173505680543,
706
+ "eval_dim_128_cosine_ndcg@10": 0.3790325714206647,
707
+ "eval_dim_128_cosine_precision@1": 0.3559539052496799,
708
+ "eval_dim_128_cosine_precision@10": 0.32131882202304735,
709
+ "eval_dim_128_cosine_precision@3": 0.35552710200597526,
710
+ "eval_dim_128_cosine_precision@5": 0.3490396927016646,
711
+ "eval_dim_128_cosine_recall@1": 0.037575464818099744,
712
+ "eval_dim_128_cosine_recall@10": 0.2541985714643628,
713
+ "eval_dim_128_cosine_recall@3": 0.11032964908822472,
714
+ "eval_dim_128_cosine_recall@5": 0.16793427308834435,
715
+ "eval_dim_256_cosine_accuracy@1": 0.3873239436619718,
716
+ "eval_dim_256_cosine_accuracy@10": 0.4494238156209987,
717
+ "eval_dim_256_cosine_accuracy@3": 0.39244558258642764,
718
+ "eval_dim_256_cosine_accuracy@5": 0.4206145966709347,
719
+ "eval_dim_256_cosine_map@100": 0.4661645952118268,
720
+ "eval_dim_256_cosine_mrr@10": 0.39812790886734506,
721
+ "eval_dim_256_cosine_ndcg@10": 0.40977946157999073,
722
+ "eval_dim_256_cosine_precision@1": 0.3873239436619718,
723
+ "eval_dim_256_cosine_precision@10": 0.348527528809219,
724
+ "eval_dim_256_cosine_precision@3": 0.3868971404182671,
725
+ "eval_dim_256_cosine_precision@5": 0.37912932138284255,
726
+ "eval_dim_256_cosine_recall@1": 0.04023203819999771,
727
+ "eval_dim_256_cosine_recall@10": 0.27112137316286944,
728
+ "eval_dim_256_cosine_recall@3": 0.1180462190143581,
729
+ "eval_dim_256_cosine_recall@5": 0.17956095699785507,
730
+ "eval_dim_512_cosine_accuracy@1": 0.39500640204865556,
731
+ "eval_dim_512_cosine_accuracy@10": 0.4532650448143406,
732
+ "eval_dim_512_cosine_accuracy@3": 0.39884763124199746,
733
+ "eval_dim_512_cosine_accuracy@5": 0.42509603072983354,
734
+ "eval_dim_512_cosine_map@100": 0.47311757377710084,
735
+ "eval_dim_512_cosine_mrr@10": 0.4048785135052737,
736
+ "eval_dim_512_cosine_ndcg@10": 0.4154101738314148,
737
+ "eval_dim_512_cosine_precision@1": 0.39500640204865556,
738
+ "eval_dim_512_cosine_precision@10": 0.35102432778489123,
739
+ "eval_dim_512_cosine_precision@3": 0.393939393939394,
740
+ "eval_dim_512_cosine_precision@5": 0.3846350832266325,
741
+ "eval_dim_512_cosine_recall@1": 0.04167554612344552,
742
+ "eval_dim_512_cosine_recall@10": 0.27558399878065315,
743
+ "eval_dim_512_cosine_recall@3": 0.12185555036210068,
744
+ "eval_dim_512_cosine_recall@5": 0.18440910016156958,
745
+ "eval_dim_64_cosine_accuracy@1": 0.31306017925736235,
746
+ "eval_dim_64_cosine_accuracy@10": 0.3758002560819462,
747
+ "eval_dim_64_cosine_accuracy@3": 0.31946222791293216,
748
+ "eval_dim_64_cosine_accuracy@5": 0.34635083226632524,
749
+ "eval_dim_64_cosine_map@100": 0.3923627170196659,
750
+ "eval_dim_64_cosine_mrr@10": 0.3240625571611481,
751
+ "eval_dim_64_cosine_ndcg@10": 0.33574924678086643,
752
+ "eval_dim_64_cosine_precision@1": 0.31306017925736235,
753
+ "eval_dim_64_cosine_precision@10": 0.2819462227912932,
754
+ "eval_dim_64_cosine_precision@3": 0.313486982501067,
755
+ "eval_dim_64_cosine_precision@5": 0.3075544174135723,
756
+ "eval_dim_64_cosine_recall@1": 0.033872169883188745,
757
+ "eval_dim_64_cosine_recall@10": 0.228651154461535,
758
+ "eval_dim_64_cosine_recall@3": 0.09984524687478234,
759
+ "eval_dim_64_cosine_recall@5": 0.15245541388627262,
760
+ "eval_dim_768_cosine_accuracy@1": 0.4026888604353393,
761
+ "eval_dim_768_cosine_accuracy@10": 0.469270166453265,
762
+ "eval_dim_768_cosine_accuracy@3": 0.4065300896286812,
763
+ "eval_dim_768_cosine_accuracy@5": 0.4359795134443022,
764
+ "eval_dim_768_cosine_map@100": 0.48436770951404184,
765
+ "eval_dim_768_cosine_mrr@10": 0.41397348738898004,
766
+ "eval_dim_768_cosine_ndcg@10": 0.42608814635365755,
767
+ "eval_dim_768_cosine_precision@1": 0.4026888604353393,
768
+ "eval_dim_768_cosine_precision@10": 0.36241997439180534,
769
+ "eval_dim_768_cosine_precision@3": 0.4016218523260776,
770
+ "eval_dim_768_cosine_precision@5": 0.3929577464788732,
771
+ "eval_dim_768_cosine_recall@1": 0.042158204863822595,
772
+ "eval_dim_768_cosine_recall@10": 0.28222410577862556,
773
+ "eval_dim_768_cosine_recall@3": 0.12340911592737758,
774
+ "eval_dim_768_cosine_recall@5": 0.18693795146685696,
775
+ "eval_runtime": 183.9141,
776
+ "eval_samples_per_second": 0.0,
777
+ "eval_sequential_score": 0.33574924678086643,
778
+ "eval_steps_per_second": 0.0,
779
+ "step": 98
780
+ }
781
+ ],
782
+ "logging_steps": 1,
783
+ "max_steps": 1960,
784
+ "num_input_tokens_seen": 0,
785
+ "num_train_epochs": 20,
786
+ "save_steps": 500,
787
+ "stateful_callbacks": {
788
+ "EarlyStoppingCallback": {
789
+ "args": {
790
+ "early_stopping_patience": 2,
791
+ "early_stopping_threshold": 0.0
792
+ },
793
+ "attributes": {
794
+ "early_stopping_patience_counter": 0
795
+ }
796
+ },
797
+ "TrainerControl": {
798
+ "args": {
799
+ "should_epoch_stop": false,
800
+ "should_evaluate": false,
801
+ "should_log": false,
802
+ "should_save": true,
803
+ "should_training_stop": false
804
+ },
805
+ "attributes": {}
806
+ }
807
+ },
808
+ "total_flos": 0.0,
809
+ "train_batch_size": 2,
810
+ "trial_name": null,
811
+ "trial_params": null
812
+ }
checkpoint-98/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a8a832f799db6edc75ec7d1e9c1a684653e1255a6753af8a20470c25db5513
3
+ size 6097
eval/Information-Retrieval_evaluation_dim_128_results.csv CHANGED
@@ -10,3 +10,6 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
10
  2.0,196,0.3553137003841229,0.3617157490396927,0.38988476312419973,0.4167733674775928,0.3553137003841229,0.038627357901670004,0.35552710200597526,0.11364993084786716,0.34814340588988474,0.17269211708889393,0.3176696542893726,0.2586321191653615,0.36626094953559696,0.37821276050416114,0.4346957375897274
11
  3.0,294,0.34763124199743917,0.353393085787452,0.38348271446862997,0.4199743918053777,0.34763124199743917,0.036574097887490074,0.34784464361929146,0.10792857681593648,0.34135723431498083,0.16397305340057647,0.318629961587708,0.25234098526291365,0.36006899985773183,0.37378784294095396,0.4332520995017439
12
  4.0,392,0.34507042253521125,0.35147247119078107,0.38028169014084506,0.41101152368758004,0.34507042253521125,0.03674308261195813,0.34571062740076824,0.10854200462134246,0.3390524967989757,0.16528054487712734,0.3124839948783611,0.24990838450036762,0.3567330752189903,0.3687761857923042,0.43107536367707355
 
 
 
 
10
  2.0,196,0.3553137003841229,0.3617157490396927,0.38988476312419973,0.4167733674775928,0.3553137003841229,0.038627357901670004,0.35552710200597526,0.11364993084786716,0.34814340588988474,0.17269211708889393,0.3176696542893726,0.2586321191653615,0.36626094953559696,0.37821276050416114,0.4346957375897274
11
  3.0,294,0.34763124199743917,0.353393085787452,0.38348271446862997,0.4199743918053777,0.34763124199743917,0.036574097887490074,0.34784464361929146,0.10792857681593648,0.34135723431498083,0.16397305340057647,0.318629961587708,0.25234098526291365,0.36006899985773183,0.37378784294095396,0.4332520995017439
12
  4.0,392,0.34507042253521125,0.35147247119078107,0.38028169014084506,0.41101152368758004,0.34507042253521125,0.03674308261195813,0.34571062740076824,0.10854200462134246,0.3390524967989757,0.16528054487712734,0.3124839948783611,0.24990838450036762,0.3567330752189903,0.3687761857923042,0.43107536367707355
13
+ 1.0,98,0.3559539052496799,0.3617157490396927,0.39244558258642764,0.4186939820742638,0.3559539052496799,0.037575464818099744,0.35552710200597526,0.11032964908822472,0.3490396927016646,0.16793427308834435,0.32131882202304735,0.2541985714643628,0.3671173505680543,0.3790325714206647,0.43535825619272106
14
+ 2.0,196,0.34507042253521125,0.35147247119078107,0.38412291933418696,0.41357234314980795,0.34507042253521125,0.03779060006776101,0.34528382415706355,0.11111523194759507,0.3390524967989757,0.16892829224345354,0.3118437900128041,0.2542611355685967,0.35724981200333256,0.3705587688392343,0.4308148525481854
15
+ 3.0,294,0.353393085787452,0.35979513444302175,0.3847631241997439,0.4142125480153649,0.353393085787452,0.036464605000445925,0.35381988903115663,0.10761057769873429,0.34609475032010245,0.1630330675703894,0.31952624839948784,0.2478046074721795,0.36410660935308786,0.37609461891444046,0.4332448707193373
eval/Information-Retrieval_evaluation_dim_256_results.csv CHANGED
@@ -10,3 +10,6 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
10
  2.0,196,0.3854033290653009,0.38988476312419973,0.4199743918053777,0.4500640204865557,0.3854033290653009,0.040129876225339534,0.3851899274434486,0.11811318592862516,0.37759282970550573,0.17998663619137895,0.3473111395646607,0.2712240355508765,0.39665874032071163,0.40840027342579643,0.4644962788032259
11
  3.0,294,0.3905249679897567,0.39564660691421255,0.4199743918053777,0.4513444302176697,0.3905249679897567,0.040552940063526215,0.39031156636790443,0.11930917453107383,0.3814340588988476,0.1806280229444006,0.3508962868117798,0.2707983661312114,0.40107767819035406,0.4117889497609331,0.4689769976086867
12
  4.0,392,0.37964148527528807,0.3873239436619718,0.4142125480153649,0.44494238156209986,0.37964148527528807,0.039124417631678836,0.38028169014084506,0.1153665545855213,0.3734955185659411,0.1757838879336913,0.34526248399487836,0.2665534618848508,0.3914128711663921,0.4037131645468801,0.4618802165631398
 
 
 
 
10
  2.0,196,0.3854033290653009,0.38988476312419973,0.4199743918053777,0.4500640204865557,0.3854033290653009,0.040129876225339534,0.3851899274434486,0.11811318592862516,0.37759282970550573,0.17998663619137895,0.3473111395646607,0.2712240355508765,0.39665874032071163,0.40840027342579643,0.4644962788032259
11
  3.0,294,0.3905249679897567,0.39564660691421255,0.4199743918053777,0.4513444302176697,0.3905249679897567,0.040552940063526215,0.39031156636790443,0.11930917453107383,0.3814340588988476,0.1806280229444006,0.3508962868117798,0.2707983661312114,0.40107767819035406,0.4117889497609331,0.4689769976086867
12
  4.0,392,0.37964148527528807,0.3873239436619718,0.4142125480153649,0.44494238156209986,0.37964148527528807,0.039124417631678836,0.38028169014084506,0.1153665545855213,0.3734955185659411,0.1757838879336913,0.34526248399487836,0.2665534618848508,0.3914128711663921,0.4037131645468801,0.4618802165631398
13
+ 1.0,98,0.3873239436619718,0.39244558258642764,0.4206145966709347,0.4494238156209987,0.3873239436619718,0.04023203819999771,0.3868971404182671,0.1180462190143581,0.37912932138284255,0.17956095699785507,0.348527528809219,0.27112137316286944,0.39812790886734506,0.40977946157999073,0.4661645952118268
14
+ 2.0,196,0.37900128040973113,0.38348271446862997,0.4154929577464789,0.44878361075544176,0.37900128040973113,0.04027834797290038,0.37793427230046944,0.11799375375346732,0.3701664532650448,0.17890927920221725,0.34206145966709345,0.27059289435393563,0.3909187447919838,0.4032243160613258,0.46299996573163127
15
+ 3.0,294,0.3860435339308579,0.39244558258642764,0.4167733674775928,0.44814340588988477,0.3860435339308579,0.03962321211820953,0.3866837387964149,0.11744680009464445,0.37836107554417414,0.17843204724958808,0.3476952624839948,0.26814407122008105,0.3969033900371925,0.40839722669645323,0.4642655010516818
eval/Information-Retrieval_evaluation_dim_512_results.csv CHANGED
@@ -10,3 +10,6 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
10
  2.0,196,0.3905249679897567,0.39436619718309857,0.42573623559539053,0.4526248399487836,0.3905249679897567,0.041244569952314354,0.38988476312419973,0.12120282671426413,0.3818181818181818,0.18424574322417833,0.3498719590268886,0.27661387603808657,0.4012791394833645,0.41305830961162454,0.46989479441394943
11
  3.0,294,0.39820742637644047,0.4046094750320102,0.4263764404609475,0.45838668373879643,0.39820742637644047,0.04131054911164303,0.3986342296201451,0.12173427262435019,0.3893725992317541,0.18446122921285565,0.35755441741357236,0.27750046911354176,0.4088185679734973,0.41980419360887333,0.47818911424096583
12
  4.0,392,0.39308578745198464,0.4020486555697823,0.4225352112676056,0.45774647887323944,0.39308578745198464,0.04075326438991671,0.3941527955612463,0.12015983913317638,0.3854033290653009,0.1819336388905291,0.3544174135723431,0.27537478153215217,0.404457807450765,0.41611852026670604,0.4759217537331298
 
 
 
 
10
  2.0,196,0.3905249679897567,0.39436619718309857,0.42573623559539053,0.4526248399487836,0.3905249679897567,0.041244569952314354,0.38988476312419973,0.12120282671426413,0.3818181818181818,0.18424574322417833,0.3498719590268886,0.27661387603808657,0.4012791394833645,0.41305830961162454,0.46989479441394943
11
  3.0,294,0.39820742637644047,0.4046094750320102,0.4263764404609475,0.45838668373879643,0.39820742637644047,0.04131054911164303,0.3986342296201451,0.12173427262435019,0.3893725992317541,0.18446122921285565,0.35755441741357236,0.27750046911354176,0.4088185679734973,0.41980419360887333,0.47818911424096583
12
  4.0,392,0.39308578745198464,0.4020486555697823,0.4225352112676056,0.45774647887323944,0.39308578745198464,0.04075326438991671,0.3941527955612463,0.12015983913317638,0.3854033290653009,0.1819336388905291,0.3544174135723431,0.27537478153215217,0.404457807450765,0.41611852026670604,0.4759217537331298
13
+ 1.0,98,0.39500640204865556,0.39884763124199746,0.42509603072983354,0.4532650448143406,0.39500640204865556,0.04167554612344552,0.393939393939394,0.12185555036210068,0.3846350832266325,0.18440910016156958,0.35102432778489123,0.27558399878065315,0.4048785135052737,0.4154101738314148,0.47311757377710084
14
+ 2.0,196,0.38028169014084506,0.38412291933418696,0.4180537772087068,0.44430217669654287,0.38028169014084506,0.041217743020374786,0.37942808365343583,0.12079180058349871,0.3714468629961588,0.18295012439591,0.3401408450704225,0.2733570628886365,0.39145656768896175,0.4038131313154522,0.46609447657301045
15
+ 3.0,294,0.39436619718309857,0.39884763124199746,0.4180537772087068,0.4532650448143406,0.39436619718309857,0.04042853140523698,0.39436619718309857,0.1196927035383132,0.38412291933418696,0.18113736600353658,0.35262483994878363,0.2725004471030787,0.4040899437026195,0.41401334483433183,0.47229660803723117
eval/Information-Retrieval_evaluation_dim_64_results.csv CHANGED
@@ -10,3 +10,6 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
10
  2.0,196,0.3028169014084507,0.31049935979513443,0.3399487836107554,0.3719590268886043,0.3028169014084507,0.03383408444379441,0.30367050789586,0.09992674550587541,0.2982074263764405,0.15219083914438378,0.2746478873239437,0.22977756399761853,0.3150631059081757,0.32829551547419517,0.3845480162631014
11
  3.0,294,0.29513444302176695,0.30153649167733676,0.3265044814340589,0.3559539052496799,0.29513444302176695,0.0310144236339133,0.29598804950917623,0.09171812890758381,0.2906530089628681,0.13962628846987257,0.2701024327784891,0.21535709630112995,0.3058733715423852,0.3175516019719684,0.3770640294522326
12
  4.0,392,0.3060179257362356,0.3079385403329065,0.33418693982074266,0.3681177976952625,0.3060179257362356,0.033221031499260444,0.30516431924882625,0.09768707755697564,0.29833546734955185,0.14884668347538832,0.2750960307298336,0.23035737422209354,0.3159395768550693,0.3271193606854658,0.38669906496360756
 
 
 
 
10
  2.0,196,0.3028169014084507,0.31049935979513443,0.3399487836107554,0.3719590268886043,0.3028169014084507,0.03383408444379441,0.30367050789586,0.09992674550587541,0.2982074263764405,0.15219083914438378,0.2746478873239437,0.22977756399761853,0.3150631059081757,0.32829551547419517,0.3845480162631014
11
  3.0,294,0.29513444302176695,0.30153649167733676,0.3265044814340589,0.3559539052496799,0.29513444302176695,0.0310144236339133,0.29598804950917623,0.09171812890758381,0.2906530089628681,0.13962628846987257,0.2701024327784891,0.21535709630112995,0.3058733715423852,0.3175516019719684,0.3770640294522326
12
  4.0,392,0.3060179257362356,0.3079385403329065,0.33418693982074266,0.3681177976952625,0.3060179257362356,0.033221031499260444,0.30516431924882625,0.09768707755697564,0.29833546734955185,0.14884668347538832,0.2750960307298336,0.23035737422209354,0.3159395768550693,0.3271193606854658,0.38669906496360756
13
+ 1.0,98,0.31306017925736235,0.31946222791293216,0.34635083226632524,0.3758002560819462,0.31306017925736235,0.033872169883188745,0.313486982501067,0.09984524687478234,0.3075544174135723,0.15245541388627262,0.2819462227912932,0.228651154461535,0.3240625571611481,0.33574924678086643,0.3923627170196659
14
+ 2.0,196,0.3066581306017926,0.3111395646606914,0.3354673495518566,0.36427656850192064,0.3066581306017926,0.03426882400643975,0.30623132735808795,0.10063654687404197,0.2988476312419974,0.1525674849860816,0.2722151088348272,0.227699287913431,0.31652084222506716,0.32687333076394454,0.38693424826091144
15
+ 3.0,294,0.3079385403329065,0.31562099871959026,0.3348271446862996,0.36939820742637647,0.3079385403329065,0.03154669390524976,0.3092189500640205,0.09368644321809669,0.3026888604353393,0.14256307415283676,0.28040973111395645,0.21725520447019792,0.3185400280470698,0.3297439353321731,0.3853517715303568
eval/Information-Retrieval_evaluation_dim_768_results.csv CHANGED
@@ -10,3 +10,6 @@ epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accurac
10
  2.0,196,0.4001280409731114,0.4058898847631242,0.4372599231754161,0.471190781049936,0.4001280409731114,0.042347333926694236,0.3997012377294067,0.1240435037991904,0.3919334186939821,0.18802233648261496,0.3613316261203586,0.2824349113791798,0.4124385200089422,0.4252421162228998,0.4841264299392437
11
  3.0,294,0.4020486555697823,0.40717029449423814,0.4327784891165173,0.4673495518565941,0.4020486555697823,0.04197809637481895,0.40183525394792996,0.12353744887550396,0.3928297055057618,0.18676497822254692,0.36235595390524966,0.2818107957085131,0.41323521939719104,0.4249694897262844,0.4842045422278839
12
  4.0,392,0.39436619718309857,0.4014084507042254,0.4321382842509603,0.4679897567221511,0.39436619718309857,0.04157946017051904,0.39457959880495086,0.12214811084382268,0.38706786171574903,0.18499389797471857,0.35928297055057623,0.2820017295188253,0.4073224701745827,0.42115237797407157,0.4829322015305782
 
 
 
 
10
  2.0,196,0.4001280409731114,0.4058898847631242,0.4372599231754161,0.471190781049936,0.4001280409731114,0.042347333926694236,0.3997012377294067,0.1240435037991904,0.3919334186939821,0.18802233648261496,0.3613316261203586,0.2824349113791798,0.4124385200089422,0.4252421162228998,0.4841264299392437
11
  3.0,294,0.4020486555697823,0.40717029449423814,0.4327784891165173,0.4673495518565941,0.4020486555697823,0.04197809637481895,0.40183525394792996,0.12353744887550396,0.3928297055057618,0.18676497822254692,0.36235595390524966,0.2818107957085131,0.41323521939719104,0.4249694897262844,0.4842045422278839
12
  4.0,392,0.39436619718309857,0.4014084507042254,0.4321382842509603,0.4679897567221511,0.39436619718309857,0.04157946017051904,0.39457959880495086,0.12214811084382268,0.38706786171574903,0.18499389797471857,0.35928297055057623,0.2820017295188253,0.4073224701745827,0.42115237797407157,0.4829322015305782
13
+ 1.0,98,0.4026888604353393,0.4065300896286812,0.4359795134443022,0.469270166453265,0.4026888604353393,0.042158204863822595,0.4016218523260776,0.12340911592737758,0.3929577464788732,0.18693795146685696,0.36241997439180534,0.28222410577862556,0.41397348738898004,0.42608814635365755,0.48436770951404184
14
+ 2.0,196,0.3758002560819462,0.38156209987195905,0.41613316261203587,0.4468629961587708,0.3758002560819462,0.04146170353478509,0.37537345283824153,0.12127139138148112,0.3681177976952625,0.18355055377188786,0.33898847631241996,0.275632920609814,0.38836326037030233,0.4020597577790278,0.4686277000119534
15
+ 3.0,294,0.4020486555697823,0.4052496798975672,0.42893725992317544,0.46094750320102434,0.4020486555697823,0.04175313555284748,0.401195049082373,0.12278476862052412,0.39129321382842513,0.18536806181354978,0.3589628681177977,0.2777345271673647,0.4118049204316806,0.4220301651533148,0.4807606113925945
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43d09dad89bfac078d48beef8c741a8d192bf63470eada6ae8d559b77880a725
3
  size 596070136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5a818377bdcd1bbf4879eeeb4ba232b290e971113ba2fd94ca9587f19f3f3
3
  size 596070136
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7b1978ddb1f8ac53331bb6b2e761a7e89618f491581115c3167505094898d39
3
  size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a8a832f799db6edc75ec7d1e9c1a684653e1255a6753af8a20470c25db5513
3
  size 6097