Commit
•
b6b47ba
1
Parent(s):
5dc1969
Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +849 -0
- config.json +32 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,849 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
library_name: sentence-transformers
|
6 |
+
tags:
|
7 |
+
- sentence-transformers
|
8 |
+
- sentence-similarity
|
9 |
+
- feature-extraction
|
10 |
+
- generated_from_trainer
|
11 |
+
- dataset_size:161
|
12 |
+
- loss:MatryoshkaLoss
|
13 |
+
- loss:MultipleNegativesRankingLoss
|
14 |
+
base_model: BAAI/bge-base-en-v1.5
|
15 |
+
datasets: []
|
16 |
+
metrics:
|
17 |
+
- cosine_accuracy@1
|
18 |
+
- cosine_accuracy@3
|
19 |
+
- cosine_accuracy@5
|
20 |
+
- cosine_accuracy@10
|
21 |
+
- cosine_precision@1
|
22 |
+
- cosine_precision@3
|
23 |
+
- cosine_precision@5
|
24 |
+
- cosine_precision@10
|
25 |
+
- cosine_recall@1
|
26 |
+
- cosine_recall@3
|
27 |
+
- cosine_recall@5
|
28 |
+
- cosine_recall@10
|
29 |
+
- cosine_ndcg@10
|
30 |
+
- cosine_mrr@10
|
31 |
+
- cosine_map@100
|
32 |
+
widget:
|
33 |
+
- source_sentence: 'As per Part II of the PDPA, Personal Data Protection Commission
|
34 |
+
(PDPC) is the
|
35 |
+
|
36 |
+
regulatory body to enforce the provisions of PDPA. The PDPC is empowered with
|
37 |
+
|
38 |
+
broad discretion to issue remedial directions, initiate investigation
|
39 |
+
|
40 |
+
inquiries, and impose fines and penalties on the organisations in case of any
|
41 |
+
|
42 |
+
non-compliance of PDPA.
|
43 |
+
|
44 |
+
|
45 |
+
1
|
46 |
+
|
47 |
+
|
48 |
+
If organisations misuse the personal data or hide information concerning its
|
49 |
+
|
50 |
+
collection, use, or disclosure, PDPA states penalties not exceeding **S$50,000
|
51 |
+
|
52 |
+
(approx. $36,000)**.
|
53 |
+
|
54 |
+
|
55 |
+
2
|
56 |
+
|
57 |
+
|
58 |
+
Penalty for hindering a PDPC investigation can lead to a fine of not more than
|
59 |
+
|
60 |
+
**S$100,000 (approx. $72,000)**. The PDPA states that companies are also
|
61 |
+
|
62 |
+
liable for their employees’ actions, whether they are aware of them or not.
|
63 |
+
|
64 |
+
|
65 |
+
3
|
66 |
+
|
67 |
+
|
68 |
+
New amendments to PDPA have enforced increased financial penalties for
|
69 |
+
|
70 |
+
breaches of the PDPA up to **10%** of annual gross turnover in Singapore, or
|
71 |
+
|
72 |
+
**S$ 1 million** , whichever is higher.
|
73 |
+
|
74 |
+
|
75 |
+
4
|
76 |
+
|
77 |
+
|
78 |
+
Non-compliance with specific provisions under the PDPA may also constitute an
|
79 |
+
|
80 |
+
offense, for which a fine or a term of **imprisonment** may be imposed.
|
81 |
+
|
82 |
+
|
83 |
+
5
|
84 |
+
|
85 |
+
|
86 |
+
An individual can bring a private civil action against an organisation for
|
87 |
+
|
88 |
+
having suffered **loss or damage** directly due to a contravention of the
|
89 |
+
|
90 |
+
provisions of the PDPA.'
|
91 |
+
sentences:
|
92 |
+
- What is the right to notice under the CCPA?
|
93 |
+
- What are the risks of non-compliance with the PDPA?
|
94 |
+
- What is the definition of personal data under the PDP Law?
|
95 |
+
- source_sentence: The DPA requires all data controllers to take appropriate technical
|
96 |
+
and organisational measures that are necessary to protect data from unauthorised
|
97 |
+
destruction, negligent loss, unauthorised alteration or access and any other unauthorised
|
98 |
+
processing of the data.
|
99 |
+
sentences:
|
100 |
+
- Which regulatory authority enforces GDPR in France?
|
101 |
+
- What are the security requirements under the DPA?
|
102 |
+
- How do PIPEDA and GDPR differ?
|
103 |
+
- source_sentence: if the data controller or the data processor holds a valid registration
|
104 |
+
certificate authorizing him or her to store personal data outside Rwanda
|
105 |
+
sentences:
|
106 |
+
- What is the difference between GDPR and a Data Protection Act?
|
107 |
+
- What is the voluntary certification by the CPPA?
|
108 |
+
- Where is personal data storage outside of Rwanda permitted?
|
109 |
+
- source_sentence: The PDP law will regulate sensitive personal data as well as other
|
110 |
+
personal data that may endanger or harm the privacy of the data subject.
|
111 |
+
sentences:
|
112 |
+
- What is the material scope of the PDP Law?
|
113 |
+
- What is the definition of personal information under the DPA in the Philippines?
|
114 |
+
- What does Securiti offer to help with data privacy compliance?
|
115 |
+
- source_sentence: Thailand's PDPA applies to any legal entity collecting, using,
|
116 |
+
or disclosing a natural (and alive) person's personal data.
|
117 |
+
sentences:
|
118 |
+
- Who does the Thailand's PDPA apply to?
|
119 |
+
- What penalties could an organization face for infringing Kenya's Data Protection
|
120 |
+
Act?
|
121 |
+
- What is the CPRA?
|
122 |
+
pipeline_tag: sentence-similarity
|
123 |
+
model-index:
|
124 |
+
- name: SentenceTransformer based on BAAI/bge-base-en-v1.5
|
125 |
+
results:
|
126 |
+
- task:
|
127 |
+
type: information-retrieval
|
128 |
+
name: Information Retrieval
|
129 |
+
dataset:
|
130 |
+
name: dim 768
|
131 |
+
type: dim_768
|
132 |
+
metrics:
|
133 |
+
- type: cosine_accuracy@1
|
134 |
+
value: 0.5
|
135 |
+
name: Cosine Accuracy@1
|
136 |
+
- type: cosine_accuracy@3
|
137 |
+
value: 0.8333333333333334
|
138 |
+
name: Cosine Accuracy@3
|
139 |
+
- type: cosine_accuracy@5
|
140 |
+
value: 0.9444444444444444
|
141 |
+
name: Cosine Accuracy@5
|
142 |
+
- type: cosine_accuracy@10
|
143 |
+
value: 1.0
|
144 |
+
name: Cosine Accuracy@10
|
145 |
+
- type: cosine_precision@1
|
146 |
+
value: 0.5
|
147 |
+
name: Cosine Precision@1
|
148 |
+
- type: cosine_precision@3
|
149 |
+
value: 0.27777777777777773
|
150 |
+
name: Cosine Precision@3
|
151 |
+
- type: cosine_precision@5
|
152 |
+
value: 0.1888888888888889
|
153 |
+
name: Cosine Precision@5
|
154 |
+
- type: cosine_precision@10
|
155 |
+
value: 0.10000000000000002
|
156 |
+
name: Cosine Precision@10
|
157 |
+
- type: cosine_recall@1
|
158 |
+
value: 0.5
|
159 |
+
name: Cosine Recall@1
|
160 |
+
- type: cosine_recall@3
|
161 |
+
value: 0.8333333333333334
|
162 |
+
name: Cosine Recall@3
|
163 |
+
- type: cosine_recall@5
|
164 |
+
value: 0.9444444444444444
|
165 |
+
name: Cosine Recall@5
|
166 |
+
- type: cosine_recall@10
|
167 |
+
value: 1.0
|
168 |
+
name: Cosine Recall@10
|
169 |
+
- type: cosine_ndcg@10
|
170 |
+
value: 0.736082728585743
|
171 |
+
name: Cosine Ndcg@10
|
172 |
+
- type: cosine_mrr@10
|
173 |
+
value: 0.6515432098765431
|
174 |
+
name: Cosine Mrr@10
|
175 |
+
- type: cosine_map@100
|
176 |
+
value: 0.6515432098765432
|
177 |
+
name: Cosine Map@100
|
178 |
+
- task:
|
179 |
+
type: information-retrieval
|
180 |
+
name: Information Retrieval
|
181 |
+
dataset:
|
182 |
+
name: dim 512
|
183 |
+
type: dim_512
|
184 |
+
metrics:
|
185 |
+
- type: cosine_accuracy@1
|
186 |
+
value: 0.5
|
187 |
+
name: Cosine Accuracy@1
|
188 |
+
- type: cosine_accuracy@3
|
189 |
+
value: 0.7777777777777778
|
190 |
+
name: Cosine Accuracy@3
|
191 |
+
- type: cosine_accuracy@5
|
192 |
+
value: 0.9444444444444444
|
193 |
+
name: Cosine Accuracy@5
|
194 |
+
- type: cosine_accuracy@10
|
195 |
+
value: 1.0
|
196 |
+
name: Cosine Accuracy@10
|
197 |
+
- type: cosine_precision@1
|
198 |
+
value: 0.5
|
199 |
+
name: Cosine Precision@1
|
200 |
+
- type: cosine_precision@3
|
201 |
+
value: 0.25925925925925924
|
202 |
+
name: Cosine Precision@3
|
203 |
+
- type: cosine_precision@5
|
204 |
+
value: 0.1888888888888889
|
205 |
+
name: Cosine Precision@5
|
206 |
+
- type: cosine_precision@10
|
207 |
+
value: 0.10000000000000002
|
208 |
+
name: Cosine Precision@10
|
209 |
+
- type: cosine_recall@1
|
210 |
+
value: 0.5
|
211 |
+
name: Cosine Recall@1
|
212 |
+
- type: cosine_recall@3
|
213 |
+
value: 0.7777777777777778
|
214 |
+
name: Cosine Recall@3
|
215 |
+
- type: cosine_recall@5
|
216 |
+
value: 0.9444444444444444
|
217 |
+
name: Cosine Recall@5
|
218 |
+
- type: cosine_recall@10
|
219 |
+
value: 1.0
|
220 |
+
name: Cosine Recall@10
|
221 |
+
- type: cosine_ndcg@10
|
222 |
+
value: 0.744344523828935
|
223 |
+
name: Cosine Ndcg@10
|
224 |
+
- type: cosine_mrr@10
|
225 |
+
value: 0.6626543209876543
|
226 |
+
name: Cosine Mrr@10
|
227 |
+
- type: cosine_map@100
|
228 |
+
value: 0.6626543209876543
|
229 |
+
name: Cosine Map@100
|
230 |
+
- task:
|
231 |
+
type: information-retrieval
|
232 |
+
name: Information Retrieval
|
233 |
+
dataset:
|
234 |
+
name: dim 256
|
235 |
+
type: dim_256
|
236 |
+
metrics:
|
237 |
+
- type: cosine_accuracy@1
|
238 |
+
value: 0.5
|
239 |
+
name: Cosine Accuracy@1
|
240 |
+
- type: cosine_accuracy@3
|
241 |
+
value: 0.8888888888888888
|
242 |
+
name: Cosine Accuracy@3
|
243 |
+
- type: cosine_accuracy@5
|
244 |
+
value: 0.8888888888888888
|
245 |
+
name: Cosine Accuracy@5
|
246 |
+
- type: cosine_accuracy@10
|
247 |
+
value: 1.0
|
248 |
+
name: Cosine Accuracy@10
|
249 |
+
- type: cosine_precision@1
|
250 |
+
value: 0.5
|
251 |
+
name: Cosine Precision@1
|
252 |
+
- type: cosine_precision@3
|
253 |
+
value: 0.2962962962962962
|
254 |
+
name: Cosine Precision@3
|
255 |
+
- type: cosine_precision@5
|
256 |
+
value: 0.1777777777777778
|
257 |
+
name: Cosine Precision@5
|
258 |
+
- type: cosine_precision@10
|
259 |
+
value: 0.10000000000000002
|
260 |
+
name: Cosine Precision@10
|
261 |
+
- type: cosine_recall@1
|
262 |
+
value: 0.5
|
263 |
+
name: Cosine Recall@1
|
264 |
+
- type: cosine_recall@3
|
265 |
+
value: 0.8888888888888888
|
266 |
+
name: Cosine Recall@3
|
267 |
+
- type: cosine_recall@5
|
268 |
+
value: 0.8888888888888888
|
269 |
+
name: Cosine Recall@5
|
270 |
+
- type: cosine_recall@10
|
271 |
+
value: 1.0
|
272 |
+
name: Cosine Recall@10
|
273 |
+
- type: cosine_ndcg@10
|
274 |
+
value: 0.7569877225340996
|
275 |
+
name: Cosine Ndcg@10
|
276 |
+
- type: cosine_mrr@10
|
277 |
+
value: 0.6790123456790123
|
278 |
+
name: Cosine Mrr@10
|
279 |
+
- type: cosine_map@100
|
280 |
+
value: 0.6790123456790124
|
281 |
+
name: Cosine Map@100
|
282 |
+
- task:
|
283 |
+
type: information-retrieval
|
284 |
+
name: Information Retrieval
|
285 |
+
dataset:
|
286 |
+
name: dim 128
|
287 |
+
type: dim_128
|
288 |
+
metrics:
|
289 |
+
- type: cosine_accuracy@1
|
290 |
+
value: 0.5
|
291 |
+
name: Cosine Accuracy@1
|
292 |
+
- type: cosine_accuracy@3
|
293 |
+
value: 0.8333333333333334
|
294 |
+
name: Cosine Accuracy@3
|
295 |
+
- type: cosine_accuracy@5
|
296 |
+
value: 0.8888888888888888
|
297 |
+
name: Cosine Accuracy@5
|
298 |
+
- type: cosine_accuracy@10
|
299 |
+
value: 0.9444444444444444
|
300 |
+
name: Cosine Accuracy@10
|
301 |
+
- type: cosine_precision@1
|
302 |
+
value: 0.5
|
303 |
+
name: Cosine Precision@1
|
304 |
+
- type: cosine_precision@3
|
305 |
+
value: 0.27777777777777773
|
306 |
+
name: Cosine Precision@3
|
307 |
+
- type: cosine_precision@5
|
308 |
+
value: 0.1777777777777778
|
309 |
+
name: Cosine Precision@5
|
310 |
+
- type: cosine_precision@10
|
311 |
+
value: 0.09444444444444446
|
312 |
+
name: Cosine Precision@10
|
313 |
+
- type: cosine_recall@1
|
314 |
+
value: 0.5
|
315 |
+
name: Cosine Recall@1
|
316 |
+
- type: cosine_recall@3
|
317 |
+
value: 0.8333333333333334
|
318 |
+
name: Cosine Recall@3
|
319 |
+
- type: cosine_recall@5
|
320 |
+
value: 0.8888888888888888
|
321 |
+
name: Cosine Recall@5
|
322 |
+
- type: cosine_recall@10
|
323 |
+
value: 0.9444444444444444
|
324 |
+
name: Cosine Recall@10
|
325 |
+
- type: cosine_ndcg@10
|
326 |
+
value: 0.7291386563584304
|
327 |
+
name: Cosine Ndcg@10
|
328 |
+
- type: cosine_mrr@10
|
329 |
+
value: 0.6589506172839507
|
330 |
+
name: Cosine Mrr@10
|
331 |
+
- type: cosine_map@100
|
332 |
+
value: 0.6604938271604938
|
333 |
+
name: Cosine Map@100
|
334 |
+
- task:
|
335 |
+
type: information-retrieval
|
336 |
+
name: Information Retrieval
|
337 |
+
dataset:
|
338 |
+
name: dim 64
|
339 |
+
type: dim_64
|
340 |
+
metrics:
|
341 |
+
- type: cosine_accuracy@1
|
342 |
+
value: 0.4444444444444444
|
343 |
+
name: Cosine Accuracy@1
|
344 |
+
- type: cosine_accuracy@3
|
345 |
+
value: 0.6111111111111112
|
346 |
+
name: Cosine Accuracy@3
|
347 |
+
- type: cosine_accuracy@5
|
348 |
+
value: 0.6666666666666666
|
349 |
+
name: Cosine Accuracy@5
|
350 |
+
- type: cosine_accuracy@10
|
351 |
+
value: 1.0
|
352 |
+
name: Cosine Accuracy@10
|
353 |
+
- type: cosine_precision@1
|
354 |
+
value: 0.4444444444444444
|
355 |
+
name: Cosine Precision@1
|
356 |
+
- type: cosine_precision@3
|
357 |
+
value: 0.2037037037037037
|
358 |
+
name: Cosine Precision@3
|
359 |
+
- type: cosine_precision@5
|
360 |
+
value: 0.13333333333333336
|
361 |
+
name: Cosine Precision@5
|
362 |
+
- type: cosine_precision@10
|
363 |
+
value: 0.10000000000000002
|
364 |
+
name: Cosine Precision@10
|
365 |
+
- type: cosine_recall@1
|
366 |
+
value: 0.4444444444444444
|
367 |
+
name: Cosine Recall@1
|
368 |
+
- type: cosine_recall@3
|
369 |
+
value: 0.6111111111111112
|
370 |
+
name: Cosine Recall@3
|
371 |
+
- type: cosine_recall@5
|
372 |
+
value: 0.6666666666666666
|
373 |
+
name: Cosine Recall@5
|
374 |
+
- type: cosine_recall@10
|
375 |
+
value: 1.0
|
376 |
+
name: Cosine Recall@10
|
377 |
+
- type: cosine_ndcg@10
|
378 |
+
value: 0.6740519326169271
|
379 |
+
name: Cosine Ndcg@10
|
380 |
+
- type: cosine_mrr@10
|
381 |
+
value: 0.5768298059964727
|
382 |
+
name: Cosine Mrr@10
|
383 |
+
- type: cosine_map@100
|
384 |
+
value: 0.5768298059964727
|
385 |
+
name: Cosine Map@100
|
386 |
+
---
|
387 |
+
|
388 |
+
# SentenceTransformer based on BAAI/bge-base-en-v1.5
|
389 |
+
|
390 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). 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.
|
391 |
+
|
392 |
+
## Model Details
|
393 |
+
|
394 |
+
### Model Description
|
395 |
+
- **Model Type:** Sentence Transformer
|
396 |
+
- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
|
397 |
+
- **Maximum Sequence Length:** 512 tokens
|
398 |
+
- **Output Dimensionality:** 768 tokens
|
399 |
+
- **Similarity Function:** Cosine Similarity
|
400 |
+
<!-- - **Training Dataset:** Unknown -->
|
401 |
+
- **Language:** en
|
402 |
+
- **License:** apache-2.0
|
403 |
+
|
404 |
+
### Model Sources
|
405 |
+
|
406 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
407 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
408 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
409 |
+
|
410 |
+
### Full Model Architecture
|
411 |
+
|
412 |
+
```
|
413 |
+
SentenceTransformer(
|
414 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
|
415 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
416 |
+
(2): Normalize()
|
417 |
+
)
|
418 |
+
```
|
419 |
+
|
420 |
+
## Usage
|
421 |
+
|
422 |
+
### Direct Usage (Sentence Transformers)
|
423 |
+
|
424 |
+
First install the Sentence Transformers library:
|
425 |
+
|
426 |
+
```bash
|
427 |
+
pip install -U sentence-transformers
|
428 |
+
```
|
429 |
+
|
430 |
+
Then you can load this model and run inference.
|
431 |
+
```python
|
432 |
+
from sentence_transformers import SentenceTransformer
|
433 |
+
|
434 |
+
# Download from the 🤗 Hub
|
435 |
+
model = SentenceTransformer("MugheesAwan11/bge-base-securiti-dataset-1-v5")
|
436 |
+
# Run inference
|
437 |
+
sentences = [
|
438 |
+
"Thailand's PDPA applies to any legal entity collecting, using, or disclosing a natural (and alive) person's personal data.",
|
439 |
+
"Who does the Thailand's PDPA apply to?",
|
440 |
+
"What penalties could an organization face for infringing Kenya's Data Protection Act?",
|
441 |
+
]
|
442 |
+
embeddings = model.encode(sentences)
|
443 |
+
print(embeddings.shape)
|
444 |
+
# [3, 768]
|
445 |
+
|
446 |
+
# Get the similarity scores for the embeddings
|
447 |
+
similarities = model.similarity(embeddings, embeddings)
|
448 |
+
print(similarities.shape)
|
449 |
+
# [3, 3]
|
450 |
+
```
|
451 |
+
|
452 |
+
<!--
|
453 |
+
### Direct Usage (Transformers)
|
454 |
+
|
455 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
456 |
+
|
457 |
+
</details>
|
458 |
+
-->
|
459 |
+
|
460 |
+
<!--
|
461 |
+
### Downstream Usage (Sentence Transformers)
|
462 |
+
|
463 |
+
You can finetune this model on your own dataset.
|
464 |
+
|
465 |
+
<details><summary>Click to expand</summary>
|
466 |
+
|
467 |
+
</details>
|
468 |
+
-->
|
469 |
+
|
470 |
+
<!--
|
471 |
+
### Out-of-Scope Use
|
472 |
+
|
473 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
474 |
+
-->
|
475 |
+
|
476 |
+
## Evaluation
|
477 |
+
|
478 |
+
### Metrics
|
479 |
+
|
480 |
+
#### Information Retrieval
|
481 |
+
* Dataset: `dim_768`
|
482 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
483 |
+
|
484 |
+
| Metric | Value |
|
485 |
+
|:--------------------|:-----------|
|
486 |
+
| cosine_accuracy@1 | 0.5 |
|
487 |
+
| cosine_accuracy@3 | 0.8333 |
|
488 |
+
| cosine_accuracy@5 | 0.9444 |
|
489 |
+
| cosine_accuracy@10 | 1.0 |
|
490 |
+
| cosine_precision@1 | 0.5 |
|
491 |
+
| cosine_precision@3 | 0.2778 |
|
492 |
+
| cosine_precision@5 | 0.1889 |
|
493 |
+
| cosine_precision@10 | 0.1 |
|
494 |
+
| cosine_recall@1 | 0.5 |
|
495 |
+
| cosine_recall@3 | 0.8333 |
|
496 |
+
| cosine_recall@5 | 0.9444 |
|
497 |
+
| cosine_recall@10 | 1.0 |
|
498 |
+
| cosine_ndcg@10 | 0.7361 |
|
499 |
+
| cosine_mrr@10 | 0.6515 |
|
500 |
+
| **cosine_map@100** | **0.6515** |
|
501 |
+
|
502 |
+
#### Information Retrieval
|
503 |
+
* Dataset: `dim_512`
|
504 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
505 |
+
|
506 |
+
| Metric | Value |
|
507 |
+
|:--------------------|:-----------|
|
508 |
+
| cosine_accuracy@1 | 0.5 |
|
509 |
+
| cosine_accuracy@3 | 0.7778 |
|
510 |
+
| cosine_accuracy@5 | 0.9444 |
|
511 |
+
| cosine_accuracy@10 | 1.0 |
|
512 |
+
| cosine_precision@1 | 0.5 |
|
513 |
+
| cosine_precision@3 | 0.2593 |
|
514 |
+
| cosine_precision@5 | 0.1889 |
|
515 |
+
| cosine_precision@10 | 0.1 |
|
516 |
+
| cosine_recall@1 | 0.5 |
|
517 |
+
| cosine_recall@3 | 0.7778 |
|
518 |
+
| cosine_recall@5 | 0.9444 |
|
519 |
+
| cosine_recall@10 | 1.0 |
|
520 |
+
| cosine_ndcg@10 | 0.7443 |
|
521 |
+
| cosine_mrr@10 | 0.6627 |
|
522 |
+
| **cosine_map@100** | **0.6627** |
|
523 |
+
|
524 |
+
#### Information Retrieval
|
525 |
+
* Dataset: `dim_256`
|
526 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
527 |
+
|
528 |
+
| Metric | Value |
|
529 |
+
|:--------------------|:----------|
|
530 |
+
| cosine_accuracy@1 | 0.5 |
|
531 |
+
| cosine_accuracy@3 | 0.8889 |
|
532 |
+
| cosine_accuracy@5 | 0.8889 |
|
533 |
+
| cosine_accuracy@10 | 1.0 |
|
534 |
+
| cosine_precision@1 | 0.5 |
|
535 |
+
| cosine_precision@3 | 0.2963 |
|
536 |
+
| cosine_precision@5 | 0.1778 |
|
537 |
+
| cosine_precision@10 | 0.1 |
|
538 |
+
| cosine_recall@1 | 0.5 |
|
539 |
+
| cosine_recall@3 | 0.8889 |
|
540 |
+
| cosine_recall@5 | 0.8889 |
|
541 |
+
| cosine_recall@10 | 1.0 |
|
542 |
+
| cosine_ndcg@10 | 0.757 |
|
543 |
+
| cosine_mrr@10 | 0.679 |
|
544 |
+
| **cosine_map@100** | **0.679** |
|
545 |
+
|
546 |
+
#### Information Retrieval
|
547 |
+
* Dataset: `dim_128`
|
548 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
549 |
+
|
550 |
+
| Metric | Value |
|
551 |
+
|:--------------------|:-----------|
|
552 |
+
| cosine_accuracy@1 | 0.5 |
|
553 |
+
| cosine_accuracy@3 | 0.8333 |
|
554 |
+
| cosine_accuracy@5 | 0.8889 |
|
555 |
+
| cosine_accuracy@10 | 0.9444 |
|
556 |
+
| cosine_precision@1 | 0.5 |
|
557 |
+
| cosine_precision@3 | 0.2778 |
|
558 |
+
| cosine_precision@5 | 0.1778 |
|
559 |
+
| cosine_precision@10 | 0.0944 |
|
560 |
+
| cosine_recall@1 | 0.5 |
|
561 |
+
| cosine_recall@3 | 0.8333 |
|
562 |
+
| cosine_recall@5 | 0.8889 |
|
563 |
+
| cosine_recall@10 | 0.9444 |
|
564 |
+
| cosine_ndcg@10 | 0.7291 |
|
565 |
+
| cosine_mrr@10 | 0.659 |
|
566 |
+
| **cosine_map@100** | **0.6605** |
|
567 |
+
|
568 |
+
#### Information Retrieval
|
569 |
+
* Dataset: `dim_64`
|
570 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
571 |
+
|
572 |
+
| Metric | Value |
|
573 |
+
|:--------------------|:-----------|
|
574 |
+
| cosine_accuracy@1 | 0.4444 |
|
575 |
+
| cosine_accuracy@3 | 0.6111 |
|
576 |
+
| cosine_accuracy@5 | 0.6667 |
|
577 |
+
| cosine_accuracy@10 | 1.0 |
|
578 |
+
| cosine_precision@1 | 0.4444 |
|
579 |
+
| cosine_precision@3 | 0.2037 |
|
580 |
+
| cosine_precision@5 | 0.1333 |
|
581 |
+
| cosine_precision@10 | 0.1 |
|
582 |
+
| cosine_recall@1 | 0.4444 |
|
583 |
+
| cosine_recall@3 | 0.6111 |
|
584 |
+
| cosine_recall@5 | 0.6667 |
|
585 |
+
| cosine_recall@10 | 1.0 |
|
586 |
+
| cosine_ndcg@10 | 0.6741 |
|
587 |
+
| cosine_mrr@10 | 0.5768 |
|
588 |
+
| **cosine_map@100** | **0.5768** |
|
589 |
+
|
590 |
+
<!--
|
591 |
+
## Bias, Risks and Limitations
|
592 |
+
|
593 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
594 |
+
-->
|
595 |
+
|
596 |
+
<!--
|
597 |
+
### Recommendations
|
598 |
+
|
599 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
600 |
+
-->
|
601 |
+
|
602 |
+
## Training Details
|
603 |
+
|
604 |
+
### Training Dataset
|
605 |
+
|
606 |
+
#### Unnamed Dataset
|
607 |
+
|
608 |
+
|
609 |
+
* Size: 161 training samples
|
610 |
+
* Columns: <code>positive</code> and <code>anchor</code>
|
611 |
+
* Approximate statistics based on the first 1000 samples:
|
612 |
+
| | positive | anchor |
|
613 |
+
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
|
614 |
+
| type | string | string |
|
615 |
+
| details | <ul><li>min: 5 tokens</li><li>mean: 40.09 tokens</li><li>max: 481 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 13.01 tokens</li><li>max: 24 tokens</li></ul> |
|
616 |
+
* Samples:
|
617 |
+
| positive | anchor |
|
618 |
+
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------|
|
619 |
+
| <code>The DPA may impose administrative fines of up to €10 million, or up to 2%<br>of<br>worldwide turnover. The DPA may also impose heavier fines up to €20 million,<br>or up to 4% of worldwide turnover.</code> | <code>What is the penalty for non-compliance with the GDPR in Italy?</code> |
|
620 |
+
| <code>As per the DPA, the data handler must seek consent in writing from the data subject to collect any sensitive personal data.</code> | <code>What are the consent requirements under the DPA?</code> |
|
621 |
+
| <code>China's cybersecurity laws include the Cybersecurity Law, which governs<br>various aspects of cybersecurity, data protection, and the obligations of<br>organizations to ensure the security of networks and data within China's<br>territory.</code> | <code>What are the cybersecurity laws in China?</code> |
|
622 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
623 |
+
```json
|
624 |
+
{
|
625 |
+
"loss": "MultipleNegativesRankingLoss",
|
626 |
+
"matryoshka_dims": [
|
627 |
+
768,
|
628 |
+
512,
|
629 |
+
256,
|
630 |
+
128,
|
631 |
+
64
|
632 |
+
],
|
633 |
+
"matryoshka_weights": [
|
634 |
+
1,
|
635 |
+
1,
|
636 |
+
1,
|
637 |
+
1,
|
638 |
+
1
|
639 |
+
],
|
640 |
+
"n_dims_per_step": -1
|
641 |
+
}
|
642 |
+
```
|
643 |
+
|
644 |
+
### Training Hyperparameters
|
645 |
+
#### Non-Default Hyperparameters
|
646 |
+
|
647 |
+
- `eval_strategy`: epoch
|
648 |
+
- `per_device_train_batch_size`: 32
|
649 |
+
- `per_device_eval_batch_size`: 16
|
650 |
+
- `gradient_accumulation_steps`: 2
|
651 |
+
- `learning_rate`: 2e-05
|
652 |
+
- `num_train_epochs`: 2
|
653 |
+
- `lr_scheduler_type`: cosine
|
654 |
+
- `warmup_ratio`: 0.1
|
655 |
+
- `bf16`: True
|
656 |
+
- `tf32`: True
|
657 |
+
- `load_best_model_at_end`: True
|
658 |
+
- `optim`: adamw_torch_fused
|
659 |
+
- `batch_sampler`: no_duplicates
|
660 |
+
|
661 |
+
#### All Hyperparameters
|
662 |
+
<details><summary>Click to expand</summary>
|
663 |
+
|
664 |
+
- `overwrite_output_dir`: False
|
665 |
+
- `do_predict`: False
|
666 |
+
- `eval_strategy`: epoch
|
667 |
+
- `prediction_loss_only`: True
|
668 |
+
- `per_device_train_batch_size`: 32
|
669 |
+
- `per_device_eval_batch_size`: 16
|
670 |
+
- `per_gpu_train_batch_size`: None
|
671 |
+
- `per_gpu_eval_batch_size`: None
|
672 |
+
- `gradient_accumulation_steps`: 2
|
673 |
+
- `eval_accumulation_steps`: None
|
674 |
+
- `learning_rate`: 2e-05
|
675 |
+
- `weight_decay`: 0.0
|
676 |
+
- `adam_beta1`: 0.9
|
677 |
+
- `adam_beta2`: 0.999
|
678 |
+
- `adam_epsilon`: 1e-08
|
679 |
+
- `max_grad_norm`: 1.0
|
680 |
+
- `num_train_epochs`: 2
|
681 |
+
- `max_steps`: -1
|
682 |
+
- `lr_scheduler_type`: cosine
|
683 |
+
- `lr_scheduler_kwargs`: {}
|
684 |
+
- `warmup_ratio`: 0.1
|
685 |
+
- `warmup_steps`: 0
|
686 |
+
- `log_level`: passive
|
687 |
+
- `log_level_replica`: warning
|
688 |
+
- `log_on_each_node`: True
|
689 |
+
- `logging_nan_inf_filter`: True
|
690 |
+
- `save_safetensors`: True
|
691 |
+
- `save_on_each_node`: False
|
692 |
+
- `save_only_model`: False
|
693 |
+
- `restore_callback_states_from_checkpoint`: False
|
694 |
+
- `no_cuda`: False
|
695 |
+
- `use_cpu`: False
|
696 |
+
- `use_mps_device`: False
|
697 |
+
- `seed`: 42
|
698 |
+
- `data_seed`: None
|
699 |
+
- `jit_mode_eval`: False
|
700 |
+
- `use_ipex`: False
|
701 |
+
- `bf16`: True
|
702 |
+
- `fp16`: False
|
703 |
+
- `fp16_opt_level`: O1
|
704 |
+
- `half_precision_backend`: auto
|
705 |
+
- `bf16_full_eval`: False
|
706 |
+
- `fp16_full_eval`: False
|
707 |
+
- `tf32`: True
|
708 |
+
- `local_rank`: 0
|
709 |
+
- `ddp_backend`: None
|
710 |
+
- `tpu_num_cores`: None
|
711 |
+
- `tpu_metrics_debug`: False
|
712 |
+
- `debug`: []
|
713 |
+
- `dataloader_drop_last`: False
|
714 |
+
- `dataloader_num_workers`: 0
|
715 |
+
- `dataloader_prefetch_factor`: None
|
716 |
+
- `past_index`: -1
|
717 |
+
- `disable_tqdm`: False
|
718 |
+
- `remove_unused_columns`: True
|
719 |
+
- `label_names`: None
|
720 |
+
- `load_best_model_at_end`: True
|
721 |
+
- `ignore_data_skip`: False
|
722 |
+
- `fsdp`: []
|
723 |
+
- `fsdp_min_num_params`: 0
|
724 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
725 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
726 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
727 |
+
- `deepspeed`: None
|
728 |
+
- `label_smoothing_factor`: 0.0
|
729 |
+
- `optim`: adamw_torch_fused
|
730 |
+
- `optim_args`: None
|
731 |
+
- `adafactor`: False
|
732 |
+
- `group_by_length`: False
|
733 |
+
- `length_column_name`: length
|
734 |
+
- `ddp_find_unused_parameters`: None
|
735 |
+
- `ddp_bucket_cap_mb`: None
|
736 |
+
- `ddp_broadcast_buffers`: False
|
737 |
+
- `dataloader_pin_memory`: True
|
738 |
+
- `dataloader_persistent_workers`: False
|
739 |
+
- `skip_memory_metrics`: True
|
740 |
+
- `use_legacy_prediction_loop`: False
|
741 |
+
- `push_to_hub`: False
|
742 |
+
- `resume_from_checkpoint`: None
|
743 |
+
- `hub_model_id`: None
|
744 |
+
- `hub_strategy`: every_save
|
745 |
+
- `hub_private_repo`: False
|
746 |
+
- `hub_always_push`: False
|
747 |
+
- `gradient_checkpointing`: False
|
748 |
+
- `gradient_checkpointing_kwargs`: None
|
749 |
+
- `include_inputs_for_metrics`: False
|
750 |
+
- `eval_do_concat_batches`: True
|
751 |
+
- `fp16_backend`: auto
|
752 |
+
- `push_to_hub_model_id`: None
|
753 |
+
- `push_to_hub_organization`: None
|
754 |
+
- `mp_parameters`:
|
755 |
+
- `auto_find_batch_size`: False
|
756 |
+
- `full_determinism`: False
|
757 |
+
- `torchdynamo`: None
|
758 |
+
- `ray_scope`: last
|
759 |
+
- `ddp_timeout`: 1800
|
760 |
+
- `torch_compile`: False
|
761 |
+
- `torch_compile_backend`: None
|
762 |
+
- `torch_compile_mode`: None
|
763 |
+
- `dispatch_batches`: None
|
764 |
+
- `split_batches`: None
|
765 |
+
- `include_tokens_per_second`: False
|
766 |
+
- `include_num_input_tokens_seen`: False
|
767 |
+
- `neftune_noise_alpha`: None
|
768 |
+
- `optim_target_modules`: None
|
769 |
+
- `batch_eval_metrics`: False
|
770 |
+
- `batch_sampler`: no_duplicates
|
771 |
+
- `multi_dataset_batch_sampler`: proportional
|
772 |
+
|
773 |
+
</details>
|
774 |
+
|
775 |
+
### Training Logs
|
776 |
+
| Epoch | Step | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
|
777 |
+
|:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
|
778 |
+
| 1.0 | 3 | 0.6510 | 0.6691 | 0.6534 | 0.5641 | 0.6515 |
|
779 |
+
| **2.0** | **6** | **0.6605** | **0.679** | **0.6627** | **0.5768** | **0.6515** |
|
780 |
+
|
781 |
+
* The bold row denotes the saved checkpoint.
|
782 |
+
|
783 |
+
### Framework Versions
|
784 |
+
- Python: 3.10.14
|
785 |
+
- Sentence Transformers: 3.0.1
|
786 |
+
- Transformers: 4.41.2
|
787 |
+
- PyTorch: 2.1.2+cu121
|
788 |
+
- Accelerate: 0.31.0
|
789 |
+
- Datasets: 2.19.1
|
790 |
+
- Tokenizers: 0.19.1
|
791 |
+
|
792 |
+
## Citation
|
793 |
+
|
794 |
+
### BibTeX
|
795 |
+
|
796 |
+
#### Sentence Transformers
|
797 |
+
```bibtex
|
798 |
+
@inproceedings{reimers-2019-sentence-bert,
|
799 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
800 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
801 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
802 |
+
month = "11",
|
803 |
+
year = "2019",
|
804 |
+
publisher = "Association for Computational Linguistics",
|
805 |
+
url = "https://arxiv.org/abs/1908.10084",
|
806 |
+
}
|
807 |
+
```
|
808 |
+
|
809 |
+
#### MatryoshkaLoss
|
810 |
+
```bibtex
|
811 |
+
@misc{kusupati2024matryoshka,
|
812 |
+
title={Matryoshka Representation Learning},
|
813 |
+
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},
|
814 |
+
year={2024},
|
815 |
+
eprint={2205.13147},
|
816 |
+
archivePrefix={arXiv},
|
817 |
+
primaryClass={cs.LG}
|
818 |
+
}
|
819 |
+
```
|
820 |
+
|
821 |
+
#### MultipleNegativesRankingLoss
|
822 |
+
```bibtex
|
823 |
+
@misc{henderson2017efficient,
|
824 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
825 |
+
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},
|
826 |
+
year={2017},
|
827 |
+
eprint={1705.00652},
|
828 |
+
archivePrefix={arXiv},
|
829 |
+
primaryClass={cs.CL}
|
830 |
+
}
|
831 |
+
```
|
832 |
+
|
833 |
+
<!--
|
834 |
+
## Glossary
|
835 |
+
|
836 |
+
*Clearly define terms in order to be accessible across audiences.*
|
837 |
+
-->
|
838 |
+
|
839 |
+
<!--
|
840 |
+
## Model Card Authors
|
841 |
+
|
842 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
843 |
+
-->
|
844 |
+
|
845 |
+
<!--
|
846 |
+
## Model Card Contact
|
847 |
+
|
848 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
849 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BAAI/bge-base-en-v1.5",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.41.2",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 30522
|
32 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.41.2",
|
5 |
+
"pytorch": "2.1.2+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd14f5b69b24c8ae1a9b2ed740e6fef32e5800b6f38783c0e657a82b43bf077a
|
3 |
+
size 437951328
|
modules.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
+
}
|
20 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": true
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|