Add new SentenceTransformer model.
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- README.md +839 -0
- config.json +28 -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 +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 1024,
|
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 +1,839 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: BAAI/bge-m3
|
3 |
+
datasets: []
|
4 |
+
language: []
|
5 |
+
library_name: sentence-transformers
|
6 |
+
metrics:
|
7 |
+
- cosine_accuracy@1
|
8 |
+
- cosine_accuracy@3
|
9 |
+
- cosine_accuracy@5
|
10 |
+
- cosine_accuracy@10
|
11 |
+
- cosine_precision@1
|
12 |
+
- cosine_precision@3
|
13 |
+
- cosine_precision@5
|
14 |
+
- cosine_precision@10
|
15 |
+
- cosine_recall@1
|
16 |
+
- cosine_recall@3
|
17 |
+
- cosine_recall@5
|
18 |
+
- cosine_recall@10
|
19 |
+
- cosine_ndcg@10
|
20 |
+
- cosine_mrr@10
|
21 |
+
- cosine_map@100
|
22 |
+
pipeline_tag: sentence-similarity
|
23 |
+
tags:
|
24 |
+
- sentence-transformers
|
25 |
+
- sentence-similarity
|
26 |
+
- feature-extraction
|
27 |
+
- generated_from_trainer
|
28 |
+
- dataset_size:4957
|
29 |
+
- loss:MatryoshkaLoss
|
30 |
+
- loss:MultipleNegativesRankingLoss
|
31 |
+
widget:
|
32 |
+
- source_sentence: 312 Aus steuerlicher Sicht ist es möglich, mehrere Versorgungszusagen
|
33 |
+
nebeneinander, also neben einer Altzusage auch eine Neuzusage zu erteilen (z.
|
34 |
+
B. „alte“ Direktversicherung und „neuer“ Pensionsfonds).
|
35 |
+
sentences:
|
36 |
+
- Wann liegt bei der betrieblichen Altersversorgung eine schädliche Verwendung vor?
|
37 |
+
- Welche steuerliche Behandlung erfahren Auszahlungen aus Altersvorsorgeverträgen
|
38 |
+
nach § 22 Nr. 5 EStG?
|
39 |
+
- Können verschiedene Versorgungszusagen wie Direktversicherung und Pensionsfonds
|
40 |
+
gleichzeitig bestehen?
|
41 |
+
- source_sentence: 5 Pflichtversicherte nach dem Gesetz über die Alterssicherung der
|
42 |
+
Landwirte gehören, soweit sie nicht als Pflichtversicherte der gesetzlichen Rentenversicherung
|
43 |
+
ohnehin bereits anspruchsberechtigt sind, in dieser Eigenschaft ebenfalls zum
|
44 |
+
begünstigten Personenkreis. Darunter fallen insbesondere die in Anlage 1 Abschnitt
|
45 |
+
B aufgeführten Personen.
|
46 |
+
sentences:
|
47 |
+
- Wann wird das Anrecht der ausgleichsberechtigten Person bei intern geteilter Altersvorsorge
|
48 |
+
als abgeschlossen betrachtet?
|
49 |
+
- Welche Personen sind in der Anlage 1 Abschnitt B bezüglich der Alterssicherung
|
50 |
+
der Landwirte aufgeführt?
|
51 |
+
- In welchen Fällen führt die Möglichkeit einer Beitragserstattung nicht zur Versagung
|
52 |
+
der Anerkennung als betriebliche Altersversorgung?
|
53 |
+
- source_sentence: 233 Voraussetzung für die Förderung durch Sonderausgabenabzug nach
|
54 |
+
§ 10a EStG und Zulage nach Abschnitt XI EStG ist in den Fällen der Rz. 231 f.,
|
55 |
+
dass der Steuerpflichtige zum begünstigten Personenkreis gehört. Die zeitliche
|
56 |
+
Zuordnung dieser Altersvorsorgebeiträge richtet sich grundsätzlich nach § 11 Abs.
|
57 |
+
2 EStG.
|
58 |
+
sentences:
|
59 |
+
- Wer gehört zum begünstigten Personenkreis für die Altersvorsorgeförderung?
|
60 |
+
- Wie werden erstattete Kosten eines Altersvorsorgevertrags besteuert, wenn sie
|
61 |
+
dem Steuerpflichtigen ausgezahlt werden?
|
62 |
+
- Ist der Übertragungswert einer betrieblichen Altersversorgung bei einem Arbeitgeberwechsel
|
63 |
+
steuerfrei?
|
64 |
+
- source_sentence: 127 Die Entnahme des Teilkapitalbetrags von bis zu 30 % des zur
|
65 |
+
Verfügung stehenden Kapitals aus dem Vertrag hat zu Beginn der Auszahlungsphase
|
66 |
+
zu erfolgen. Eine Verteilung über mehrere Auszahlungszeitpunkte ist nicht möglich.
|
67 |
+
sentences:
|
68 |
+
- Kann ich den Teilkapitalbetrag aus meiner Altersvorsorge zu verschiedenen Zeitpunkten
|
69 |
+
entnehmen?
|
70 |
+
- Welche Einkunftsarten können Leistungen aus einer Versorgungszusage des Arbeitgebers
|
71 |
+
sein?
|
72 |
+
- Was ist im Todesfall des Zulageberechtigten bezüglich der Förderbeiträge zu tun?
|
73 |
+
- source_sentence: '67 Abwandlung des Beispiels 1 in Rn. 66: A erhält zudem zwei Kinderzulagen
|
74 |
+
für seine in den Jahren 2004 und 2005 geborenen Kinder. Beitragspflichtige Einnahmen
|
75 |
+
53.000 € 4 % 2.120 € höchstens 2.100 € anzusetzen 2.100 € abzüglich Zulage 175
|
76 |
+
€ Mindesteigenbeitrag (§ 86 Abs. 1 Satz 2 EStG) 1.925 € Sockelbetrag (§ 86 Abs.
|
77 |
+
1 Satz 4 EStG) 60 € maßgebend (§ 86 Abs. 1 Satz 5 EStG) 1.925 € Die von A geleisteten
|
78 |
+
Beiträge übersteigen den Mindesteigenbeitrag. Die Zulage wird nicht gekürzt.'
|
79 |
+
sentences:
|
80 |
+
- Wird die Zulage für A gekürzt, wenn die Beiträge den Mindesteigenbeitrag übersteigen?
|
81 |
+
- Was versteht man unter Sonderzahlungen des Arbeitgebers?
|
82 |
+
- Wie erfolgt die Besteuerung bei der ausgleichsberechtigten Person nach einer externen
|
83 |
+
Teilung?
|
84 |
+
model-index:
|
85 |
+
- name: SentenceTransformer based on BAAI/bge-m3
|
86 |
+
results:
|
87 |
+
- task:
|
88 |
+
type: information-retrieval
|
89 |
+
name: Information Retrieval
|
90 |
+
dataset:
|
91 |
+
name: dim 768
|
92 |
+
type: dim_768
|
93 |
+
metrics:
|
94 |
+
- type: cosine_accuracy@1
|
95 |
+
value: 0.019963702359346643
|
96 |
+
name: Cosine Accuracy@1
|
97 |
+
- type: cosine_accuracy@3
|
98 |
+
value: 0.24863883847549909
|
99 |
+
name: Cosine Accuracy@3
|
100 |
+
- type: cosine_accuracy@5
|
101 |
+
value: 0.3992740471869328
|
102 |
+
name: Cosine Accuracy@5
|
103 |
+
- type: cosine_accuracy@10
|
104 |
+
value: 0.6588021778584392
|
105 |
+
name: Cosine Accuracy@10
|
106 |
+
- type: cosine_precision@1
|
107 |
+
value: 0.019963702359346643
|
108 |
+
name: Cosine Precision@1
|
109 |
+
- type: cosine_precision@3
|
110 |
+
value: 0.08287961282516636
|
111 |
+
name: Cosine Precision@3
|
112 |
+
- type: cosine_precision@5
|
113 |
+
value: 0.07985480943738657
|
114 |
+
name: Cosine Precision@5
|
115 |
+
- type: cosine_precision@10
|
116 |
+
value: 0.06588021778584391
|
117 |
+
name: Cosine Precision@10
|
118 |
+
- type: cosine_recall@1
|
119 |
+
value: 0.019963702359346643
|
120 |
+
name: Cosine Recall@1
|
121 |
+
- type: cosine_recall@3
|
122 |
+
value: 0.24863883847549909
|
123 |
+
name: Cosine Recall@3
|
124 |
+
- type: cosine_recall@5
|
125 |
+
value: 0.3992740471869328
|
126 |
+
name: Cosine Recall@5
|
127 |
+
- type: cosine_recall@10
|
128 |
+
value: 0.6588021778584392
|
129 |
+
name: Cosine Recall@10
|
130 |
+
- type: cosine_ndcg@10
|
131 |
+
value: 0.3072766574898433
|
132 |
+
name: Cosine Ndcg@10
|
133 |
+
- type: cosine_mrr@10
|
134 |
+
value: 0.19910408204419097
|
135 |
+
name: Cosine Mrr@10
|
136 |
+
- type: cosine_map@100
|
137 |
+
value: 0.21588812107724084
|
138 |
+
name: Cosine Map@100
|
139 |
+
- task:
|
140 |
+
type: information-retrieval
|
141 |
+
name: Information Retrieval
|
142 |
+
dataset:
|
143 |
+
name: dim 512
|
144 |
+
type: dim_512
|
145 |
+
metrics:
|
146 |
+
- type: cosine_accuracy@1
|
147 |
+
value: 0.029038112522686024
|
148 |
+
name: Cosine Accuracy@1
|
149 |
+
- type: cosine_accuracy@3
|
150 |
+
value: 0.25226860254083483
|
151 |
+
name: Cosine Accuracy@3
|
152 |
+
- type: cosine_accuracy@5
|
153 |
+
value: 0.4029038112522686
|
154 |
+
name: Cosine Accuracy@5
|
155 |
+
- type: cosine_accuracy@10
|
156 |
+
value: 0.647912885662432
|
157 |
+
name: Cosine Accuracy@10
|
158 |
+
- type: cosine_precision@1
|
159 |
+
value: 0.029038112522686024
|
160 |
+
name: Cosine Precision@1
|
161 |
+
- type: cosine_precision@3
|
162 |
+
value: 0.08408953418027827
|
163 |
+
name: Cosine Precision@3
|
164 |
+
- type: cosine_precision@5
|
165 |
+
value: 0.08058076225045373
|
166 |
+
name: Cosine Precision@5
|
167 |
+
- type: cosine_precision@10
|
168 |
+
value: 0.0647912885662432
|
169 |
+
name: Cosine Precision@10
|
170 |
+
- type: cosine_recall@1
|
171 |
+
value: 0.029038112522686024
|
172 |
+
name: Cosine Recall@1
|
173 |
+
- type: cosine_recall@3
|
174 |
+
value: 0.25226860254083483
|
175 |
+
name: Cosine Recall@3
|
176 |
+
- type: cosine_recall@5
|
177 |
+
value: 0.4029038112522686
|
178 |
+
name: Cosine Recall@5
|
179 |
+
- type: cosine_recall@10
|
180 |
+
value: 0.647912885662432
|
181 |
+
name: Cosine Recall@10
|
182 |
+
- type: cosine_ndcg@10
|
183 |
+
value: 0.30835796317387987
|
184 |
+
name: Cosine Ndcg@10
|
185 |
+
- type: cosine_mrr@10
|
186 |
+
value: 0.20380765131218861
|
187 |
+
name: Cosine Mrr@10
|
188 |
+
- type: cosine_map@100
|
189 |
+
value: 0.22078173489998865
|
190 |
+
name: Cosine Map@100
|
191 |
+
- task:
|
192 |
+
type: information-retrieval
|
193 |
+
name: Information Retrieval
|
194 |
+
dataset:
|
195 |
+
name: dim 256
|
196 |
+
type: dim_256
|
197 |
+
metrics:
|
198 |
+
- type: cosine_accuracy@1
|
199 |
+
value: 0.034482758620689655
|
200 |
+
name: Cosine Accuracy@1
|
201 |
+
- type: cosine_accuracy@3
|
202 |
+
value: 0.23049001814882034
|
203 |
+
name: Cosine Accuracy@3
|
204 |
+
- type: cosine_accuracy@5
|
205 |
+
value: 0.38656987295825773
|
206 |
+
name: Cosine Accuracy@5
|
207 |
+
- type: cosine_accuracy@10
|
208 |
+
value: 0.647912885662432
|
209 |
+
name: Cosine Accuracy@10
|
210 |
+
- type: cosine_precision@1
|
211 |
+
value: 0.034482758620689655
|
212 |
+
name: Cosine Precision@1
|
213 |
+
- type: cosine_precision@3
|
214 |
+
value: 0.07683000604960677
|
215 |
+
name: Cosine Precision@3
|
216 |
+
- type: cosine_precision@5
|
217 |
+
value: 0.07731397459165154
|
218 |
+
name: Cosine Precision@5
|
219 |
+
- type: cosine_precision@10
|
220 |
+
value: 0.0647912885662432
|
221 |
+
name: Cosine Precision@10
|
222 |
+
- type: cosine_recall@1
|
223 |
+
value: 0.034482758620689655
|
224 |
+
name: Cosine Recall@1
|
225 |
+
- type: cosine_recall@3
|
226 |
+
value: 0.23049001814882034
|
227 |
+
name: Cosine Recall@3
|
228 |
+
- type: cosine_recall@5
|
229 |
+
value: 0.38656987295825773
|
230 |
+
name: Cosine Recall@5
|
231 |
+
- type: cosine_recall@10
|
232 |
+
value: 0.647912885662432
|
233 |
+
name: Cosine Recall@10
|
234 |
+
- type: cosine_ndcg@10
|
235 |
+
value: 0.3040645102017685
|
236 |
+
name: Cosine Ndcg@10
|
237 |
+
- type: cosine_mrr@10
|
238 |
+
value: 0.1990666320974852
|
239 |
+
name: Cosine Mrr@10
|
240 |
+
- type: cosine_map@100
|
241 |
+
value: 0.21577058637681837
|
242 |
+
name: Cosine Map@100
|
243 |
+
- task:
|
244 |
+
type: information-retrieval
|
245 |
+
name: Information Retrieval
|
246 |
+
dataset:
|
247 |
+
name: dim 128
|
248 |
+
type: dim_128
|
249 |
+
metrics:
|
250 |
+
- type: cosine_accuracy@1
|
251 |
+
value: 0.02722323049001815
|
252 |
+
name: Cosine Accuracy@1
|
253 |
+
- type: cosine_accuracy@3
|
254 |
+
value: 0.24319419237749546
|
255 |
+
name: Cosine Accuracy@3
|
256 |
+
- type: cosine_accuracy@5
|
257 |
+
value: 0.38656987295825773
|
258 |
+
name: Cosine Accuracy@5
|
259 |
+
- type: cosine_accuracy@10
|
260 |
+
value: 0.6442831215970962
|
261 |
+
name: Cosine Accuracy@10
|
262 |
+
- type: cosine_precision@1
|
263 |
+
value: 0.02722323049001815
|
264 |
+
name: Cosine Precision@1
|
265 |
+
- type: cosine_precision@3
|
266 |
+
value: 0.08106473079249849
|
267 |
+
name: Cosine Precision@3
|
268 |
+
- type: cosine_precision@5
|
269 |
+
value: 0.07731397459165155
|
270 |
+
name: Cosine Precision@5
|
271 |
+
- type: cosine_precision@10
|
272 |
+
value: 0.06442831215970962
|
273 |
+
name: Cosine Precision@10
|
274 |
+
- type: cosine_recall@1
|
275 |
+
value: 0.02722323049001815
|
276 |
+
name: Cosine Recall@1
|
277 |
+
- type: cosine_recall@3
|
278 |
+
value: 0.24319419237749546
|
279 |
+
name: Cosine Recall@3
|
280 |
+
- type: cosine_recall@5
|
281 |
+
value: 0.38656987295825773
|
282 |
+
name: Cosine Recall@5
|
283 |
+
- type: cosine_recall@10
|
284 |
+
value: 0.6442831215970962
|
285 |
+
name: Cosine Recall@10
|
286 |
+
- type: cosine_ndcg@10
|
287 |
+
value: 0.3030488823891233
|
288 |
+
name: Cosine Ndcg@10
|
289 |
+
- type: cosine_mrr@10
|
290 |
+
value: 0.19836804655316465
|
291 |
+
name: Cosine Mrr@10
|
292 |
+
- type: cosine_map@100
|
293 |
+
value: 0.21511274800304536
|
294 |
+
name: Cosine Map@100
|
295 |
+
- task:
|
296 |
+
type: information-retrieval
|
297 |
+
name: Information Retrieval
|
298 |
+
dataset:
|
299 |
+
name: dim 64
|
300 |
+
type: dim_64
|
301 |
+
metrics:
|
302 |
+
- type: cosine_accuracy@1
|
303 |
+
value: 0.016333938294010888
|
304 |
+
name: Cosine Accuracy@1
|
305 |
+
- type: cosine_accuracy@3
|
306 |
+
value: 0.2250453720508167
|
307 |
+
name: Cosine Accuracy@3
|
308 |
+
- type: cosine_accuracy@5
|
309 |
+
value: 0.37749546279491836
|
310 |
+
name: Cosine Accuracy@5
|
311 |
+
- type: cosine_accuracy@10
|
312 |
+
value: 0.617059891107078
|
313 |
+
name: Cosine Accuracy@10
|
314 |
+
- type: cosine_precision@1
|
315 |
+
value: 0.016333938294010888
|
316 |
+
name: Cosine Precision@1
|
317 |
+
- type: cosine_precision@3
|
318 |
+
value: 0.0750151240169389
|
319 |
+
name: Cosine Precision@3
|
320 |
+
- type: cosine_precision@5
|
321 |
+
value: 0.07549909255898368
|
322 |
+
name: Cosine Precision@5
|
323 |
+
- type: cosine_precision@10
|
324 |
+
value: 0.06170598911070781
|
325 |
+
name: Cosine Precision@10
|
326 |
+
- type: cosine_recall@1
|
327 |
+
value: 0.016333938294010888
|
328 |
+
name: Cosine Recall@1
|
329 |
+
- type: cosine_recall@3
|
330 |
+
value: 0.2250453720508167
|
331 |
+
name: Cosine Recall@3
|
332 |
+
- type: cosine_recall@5
|
333 |
+
value: 0.37749546279491836
|
334 |
+
name: Cosine Recall@5
|
335 |
+
- type: cosine_recall@10
|
336 |
+
value: 0.617059891107078
|
337 |
+
name: Cosine Recall@10
|
338 |
+
- type: cosine_ndcg@10
|
339 |
+
value: 0.28661971571769745
|
340 |
+
name: Cosine Ndcg@10
|
341 |
+
- type: cosine_mrr@10
|
342 |
+
value: 0.18480756488923475
|
343 |
+
name: Cosine Mrr@10
|
344 |
+
- type: cosine_map@100
|
345 |
+
value: 0.20148744214489955
|
346 |
+
name: Cosine Map@100
|
347 |
+
---
|
348 |
+
|
349 |
+
# SentenceTransformer based on BAAI/bge-m3
|
350 |
+
|
351 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
352 |
+
|
353 |
+
## Model Details
|
354 |
+
|
355 |
+
### Model Description
|
356 |
+
- **Model Type:** Sentence Transformer
|
357 |
+
- **Base model:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
|
358 |
+
- **Maximum Sequence Length:** 1024 tokens
|
359 |
+
- **Output Dimensionality:** 1024 tokens
|
360 |
+
- **Similarity Function:** Cosine Similarity
|
361 |
+
<!-- - **Training Dataset:** Unknown -->
|
362 |
+
<!-- - **Language:** Unknown -->
|
363 |
+
<!-- - **License:** Unknown -->
|
364 |
+
|
365 |
+
### Model Sources
|
366 |
+
|
367 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
368 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
369 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
370 |
+
|
371 |
+
### Full Model Architecture
|
372 |
+
|
373 |
+
```
|
374 |
+
SentenceTransformer(
|
375 |
+
(0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
|
376 |
+
(1): Pooling({'word_embedding_dimension': 1024, '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})
|
377 |
+
(2): Normalize()
|
378 |
+
)
|
379 |
+
```
|
380 |
+
|
381 |
+
## Usage
|
382 |
+
|
383 |
+
### Direct Usage (Sentence Transformers)
|
384 |
+
|
385 |
+
First install the Sentence Transformers library:
|
386 |
+
|
387 |
+
```bash
|
388 |
+
pip install -U sentence-transformers
|
389 |
+
```
|
390 |
+
|
391 |
+
Then you can load this model and run inference.
|
392 |
+
```python
|
393 |
+
from sentence_transformers import SentenceTransformer
|
394 |
+
|
395 |
+
# Download from the 🤗 Hub
|
396 |
+
model = SentenceTransformer("akot/bge-semantic-bmf-matryoshka")
|
397 |
+
# Run inference
|
398 |
+
sentences = [
|
399 |
+
'67 Abwandlung des Beispiels 1 in Rn. 66: A erhält zudem zwei Kinderzulagen für seine in den Jahren 2004 und 2005 geborenen Kinder. Beitragspflichtige Einnahmen 53.000 € 4 % 2.120 € höchstens 2.100 € anzusetzen 2.100 € abzüglich Zulage 175 € Mindesteigenbeitrag (§ 86 Abs. 1 Satz 2 EStG) 1.925 € Sockelbetrag (§ 86 Abs. 1 Satz 4 EStG) 60 € maßgebend (§ 86 Abs. 1 Satz 5 EStG) 1.925 € Die von A geleisteten Beiträge übersteigen den Mindesteigenbeitrag. Die Zulage wird nicht gekürzt.',
|
400 |
+
'Wird die Zulage für A gekürzt, wenn die Beiträge den Mindesteigenbeitrag übersteigen?',
|
401 |
+
'Wie erfolgt die Besteuerung bei der ausgleichsberechtigten Person nach einer externen Teilung?',
|
402 |
+
]
|
403 |
+
embeddings = model.encode(sentences)
|
404 |
+
print(embeddings.shape)
|
405 |
+
# [3, 1024]
|
406 |
+
|
407 |
+
# Get the similarity scores for the embeddings
|
408 |
+
similarities = model.similarity(embeddings, embeddings)
|
409 |
+
print(similarities.shape)
|
410 |
+
# [3, 3]
|
411 |
+
```
|
412 |
+
|
413 |
+
<!--
|
414 |
+
### Direct Usage (Transformers)
|
415 |
+
|
416 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
417 |
+
|
418 |
+
</details>
|
419 |
+
-->
|
420 |
+
|
421 |
+
<!--
|
422 |
+
### Downstream Usage (Sentence Transformers)
|
423 |
+
|
424 |
+
You can finetune this model on your own dataset.
|
425 |
+
|
426 |
+
<details><summary>Click to expand</summary>
|
427 |
+
|
428 |
+
</details>
|
429 |
+
-->
|
430 |
+
|
431 |
+
<!--
|
432 |
+
### Out-of-Scope Use
|
433 |
+
|
434 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
435 |
+
-->
|
436 |
+
|
437 |
+
## Evaluation
|
438 |
+
|
439 |
+
### Metrics
|
440 |
+
|
441 |
+
#### Information Retrieval
|
442 |
+
* Dataset: `dim_768`
|
443 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
444 |
+
|
445 |
+
| Metric | Value |
|
446 |
+
|:--------------------|:-----------|
|
447 |
+
| cosine_accuracy@1 | 0.02 |
|
448 |
+
| cosine_accuracy@3 | 0.2486 |
|
449 |
+
| cosine_accuracy@5 | 0.3993 |
|
450 |
+
| cosine_accuracy@10 | 0.6588 |
|
451 |
+
| cosine_precision@1 | 0.02 |
|
452 |
+
| cosine_precision@3 | 0.0829 |
|
453 |
+
| cosine_precision@5 | 0.0799 |
|
454 |
+
| cosine_precision@10 | 0.0659 |
|
455 |
+
| cosine_recall@1 | 0.02 |
|
456 |
+
| cosine_recall@3 | 0.2486 |
|
457 |
+
| cosine_recall@5 | 0.3993 |
|
458 |
+
| cosine_recall@10 | 0.6588 |
|
459 |
+
| cosine_ndcg@10 | 0.3073 |
|
460 |
+
| cosine_mrr@10 | 0.1991 |
|
461 |
+
| **cosine_map@100** | **0.2159** |
|
462 |
+
|
463 |
+
#### Information Retrieval
|
464 |
+
* Dataset: `dim_512`
|
465 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
466 |
+
|
467 |
+
| Metric | Value |
|
468 |
+
|:--------------------|:-----------|
|
469 |
+
| cosine_accuracy@1 | 0.029 |
|
470 |
+
| cosine_accuracy@3 | 0.2523 |
|
471 |
+
| cosine_accuracy@5 | 0.4029 |
|
472 |
+
| cosine_accuracy@10 | 0.6479 |
|
473 |
+
| cosine_precision@1 | 0.029 |
|
474 |
+
| cosine_precision@3 | 0.0841 |
|
475 |
+
| cosine_precision@5 | 0.0806 |
|
476 |
+
| cosine_precision@10 | 0.0648 |
|
477 |
+
| cosine_recall@1 | 0.029 |
|
478 |
+
| cosine_recall@3 | 0.2523 |
|
479 |
+
| cosine_recall@5 | 0.4029 |
|
480 |
+
| cosine_recall@10 | 0.6479 |
|
481 |
+
| cosine_ndcg@10 | 0.3084 |
|
482 |
+
| cosine_mrr@10 | 0.2038 |
|
483 |
+
| **cosine_map@100** | **0.2208** |
|
484 |
+
|
485 |
+
#### Information Retrieval
|
486 |
+
* Dataset: `dim_256`
|
487 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
488 |
+
|
489 |
+
| Metric | Value |
|
490 |
+
|:--------------------|:-----------|
|
491 |
+
| cosine_accuracy@1 | 0.0345 |
|
492 |
+
| cosine_accuracy@3 | 0.2305 |
|
493 |
+
| cosine_accuracy@5 | 0.3866 |
|
494 |
+
| cosine_accuracy@10 | 0.6479 |
|
495 |
+
| cosine_precision@1 | 0.0345 |
|
496 |
+
| cosine_precision@3 | 0.0768 |
|
497 |
+
| cosine_precision@5 | 0.0773 |
|
498 |
+
| cosine_precision@10 | 0.0648 |
|
499 |
+
| cosine_recall@1 | 0.0345 |
|
500 |
+
| cosine_recall@3 | 0.2305 |
|
501 |
+
| cosine_recall@5 | 0.3866 |
|
502 |
+
| cosine_recall@10 | 0.6479 |
|
503 |
+
| cosine_ndcg@10 | 0.3041 |
|
504 |
+
| cosine_mrr@10 | 0.1991 |
|
505 |
+
| **cosine_map@100** | **0.2158** |
|
506 |
+
|
507 |
+
#### Information Retrieval
|
508 |
+
* Dataset: `dim_128`
|
509 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
510 |
+
|
511 |
+
| Metric | Value |
|
512 |
+
|:--------------------|:-----------|
|
513 |
+
| cosine_accuracy@1 | 0.0272 |
|
514 |
+
| cosine_accuracy@3 | 0.2432 |
|
515 |
+
| cosine_accuracy@5 | 0.3866 |
|
516 |
+
| cosine_accuracy@10 | 0.6443 |
|
517 |
+
| cosine_precision@1 | 0.0272 |
|
518 |
+
| cosine_precision@3 | 0.0811 |
|
519 |
+
| cosine_precision@5 | 0.0773 |
|
520 |
+
| cosine_precision@10 | 0.0644 |
|
521 |
+
| cosine_recall@1 | 0.0272 |
|
522 |
+
| cosine_recall@3 | 0.2432 |
|
523 |
+
| cosine_recall@5 | 0.3866 |
|
524 |
+
| cosine_recall@10 | 0.6443 |
|
525 |
+
| cosine_ndcg@10 | 0.303 |
|
526 |
+
| cosine_mrr@10 | 0.1984 |
|
527 |
+
| **cosine_map@100** | **0.2151** |
|
528 |
+
|
529 |
+
#### Information Retrieval
|
530 |
+
* Dataset: `dim_64`
|
531 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
532 |
+
|
533 |
+
| Metric | Value |
|
534 |
+
|:--------------------|:-----------|
|
535 |
+
| cosine_accuracy@1 | 0.0163 |
|
536 |
+
| cosine_accuracy@3 | 0.225 |
|
537 |
+
| cosine_accuracy@5 | 0.3775 |
|
538 |
+
| cosine_accuracy@10 | 0.6171 |
|
539 |
+
| cosine_precision@1 | 0.0163 |
|
540 |
+
| cosine_precision@3 | 0.075 |
|
541 |
+
| cosine_precision@5 | 0.0755 |
|
542 |
+
| cosine_precision@10 | 0.0617 |
|
543 |
+
| cosine_recall@1 | 0.0163 |
|
544 |
+
| cosine_recall@3 | 0.225 |
|
545 |
+
| cosine_recall@5 | 0.3775 |
|
546 |
+
| cosine_recall@10 | 0.6171 |
|
547 |
+
| cosine_ndcg@10 | 0.2866 |
|
548 |
+
| cosine_mrr@10 | 0.1848 |
|
549 |
+
| **cosine_map@100** | **0.2015** |
|
550 |
+
|
551 |
+
<!--
|
552 |
+
## Bias, Risks and Limitations
|
553 |
+
|
554 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
555 |
+
-->
|
556 |
+
|
557 |
+
<!--
|
558 |
+
### Recommendations
|
559 |
+
|
560 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
561 |
+
-->
|
562 |
+
|
563 |
+
## Training Details
|
564 |
+
|
565 |
+
### Training Dataset
|
566 |
+
|
567 |
+
#### Unnamed Dataset
|
568 |
+
|
569 |
+
|
570 |
+
* Size: 4,957 training samples
|
571 |
+
* Columns: <code>positive</code> and <code>anchor</code>
|
572 |
+
* Approximate statistics based on the first 1000 samples:
|
573 |
+
| | positive | anchor |
|
574 |
+
|:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
575 |
+
| type | string | string |
|
576 |
+
| details | <ul><li>min: 6 tokens</li><li>mean: 176.7 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 24.39 tokens</li><li>max: 51 tokens</li></ul> |
|
577 |
+
* Samples:
|
578 |
+
| positive | anchor |
|
579 |
+
|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
580 |
+
| <code>134 Eine Rückzahlungsverpflichtung besteht nicht für den Teil der Zulagen, der auf nach § 1 Abs. 1 Nr. 2 AltZertG angespartes gefördertes Altersvorsorgevermögen entfällt, wenn es in Form einer Hinterbliebenenrente an die dort genannten Hinterbliebenen ausgezahlt wird. Dies gilt auch für den entsprechenden Teil der Steuerermäßigung.</code> | <code>Muss man Zulagen zurückzahlen, wenn das Altersvorsorgevermögen als Hinterbliebenenrente ausgezahlt wird?</code> |
|
581 |
+
| <code>140 Beendet der Zulageberechtigte vor der vollständigen Rückzahlung des AltersvorsorgeEigenheimbetrags die Nutzung zu eigenen Wohnzwecken, wird er so behandelt, als habe er den noch nicht zurückgezahlten Betrag schädlich verwendet. Die auf den noch ausstehenden Rückzahlungsbetrag entfallenden Zulagen sowie die nach § 10a Abs. 4 EStG gesondert festgestellten Steuerermäßigungen sind zurückzuzahlen (§ 92a Abs. 3 EStG). Die im noch ausstehenden Rückzahlungsbetrag enthaltenen Zuwächse (z.B. Zinserträge und Kursgewinne) Seite 41 sind als sonstige Einkünfte zu versteuern (§ 22 Nr. 5 Satz 5 Halbsatz 1 EStG). Außerdem hat der Zulageberechtigte den Vorteil zu versteuern, der sich aus der zinslosen Nutzung des noch nicht zurückgezahlten Betrags ergibt. Zugrunde gelegt wird hierbei eine Verzinsung von 5 % (Zins und Zinseszins) für jedes volle Kalenderjahr der Nutzung (§ 22 Nr. 5 Satz 5 Halbsatz 2 EStG). Diese Folgen treten nicht ein, wenn er den noch nicht zurückgezahlten Betrag in ein Folgeobjekt investiert (§ 92a Abs. 4 Satz 3 Nr. 1 EStG) oder zugunsten eines auf seinen Namen lautenden zertifizierten Altersvorsorgevertrags einzahlt (§ 92a Abs. 4 Satz 3 Nr. 2 EStG).</code> | <code>Was geschieht steuerlich, wenn der AltersvorsorgeEigenheimbetrag nicht vollständig zurückgezahlt wird und die Immobilie nicht mehr selbst genutzt wird?</code> |
|
582 |
+
| <code>144 Die als Einkünfte nach § 22 Nr. 5 Satz 3 EStG i.V.m. § 22 Nr. 5 Satz 2 EStG zu besteuernden Beträge muss der Anbieter gem. § 94 Abs. 1 Satz 4 EStG dem Zulageberechtigten bescheinigen und im Wege des Rentenbezugsmitteilungsverfahrens (§ 22a EStG) mitteilen. Ergeben sich insoweit steuerpflichtige Einkünfte nach § 22 Nr. 5 Satz 3 EStG für einen anderen Leistungsempfänger (z. B. Erben), ist für diesen eine entsprechende Rentenbezugsmitteilung der ZfA zu übermitteln.</code> | <code>Was muss im Falle eines anderen Leistungsempfängers, wie Erben, hinsichtlich der Rentenbezugsmitteilung getan werden?</code> |
|
583 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
584 |
+
```json
|
585 |
+
{
|
586 |
+
"loss": "MultipleNegativesRankingLoss",
|
587 |
+
"matryoshka_dims": [
|
588 |
+
768,
|
589 |
+
512,
|
590 |
+
256,
|
591 |
+
128,
|
592 |
+
64
|
593 |
+
],
|
594 |
+
"matryoshka_weights": [
|
595 |
+
1,
|
596 |
+
1,
|
597 |
+
1,
|
598 |
+
1,
|
599 |
+
1
|
600 |
+
],
|
601 |
+
"n_dims_per_step": -1
|
602 |
+
}
|
603 |
+
```
|
604 |
+
|
605 |
+
### Training Hyperparameters
|
606 |
+
#### Non-Default Hyperparameters
|
607 |
+
|
608 |
+
- `eval_strategy`: epoch
|
609 |
+
- `per_device_train_batch_size`: 16
|
610 |
+
- `per_device_eval_batch_size`: 16
|
611 |
+
- `gradient_accumulation_steps`: 16
|
612 |
+
- `learning_rate`: 2e-05
|
613 |
+
- `num_train_epochs`: 10
|
614 |
+
- `lr_scheduler_type`: cosine
|
615 |
+
- `warmup_ratio`: 0.1
|
616 |
+
- `bf16`: True
|
617 |
+
- `tf32`: True
|
618 |
+
- `load_best_model_at_end`: True
|
619 |
+
- `optim`: adamw_torch_fused
|
620 |
+
- `batch_sampler`: no_duplicates
|
621 |
+
|
622 |
+
#### All Hyperparameters
|
623 |
+
<details><summary>Click to expand</summary>
|
624 |
+
|
625 |
+
- `overwrite_output_dir`: False
|
626 |
+
- `do_predict`: False
|
627 |
+
- `eval_strategy`: epoch
|
628 |
+
- `prediction_loss_only`: True
|
629 |
+
- `per_device_train_batch_size`: 16
|
630 |
+
- `per_device_eval_batch_size`: 16
|
631 |
+
- `per_gpu_train_batch_size`: None
|
632 |
+
- `per_gpu_eval_batch_size`: None
|
633 |
+
- `gradient_accumulation_steps`: 16
|
634 |
+
- `eval_accumulation_steps`: None
|
635 |
+
- `torch_empty_cache_steps`: None
|
636 |
+
- `learning_rate`: 2e-05
|
637 |
+
- `weight_decay`: 0.0
|
638 |
+
- `adam_beta1`: 0.9
|
639 |
+
- `adam_beta2`: 0.999
|
640 |
+
- `adam_epsilon`: 1e-08
|
641 |
+
- `max_grad_norm`: 1.0
|
642 |
+
- `num_train_epochs`: 10
|
643 |
+
- `max_steps`: -1
|
644 |
+
- `lr_scheduler_type`: cosine
|
645 |
+
- `lr_scheduler_kwargs`: {}
|
646 |
+
- `warmup_ratio`: 0.1
|
647 |
+
- `warmup_steps`: 0
|
648 |
+
- `log_level`: passive
|
649 |
+
- `log_level_replica`: warning
|
650 |
+
- `log_on_each_node`: True
|
651 |
+
- `logging_nan_inf_filter`: True
|
652 |
+
- `save_safetensors`: True
|
653 |
+
- `save_on_each_node`: False
|
654 |
+
- `save_only_model`: False
|
655 |
+
- `restore_callback_states_from_checkpoint`: False
|
656 |
+
- `no_cuda`: False
|
657 |
+
- `use_cpu`: False
|
658 |
+
- `use_mps_device`: False
|
659 |
+
- `seed`: 42
|
660 |
+
- `data_seed`: None
|
661 |
+
- `jit_mode_eval`: False
|
662 |
+
- `use_ipex`: False
|
663 |
+
- `bf16`: True
|
664 |
+
- `fp16`: False
|
665 |
+
- `fp16_opt_level`: O1
|
666 |
+
- `half_precision_backend`: auto
|
667 |
+
- `bf16_full_eval`: False
|
668 |
+
- `fp16_full_eval`: False
|
669 |
+
- `tf32`: True
|
670 |
+
- `local_rank`: 0
|
671 |
+
- `ddp_backend`: None
|
672 |
+
- `tpu_num_cores`: None
|
673 |
+
- `tpu_metrics_debug`: False
|
674 |
+
- `debug`: []
|
675 |
+
- `dataloader_drop_last`: False
|
676 |
+
- `dataloader_num_workers`: 0
|
677 |
+
- `dataloader_prefetch_factor`: None
|
678 |
+
- `past_index`: -1
|
679 |
+
- `disable_tqdm`: False
|
680 |
+
- `remove_unused_columns`: True
|
681 |
+
- `label_names`: None
|
682 |
+
- `load_best_model_at_end`: True
|
683 |
+
- `ignore_data_skip`: False
|
684 |
+
- `fsdp`: []
|
685 |
+
- `fsdp_min_num_params`: 0
|
686 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
687 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
688 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
689 |
+
- `deepspeed`: None
|
690 |
+
- `label_smoothing_factor`: 0.0
|
691 |
+
- `optim`: adamw_torch_fused
|
692 |
+
- `optim_args`: None
|
693 |
+
- `adafactor`: False
|
694 |
+
- `group_by_length`: False
|
695 |
+
- `length_column_name`: length
|
696 |
+
- `ddp_find_unused_parameters`: None
|
697 |
+
- `ddp_bucket_cap_mb`: None
|
698 |
+
- `ddp_broadcast_buffers`: False
|
699 |
+
- `dataloader_pin_memory`: True
|
700 |
+
- `dataloader_persistent_workers`: False
|
701 |
+
- `skip_memory_metrics`: True
|
702 |
+
- `use_legacy_prediction_loop`: False
|
703 |
+
- `push_to_hub`: False
|
704 |
+
- `resume_from_checkpoint`: None
|
705 |
+
- `hub_model_id`: None
|
706 |
+
- `hub_strategy`: every_save
|
707 |
+
- `hub_private_repo`: False
|
708 |
+
- `hub_always_push`: False
|
709 |
+
- `gradient_checkpointing`: False
|
710 |
+
- `gradient_checkpointing_kwargs`: None
|
711 |
+
- `include_inputs_for_metrics`: False
|
712 |
+
- `eval_do_concat_batches`: True
|
713 |
+
- `fp16_backend`: auto
|
714 |
+
- `push_to_hub_model_id`: None
|
715 |
+
- `push_to_hub_organization`: None
|
716 |
+
- `mp_parameters`:
|
717 |
+
- `auto_find_batch_size`: False
|
718 |
+
- `full_determinism`: False
|
719 |
+
- `torchdynamo`: None
|
720 |
+
- `ray_scope`: last
|
721 |
+
- `ddp_timeout`: 1800
|
722 |
+
- `torch_compile`: False
|
723 |
+
- `torch_compile_backend`: None
|
724 |
+
- `torch_compile_mode`: None
|
725 |
+
- `dispatch_batches`: None
|
726 |
+
- `split_batches`: None
|
727 |
+
- `include_tokens_per_second`: False
|
728 |
+
- `include_num_input_tokens_seen`: False
|
729 |
+
- `neftune_noise_alpha`: None
|
730 |
+
- `optim_target_modules`: None
|
731 |
+
- `batch_eval_metrics`: False
|
732 |
+
- `eval_on_start`: False
|
733 |
+
- `eval_use_gather_object`: False
|
734 |
+
- `batch_sampler`: no_duplicates
|
735 |
+
- `multi_dataset_batch_sampler`: proportional
|
736 |
+
|
737 |
+
</details>
|
738 |
+
|
739 |
+
### Training Logs
|
740 |
+
| Epoch | Step | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
|
741 |
+
|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
|
742 |
+
| 0.5161 | 10 | 2.8906 | - | - | - | - | - |
|
743 |
+
| 0.9806 | 19 | - | 0.1981 | 0.2156 | 0.2153 | 0.1849 | 0.2183 |
|
744 |
+
| 1.0323 | 20 | 1.6649 | - | - | - | - | - |
|
745 |
+
| 1.5484 | 30 | 0.992 | - | - | - | - | - |
|
746 |
+
| 1.9613 | 38 | - | 0.2141 | 0.2158 | 0.2206 | 0.1972 | 0.2196 |
|
747 |
+
| 2.0645 | 40 | 0.6799 | - | - | - | - | - |
|
748 |
+
| 2.5806 | 50 | 0.4886 | - | - | - | - | - |
|
749 |
+
| 2.9935 | 58 | - | 0.2145 | 0.2080 | 0.2205 | 0.2072 | 0.2177 |
|
750 |
+
| 3.0968 | 60 | 0.3464 | - | - | - | - | - |
|
751 |
+
| 3.6129 | 70 | 0.29 | - | - | - | - | - |
|
752 |
+
| 3.9742 | 77 | - | 0.2114 | 0.2161 | 0.2220 | 0.2074 | 0.2209 |
|
753 |
+
| 4.1290 | 80 | 0.2217 | - | - | - | - | - |
|
754 |
+
| 4.6452 | 90 | 0.2296 | - | - | - | - | - |
|
755 |
+
| **4.9548** | **96** | **-** | **0.2325** | **0.22** | **0.2283** | **0.2104** | **0.2231** |
|
756 |
+
| 5.1613 | 100 | 0.1665 | - | - | - | - | - |
|
757 |
+
| 5.6774 | 110 | 0.18 | - | - | - | - | - |
|
758 |
+
| 5.9871 | 116 | - | 0.2177 | 0.2152 | 0.2234 | 0.2061 | 0.2241 |
|
759 |
+
| 6.1935 | 120 | 0.131 | - | - | - | - | - |
|
760 |
+
| 6.7097 | 130 | 0.1502 | - | - | - | - | - |
|
761 |
+
| 6.9677 | 135 | - | 0.2127 | 0.2161 | 0.2248 | 0.2037 | 0.2226 |
|
762 |
+
| 7.2258 | 140 | 0.116 | - | - | - | - | - |
|
763 |
+
| 7.7419 | 150 | 0.1363 | - | - | - | - | - |
|
764 |
+
| 8.0 | 155 | - | 0.2196 | 0.2159 | 0.2239 | 0.2077 | 0.2233 |
|
765 |
+
| 8.2581 | 160 | 0.0976 | - | - | - | - | - |
|
766 |
+
| 8.7742 | 170 | 0.1242 | - | - | - | - | - |
|
767 |
+
| 8.9806 | 174 | - | 0.2153 | 0.2203 | 0.2293 | 0.2042 | 0.2192 |
|
768 |
+
| 9.2903 | 180 | 0.109 | - | - | - | - | - |
|
769 |
+
| 9.8065 | 190 | 0.1132 | 0.2151 | 0.2158 | 0.2208 | 0.2015 | 0.2159 |
|
770 |
+
|
771 |
+
* The bold row denotes the saved checkpoint.
|
772 |
+
|
773 |
+
### Framework Versions
|
774 |
+
- Python: 3.11.4
|
775 |
+
- Sentence Transformers: 3.0.1
|
776 |
+
- Transformers: 4.44.0
|
777 |
+
- PyTorch: 2.4.0+cu121
|
778 |
+
- Accelerate: 0.33.0
|
779 |
+
- Datasets: 2.19.1
|
780 |
+
- Tokenizers: 0.19.1
|
781 |
+
|
782 |
+
## Citation
|
783 |
+
|
784 |
+
### BibTeX
|
785 |
+
|
786 |
+
#### Sentence Transformers
|
787 |
+
```bibtex
|
788 |
+
@inproceedings{reimers-2019-sentence-bert,
|
789 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
790 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
791 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
792 |
+
month = "11",
|
793 |
+
year = "2019",
|
794 |
+
publisher = "Association for Computational Linguistics",
|
795 |
+
url = "https://arxiv.org/abs/1908.10084",
|
796 |
+
}
|
797 |
+
```
|
798 |
+
|
799 |
+
#### MatryoshkaLoss
|
800 |
+
```bibtex
|
801 |
+
@misc{kusupati2024matryoshka,
|
802 |
+
title={Matryoshka Representation Learning},
|
803 |
+
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},
|
804 |
+
year={2024},
|
805 |
+
eprint={2205.13147},
|
806 |
+
archivePrefix={arXiv},
|
807 |
+
primaryClass={cs.LG}
|
808 |
+
}
|
809 |
+
```
|
810 |
+
|
811 |
+
#### MultipleNegativesRankingLoss
|
812 |
+
```bibtex
|
813 |
+
@misc{henderson2017efficient,
|
814 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
815 |
+
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},
|
816 |
+
year={2017},
|
817 |
+
eprint={1705.00652},
|
818 |
+
archivePrefix={arXiv},
|
819 |
+
primaryClass={cs.CL}
|
820 |
+
}
|
821 |
+
```
|
822 |
+
|
823 |
+
<!--
|
824 |
+
## Glossary
|
825 |
+
|
826 |
+
*Clearly define terms in order to be accessible across audiences.*
|
827 |
+
-->
|
828 |
+
|
829 |
+
<!--
|
830 |
+
## Model Card Authors
|
831 |
+
|
832 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
833 |
+
-->
|
834 |
+
|
835 |
+
<!--
|
836 |
+
## Model Card Contact
|
837 |
+
|
838 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
839 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BAAI/bge-m3",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 8194,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.44.0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.44.0",
|
5 |
+
"pytorch": "2.4.0+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 sha256:0574a7dc1b87017509bdeccb8323fd13b48764752ecf105eb2dbcde58f5cb320
|
3 |
+
size 2271064456
|
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": 1024,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e3b8957de04e3a4ed42b1a11381556f9adad8d0d502b9dd071c75f626b28f40
|
3 |
+
size 17083053
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 8192,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"sp_model_kwargs": {},
|
53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|