Hugging Face's logo

Mollel
/
MultiLinguSwahili-bert-base-sw-cased-nli-matryoshka

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:1115700
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
Mollel commited on
Commit
5b0763d
•
1 Parent(s): 9fb1ef1

Add new SentenceTransformer model.

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +890 -0
  3. config.json +32 -0
  4. config_sentence_transformers.json +10 -0
  5. model.safetensors +3 -0
  6. modules.json +14 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +7 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +57 -0
  11. vocab.txt +0 -0
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
+ }
README.md ADDED
@@ -0,0 +1,890 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: []
3
+ library_name: sentence-transformers
4
+ tags:
5
+ - sentence-transformers
6
+ - sentence-similarity
7
+ - feature-extraction
8
+ - generated_from_trainer
9
+ - dataset_size:1115700
10
+ - loss:MatryoshkaLoss
11
+ - loss:MultipleNegativesRankingLoss
12
+ base_model: Geotrend/bert-base-sw-cased
13
+ datasets: []
14
+ metrics:
15
+ - pearson_cosine
16
+ - spearman_cosine
17
+ - pearson_manhattan
18
+ - spearman_manhattan
19
+ - pearson_euclidean
20
+ - spearman_euclidean
21
+ - pearson_dot
22
+ - spearman_dot
23
+ - pearson_max
24
+ - spearman_max
25
+ widget:
26
+ - source_sentence: Ndege mwenye mdomo mrefu katikati ya ndege.
27
+ sentences:
28
+ - Panya anayekimbia juu ya gurudumu.
29
+ - Mtu anashindana katika mashindano ya mbio.
30
+ - Ndege anayeruka.
31
+ - source_sentence: Msichana mchanga mwenye nywele nyeusi anakabili kamera na kushikilia
32
+ mfuko wa karatasi wakati amevaa shati la machungwa na mabawa ya kipepeo yenye
33
+ rangi nyingi.
34
+ sentences:
35
+ - Mwanamke mzee anakataa kupigwa picha.
36
+ - mtu akila na mvulana mdogo kwenye kijia cha jiji
37
+ - Msichana mchanga anakabili kamera.
38
+ - source_sentence: Wanawake na watoto wameketi nje katika kivuli wakati kikundi cha
39
+ watoto wadogo wameketi ndani katika kivuli.
40
+ sentences:
41
+ - Mwanamke na watoto na kukaa chini.
42
+ - Mwanamke huyo anakimbia.
43
+ - Watu wanasafiri kwa baiskeli.
44
+ - source_sentence: Mtoto mdogo anaruka mikononi mwa mwanamke aliyevalia suti nyeusi
45
+ ya kuogelea akiwa kwenye dimbwi.
46
+ sentences:
47
+ - Mtoto akiruka mikononi mwa mwanamke aliyevalia suti ya kuogelea kwenye dimbwi.
48
+ - Someone is holding oranges and walking
49
+ - Mama na binti wakinunua viatu.
50
+ - source_sentence: Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa
51
+ kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi
52
+ nyuma.
53
+ sentences:
54
+ - tai huruka
55
+ - mwanamume na mwanamke wenye mikoba
56
+ - Wanaume wawili wameketi karibu na mwanamke.
57
+ pipeline_tag: sentence-similarity
58
+ model-index:
59
+ - name: SentenceTransformer based on Geotrend/bert-base-sw-cased
60
+ results:
61
+ - task:
62
+ type: semantic-similarity
63
+ name: Semantic Similarity
64
+ dataset:
65
+ name: sts test 768
66
+ type: sts-test-768
67
+ metrics:
68
+ - type: pearson_cosine
69
+ value: 0.6937245827269046
70
+ name: Pearson Cosine
71
+ - type: spearman_cosine
72
+ value: 0.6872564222432196
73
+ name: Spearman Cosine
74
+ - type: pearson_manhattan
75
+ value: 0.6671541268726737
76
+ name: Pearson Manhattan
77
+ - type: spearman_manhattan
78
+ value: 0.6578428252987948
79
+ name: Spearman Manhattan
80
+ - type: pearson_euclidean
81
+ value: 0.6672292642346008
82
+ name: Pearson Euclidean
83
+ - type: spearman_euclidean
84
+ value: 0.6577692881532263
85
+ name: Spearman Euclidean
86
+ - type: pearson_dot
87
+ value: 0.5234944445417878
88
+ name: Pearson Dot
89
+ - type: spearman_dot
90
+ value: 0.5126395384896926
91
+ name: Spearman Dot
92
+ - type: pearson_max
93
+ value: 0.6937245827269046
94
+ name: Pearson Max
95
+ - type: spearman_max
96
+ value: 0.6872564222432196
97
+ name: Spearman Max
98
+ - task:
99
+ type: semantic-similarity
100
+ name: Semantic Similarity
101
+ dataset:
102
+ name: sts test 512
103
+ type: sts-test-512
104
+ metrics:
105
+ - type: pearson_cosine
106
+ value: 0.689885399601221
107
+ name: Pearson Cosine
108
+ - type: spearman_cosine
109
+ value: 0.6847071916895495
110
+ name: Spearman Cosine
111
+ - type: pearson_manhattan
112
+ value: 0.6678379220949281
113
+ name: Pearson Manhattan
114
+ - type: spearman_manhattan
115
+ value: 0.6579957115799916
116
+ name: Spearman Manhattan
117
+ - type: pearson_euclidean
118
+ value: 0.6673062843667007
119
+ name: Pearson Euclidean
120
+ - type: spearman_euclidean
121
+ value: 0.6573006123381013
122
+ name: Spearman Euclidean
123
+ - type: pearson_dot
124
+ value: 0.49533316366864977
125
+ name: Pearson Dot
126
+ - type: spearman_dot
127
+ value: 0.48723679408818543
128
+ name: Spearman Dot
129
+ - type: pearson_max
130
+ value: 0.689885399601221
131
+ name: Pearson Max
132
+ - type: spearman_max
133
+ value: 0.6847071916895495
134
+ name: Spearman Max
135
+ - task:
136
+ type: semantic-similarity
137
+ name: Semantic Similarity
138
+ dataset:
139
+ name: sts test 256
140
+ type: sts-test-256
141
+ metrics:
142
+ - type: pearson_cosine
143
+ value: 0.6873377612773459
144
+ name: Pearson Cosine
145
+ - type: spearman_cosine
146
+ value: 0.6816874105466478
147
+ name: Spearman Cosine
148
+ - type: pearson_manhattan
149
+ value: 0.667357515297651
150
+ name: Pearson Manhattan
151
+ - type: spearman_manhattan
152
+ value: 0.6557727891191705
153
+ name: Spearman Manhattan
154
+ - type: pearson_euclidean
155
+ value: 0.6674937201647584
156
+ name: Pearson Euclidean
157
+ - type: spearman_euclidean
158
+ value: 0.6560441259953166
159
+ name: Spearman Euclidean
160
+ - type: pearson_dot
161
+ value: 0.45660372834373963
162
+ name: Pearson Dot
163
+ - type: spearman_dot
164
+ value: 0.4533070407260065
165
+ name: Spearman Dot
166
+ - type: pearson_max
167
+ value: 0.6873377612773459
168
+ name: Pearson Max
169
+ - type: spearman_max
170
+ value: 0.6816874105466478
171
+ name: Spearman Max
172
+ - task:
173
+ type: semantic-similarity
174
+ name: Semantic Similarity
175
+ dataset:
176
+ name: sts test 128
177
+ type: sts-test-128
178
+ metrics:
179
+ - type: pearson_cosine
180
+ value: 0.6836009506667413
181
+ name: Pearson Cosine
182
+ - type: spearman_cosine
183
+ value: 0.6795423695973911
184
+ name: Spearman Cosine
185
+ - type: pearson_manhattan
186
+ value: 0.6663652896396122
187
+ name: Pearson Manhattan
188
+ - type: spearman_manhattan
189
+ value: 0.6534731725514219
190
+ name: Spearman Manhattan
191
+ - type: pearson_euclidean
192
+ value: 0.6663726876345561
193
+ name: Pearson Euclidean
194
+ - type: spearman_euclidean
195
+ value: 0.6537216014002204
196
+ name: Spearman Euclidean
197
+ - type: pearson_dot
198
+ value: 0.43102957451470686
199
+ name: Pearson Dot
200
+ - type: spearman_dot
201
+ value: 0.431538008932168
202
+ name: Spearman Dot
203
+ - type: pearson_max
204
+ value: 0.6836009506667413
205
+ name: Pearson Max
206
+ - type: spearman_max
207
+ value: 0.6795423695973911
208
+ name: Spearman Max
209
+ - task:
210
+ type: semantic-similarity
211
+ name: Semantic Similarity
212
+ dataset:
213
+ name: sts test 64
214
+ type: sts-test-64
215
+ metrics:
216
+ - type: pearson_cosine
217
+ value: 0.6715253560367674
218
+ name: Pearson Cosine
219
+ - type: spearman_cosine
220
+ value: 0.669070001537953
221
+ name: Spearman Cosine
222
+ - type: pearson_manhattan
223
+ value: 0.6571390159051358
224
+ name: Pearson Manhattan
225
+ - type: spearman_manhattan
226
+ value: 0.6456119247619697
227
+ name: Spearman Manhattan
228
+ - type: pearson_euclidean
229
+ value: 0.6598587843081631
230
+ name: Pearson Euclidean
231
+ - type: spearman_euclidean
232
+ value: 0.6472279949159918
233
+ name: Spearman Euclidean
234
+ - type: pearson_dot
235
+ value: 0.36757468941627225
236
+ name: Pearson Dot
237
+ - type: spearman_dot
238
+ value: 0.3678274698380672
239
+ name: Spearman Dot
240
+ - type: pearson_max
241
+ value: 0.6715253560367674
242
+ name: Pearson Max
243
+ - type: spearman_max
244
+ value: 0.669070001537953
245
+ name: Spearman Max
246
+ ---
247
+
248
+ # SentenceTransformer based on Geotrend/bert-base-sw-cased
249
+
250
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Geotrend/bert-base-sw-cased](https://huggingface.co/Geotrend/bert-base-sw-cased) on the Mollel/swahili-n_li-triplet-swh-eng dataset. 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.
251
+
252
+ ## Model Details
253
+
254
+ ### Model Description
255
+ - **Model Type:** Sentence Transformer
256
+ - **Base model:** [Geotrend/bert-base-sw-cased](https://huggingface.co/Geotrend/bert-base-sw-cased) <!-- at revision 7d9ca957a81d2449cf1319af0b91f75f11642336 -->
257
+ - **Maximum Sequence Length:** 512 tokens
258
+ - **Output Dimensionality:** 768 tokens
259
+ - **Similarity Function:** Cosine Similarity
260
+ - **Training Dataset:**
261
+ - Mollel/swahili-n_li-triplet-swh-eng
262
+ <!-- - **Language:** Unknown -->
263
+ <!-- - **License:** Unknown -->
264
+
265
+ ### Model Sources
266
+
267
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
268
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
269
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
270
+
271
+ ### Full Model Architecture
272
+
273
+ ```
274
+ SentenceTransformer(
275
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
276
+ (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})
277
+ )
278
+ ```
279
+
280
+ ## Usage
281
+
282
+ ### Direct Usage (Sentence Transformers)
283
+
284
+ First install the Sentence Transformers library:
285
+
286
+ ```bash
287
+ pip install -U sentence-transformers
288
+ ```
289
+
290
+ Then you can load this model and run inference.
291
+ ```python
292
+ from sentence_transformers import SentenceTransformer
293
+
294
+ # Download from the 🤗 Hub
295
+ model = SentenceTransformer("Mollel/MultiLinguSwahili-bert-base-sw-cased-nli-matryoshka")
296
+ # Run inference
297
+ sentences = [
298
+ 'Mwanamume na mwanamke wachanga waliovaa mikoba wanaweka au kuondoa kitu kutoka kwenye mti mweupe wa zamani, huku watu wengine wamesimama au wameketi nyuma.',
299
+ 'mwanamume na mwanamke wenye mikoba',
300
+ 'tai huruka',
301
+ ]
302
+ embeddings = model.encode(sentences)
303
+ print(embeddings.shape)
304
+ # [3, 768]
305
+
306
+ # Get the similarity scores for the embeddings
307
+ similarities = model.similarity(embeddings, embeddings)
308
+ print(similarities.shape)
309
+ # [3, 3]
310
+ ```
311
+
312
+ <!--
313
+ ### Direct Usage (Transformers)
314
+
315
+ <details><summary>Click to see the direct usage in Transformers</summary>
316
+
317
+ </details>
318
+ -->
319
+
320
+ <!--
321
+ ### Downstream Usage (Sentence Transformers)
322
+
323
+ You can finetune this model on your own dataset.
324
+
325
+ <details><summary>Click to expand</summary>
326
+
327
+ </details>
328
+ -->
329
+
330
+ <!--
331
+ ### Out-of-Scope Use
332
+
333
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
334
+ -->
335
+
336
+ ## Evaluation
337
+
338
+ ### Metrics
339
+
340
+ #### Semantic Similarity
341
+ * Dataset: `sts-test-768`
342
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
343
+
344
+ | Metric | Value |
345
+ |:--------------------|:-----------|
346
+ | pearson_cosine | 0.6937 |
347
+ | **spearman_cosine** | **0.6873** |
348
+ | pearson_manhattan | 0.6672 |
349
+ | spearman_manhattan | 0.6578 |
350
+ | pearson_euclidean | 0.6672 |
351
+ | spearman_euclidean | 0.6578 |
352
+ | pearson_dot | 0.5235 |
353
+ | spearman_dot | 0.5126 |
354
+ | pearson_max | 0.6937 |
355
+ | spearman_max | 0.6873 |
356
+
357
+ #### Semantic Similarity
358
+ * Dataset: `sts-test-512`
359
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
360
+
361
+ | Metric | Value |
362
+ |:--------------------|:-----------|
363
+ | pearson_cosine | 0.6899 |
364
+ | **spearman_cosine** | **0.6847** |
365
+ | pearson_manhattan | 0.6678 |
366
+ | spearman_manhattan | 0.658 |
367
+ | pearson_euclidean | 0.6673 |
368
+ | spearman_euclidean | 0.6573 |
369
+ | pearson_dot | 0.4953 |
370
+ | spearman_dot | 0.4872 |
371
+ | pearson_max | 0.6899 |
372
+ | spearman_max | 0.6847 |
373
+
374
+ #### Semantic Similarity
375
+ * Dataset: `sts-test-256`
376
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
377
+
378
+ | Metric | Value |
379
+ |:--------------------|:-----------|
380
+ | pearson_cosine | 0.6873 |
381
+ | **spearman_cosine** | **0.6817** |
382
+ | pearson_manhattan | 0.6674 |
383
+ | spearman_manhattan | 0.6558 |
384
+ | pearson_euclidean | 0.6675 |
385
+ | spearman_euclidean | 0.656 |
386
+ | pearson_dot | 0.4566 |
387
+ | spearman_dot | 0.4533 |
388
+ | pearson_max | 0.6873 |
389
+ | spearman_max | 0.6817 |
390
+
391
+ #### Semantic Similarity
392
+ * Dataset: `sts-test-128`
393
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
394
+
395
+ | Metric | Value |
396
+ |:--------------------|:-----------|
397
+ | pearson_cosine | 0.6836 |
398
+ | **spearman_cosine** | **0.6795** |
399
+ | pearson_manhattan | 0.6664 |
400
+ | spearman_manhattan | 0.6535 |
401
+ | pearson_euclidean | 0.6664 |
402
+ | spearman_euclidean | 0.6537 |
403
+ | pearson_dot | 0.431 |
404
+ | spearman_dot | 0.4315 |
405
+ | pearson_max | 0.6836 |
406
+ | spearman_max | 0.6795 |
407
+
408
+ #### Semantic Similarity
409
+ * Dataset: `sts-test-64`
410
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
411
+
412
+ | Metric | Value |
413
+ |:--------------------|:-----------|
414
+ | pearson_cosine | 0.6715 |
415
+ | **spearman_cosine** | **0.6691** |
416
+ | pearson_manhattan | 0.6571 |
417
+ | spearman_manhattan | 0.6456 |
418
+ | pearson_euclidean | 0.6599 |
419
+ | spearman_euclidean | 0.6472 |
420
+ | pearson_dot | 0.3676 |
421
+ | spearman_dot | 0.3678 |
422
+ | pearson_max | 0.6715 |
423
+ | spearman_max | 0.6691 |
424
+
425
+ <!--
426
+ ## Bias, Risks and Limitations
427
+
428
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
429
+ -->
430
+
431
+ <!--
432
+ ### Recommendations
433
+
434
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
435
+ -->
436
+
437
+ ## Training Details
438
+
439
+ ### Training Dataset
440
+
441
+ #### Mollel/swahili-n_li-triplet-swh-eng
442
+
443
+ * Dataset: Mollel/swahili-n_li-triplet-swh-eng
444
+ * Size: 1,115,700 training samples
445
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
446
+ * Approximate statistics based on the first 1000 samples:
447
+ | | anchor | positive | negative |
448
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
449
+ | type | string | string | string |
450
+ | details | <ul><li>min: 9 tokens</li><li>mean: 16.73 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.74 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.0 tokens</li><li>max: 49 tokens</li></ul> |
451
+ * Samples:
452
+ | anchor | positive | negative |
453
+ |:----------------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------------------|
454
+ | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>A person is at a diner, ordering an omelette.</code> |
455
+ | <code>Mtu aliyepanda farasi anaruka juu ya ndege iliyovunjika.</code> | <code>Mtu yuko nje, juu ya farasi.</code> | <code>Mtu yuko kwenye mkahawa, akiagiza omelette.</code> |
456
+ | <code>Children smiling and waving at camera</code> | <code>There are children present</code> | <code>The kids are frowning</code> |
457
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
458
+ ```json
459
+ {
460
+ "loss": "MultipleNegativesRankingLoss",
461
+ "matryoshka_dims": [
462
+ 768,
463
+ 512,
464
+ 256,
465
+ 128,
466
+ 64
467
+ ],
468
+ "matryoshka_weights": [
469
+ 1,
470
+ 1,
471
+ 1,
472
+ 1,
473
+ 1
474
+ ],
475
+ "n_dims_per_step": -1
476
+ }
477
+ ```
478
+
479
+ ### Evaluation Dataset
480
+
481
+ #### Mollel/swahili-n_li-triplet-swh-eng
482
+
483
+ * Dataset: Mollel/swahili-n_li-triplet-swh-eng
484
+ * Size: 13,168 evaluation samples
485
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
486
+ * Approximate statistics based on the first 1000 samples:
487
+ | | anchor | positive | negative |
488
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
489
+ | type | string | string | string |
490
+ | details | <ul><li>min: 7 tokens</li><li>mean: 28.25 tokens</li><li>max: 82 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.16 tokens</li><li>max: 55 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.55 tokens</li><li>max: 46 tokens</li></ul> |
491
+ * Samples:
492
+ | anchor | positive | negative |
493
+ |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:-------------------------------------------------------------------|
494
+ | <code>Two women are embracing while holding to go packages.</code> | <code>Two woman are holding packages.</code> | <code>The men are fighting outside a deli.</code> |
495
+ | <code>Wanawake wawili wanakumbatiana huku wakishikilia vifurushi vya kwenda.</code> | <code>Wanawake wawili wanashikilia vifurushi.</code> | <code>Wanaume hao wanapigana nje ya duka la vyakula vitamu.</code> |
496
+ | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code> |
497
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
498
+ ```json
499
+ {
500
+ "loss": "MultipleNegativesRankingLoss",
501
+ "matryoshka_dims": [
502
+ 768,
503
+ 512,
504
+ 256,
505
+ 128,
506
+ 64
507
+ ],
508
+ "matryoshka_weights": [
509
+ 1,
510
+ 1,
511
+ 1,
512
+ 1,
513
+ 1
514
+ ],
515
+ "n_dims_per_step": -1
516
+ }
517
+ ```
518
+
519
+ ### Training Hyperparameters
520
+ #### Non-Default Hyperparameters
521
+
522
+ - `per_device_train_batch_size`: 32
523
+ - `per_device_eval_batch_size`: 32
524
+ - `learning_rate`: 2e-05
525
+ - `num_train_epochs`: 1
526
+ - `warmup_ratio`: 0.1
527
+ - `bf16`: True
528
+ - `batch_sampler`: no_duplicates
529
+
530
+ #### All Hyperparameters
531
+ <details><summary>Click to expand</summary>
532
+
533
+ - `overwrite_output_dir`: False
534
+ - `do_predict`: False
535
+ - `prediction_loss_only`: True
536
+ - `per_device_train_batch_size`: 32
537
+ - `per_device_eval_batch_size`: 32
538
+ - `per_gpu_train_batch_size`: None
539
+ - `per_gpu_eval_batch_size`: None
540
+ - `gradient_accumulation_steps`: 1
541
+ - `eval_accumulation_steps`: None
542
+ - `learning_rate`: 2e-05
543
+ - `weight_decay`: 0.0
544
+ - `adam_beta1`: 0.9
545
+ - `adam_beta2`: 0.999
546
+ - `adam_epsilon`: 1e-08
547
+ - `max_grad_norm`: 1.0
548
+ - `num_train_epochs`: 1
549
+ - `max_steps`: -1
550
+ - `lr_scheduler_type`: linear
551
+ - `lr_scheduler_kwargs`: {}
552
+ - `warmup_ratio`: 0.1
553
+ - `warmup_steps`: 0
554
+ - `log_level`: passive
555
+ - `log_level_replica`: warning
556
+ - `log_on_each_node`: True
557
+ - `logging_nan_inf_filter`: True
558
+ - `save_safetensors`: True
559
+ - `save_on_each_node`: False
560
+ - `save_only_model`: False
561
+ - `no_cuda`: False
562
+ - `use_cpu`: False
563
+ - `use_mps_device`: False
564
+ - `seed`: 42
565
+ - `data_seed`: None
566
+ - `jit_mode_eval`: False
567
+ - `use_ipex`: False
568
+ - `bf16`: True
569
+ - `fp16`: False
570
+ - `fp16_opt_level`: O1
571
+ - `half_precision_backend`: auto
572
+ - `bf16_full_eval`: False
573
+ - `fp16_full_eval`: False
574
+ - `tf32`: None
575
+ - `local_rank`: 0
576
+ - `ddp_backend`: None
577
+ - `tpu_num_cores`: None
578
+ - `tpu_metrics_debug`: False
579
+ - `debug`: []
580
+ - `dataloader_drop_last`: False
581
+ - `dataloader_num_workers`: 0
582
+ - `dataloader_prefetch_factor`: None
583
+ - `past_index`: -1
584
+ - `disable_tqdm`: False
585
+ - `remove_unused_columns`: True
586
+ - `label_names`: None
587
+ - `load_best_model_at_end`: False
588
+ - `ignore_data_skip`: False
589
+ - `fsdp`: []
590
+ - `fsdp_min_num_params`: 0
591
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
592
+ - `fsdp_transformer_layer_cls_to_wrap`: None
593
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}
594
+ - `deepspeed`: None
595
+ - `label_smoothing_factor`: 0.0
596
+ - `optim`: adamw_torch
597
+ - `optim_args`: None
598
+ - `adafactor`: False
599
+ - `group_by_length`: False
600
+ - `length_column_name`: length
601
+ - `ddp_find_unused_parameters`: None
602
+ - `ddp_bucket_cap_mb`: None
603
+ - `ddp_broadcast_buffers`: False
604
+ - `dataloader_pin_memory`: True
605
+ - `dataloader_persistent_workers`: False
606
+ - `skip_memory_metrics`: True
607
+ - `use_legacy_prediction_loop`: False
608
+ - `push_to_hub`: False
609
+ - `resume_from_checkpoint`: None
610
+ - `hub_model_id`: None
611
+ - `hub_strategy`: every_save
612
+ - `hub_private_repo`: False
613
+ - `hub_always_push`: False
614
+ - `gradient_checkpointing`: False
615
+ - `gradient_checkpointing_kwargs`: None
616
+ - `include_inputs_for_metrics`: False
617
+ - `eval_do_concat_batches`: True
618
+ - `fp16_backend`: auto
619
+ - `push_to_hub_model_id`: None
620
+ - `push_to_hub_organization`: None
621
+ - `mp_parameters`:
622
+ - `auto_find_batch_size`: False
623
+ - `full_determinism`: False
624
+ - `torchdynamo`: None
625
+ - `ray_scope`: last
626
+ - `ddp_timeout`: 1800
627
+ - `torch_compile`: False
628
+ - `torch_compile_backend`: None
629
+ - `torch_compile_mode`: None
630
+ - `dispatch_batches`: None
631
+ - `split_batches`: None
632
+ - `include_tokens_per_second`: False
633
+ - `include_num_input_tokens_seen`: False
634
+ - `neftune_noise_alpha`: None
635
+ - `optim_target_modules`: None
636
+ - `batch_sampler`: no_duplicates
637
+ - `multi_dataset_batch_sampler`: proportional
638
+
639
+ </details>
640
+
641
+ ### Training Logs
642
+ <details><summary>Click to expand</summary>
643
+
644
+ | Epoch | Step | Training Loss | sts-test-128_spearman_cosine | sts-test-256_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine |
645
+ |:------:|:-----:|:-------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
646
+ | 0.0057 | 100 | 19.9104 | - | - | - | - | - |
647
+ | 0.0115 | 200 | 15.4038 | - | - | - | - | - |
648
+ | 0.0172 | 300 | 12.4565 | - | - | - | - | - |
649
+ | 0.0229 | 400 | 11.8633 | - | - | - | - | - |
650
+ | 0.0287 | 500 | 11.0601 | - | - | - | - | - |
651
+ | 0.0344 | 600 | 9.7725 | - | - | - | - | - |
652
+ | 0.0402 | 700 | 8.8549 | - | - | - | - | - |
653
+ | 0.0459 | 800 | 8.0831 | - | - | - | - | - |
654
+ | 0.0516 | 900 | 7.9941 | - | - | - | - | - |
655
+ | 0.0574 | 1000 | 7.6537 | - | - | - | - | - |
656
+ | 0.0631 | 1100 | 7.9303 | - | - | - | - | - |
657
+ | 0.0688 | 1200 | 7.5246 | - | - | - | - | - |
658
+ | 0.0746 | 1300 | 7.7754 | - | - | - | - | - |
659
+ | 0.0803 | 1400 | 7.668 | - | - | - | - | - |
660
+ | 0.0860 | 1500 | 6.7171 | - | - | - | - | - |
661
+ | 0.0918 | 1600 | 6.347 | - | - | - | - | - |
662
+ | 0.0975 | 1700 | 6.0 | - | - | - | - | - |
663
+ | 0.1033 | 1800 | 6.4314 | - | - | - | - | - |
664
+ | 0.1090 | 1900 | 6.7947 | - | - | - | - | - |
665
+ | 0.1147 | 2000 | 6.9316 | - | - | - | - | - |
666
+ | 0.1205 | 2100 | 6.6304 | - | - | - | - | - |
667
+ | 0.1262 | 2200 | 6.132 | - | - | - | - | - |
668
+ | 0.1319 | 2300 | 5.8953 | - | - | - | - | - |
669
+ | 0.1377 | 2400 | 5.6954 | - | - | - | - | - |
670
+ | 0.1434 | 2500 | 5.6832 | - | - | - | - | - |
671
+ | 0.1491 | 2600 | 5.2266 | - | - | - | - | - |
672
+ | 0.1549 | 2700 | 5.0678 | - | - | - | - | - |
673
+ | 0.1606 | 2800 | 5.4733 | - | - | - | - | - |
674
+ | 0.1664 | 2900 | 6.0899 | - | - | - | - | - |
675
+ | 0.1721 | 3000 | 6.332 | - | - | - | - | - |
676
+ | 0.1778 | 3100 | 6.4937 | - | - | - | - | - |
677
+ | 0.1836 | 3200 | 6.2242 | - | - | - | - | - |
678
+ | 0.1893 | 3300 | 5.8023 | - | - | - | - | - |
679
+ | 0.1950 | 3400 | 5.0745 | - | - | - | - | - |
680
+ | 0.2008 | 3500 | 5.5806 | - | - | - | - | - |
681
+ | 0.2065 | 3600 | 5.5191 | - | - | - | - | - |
682
+ | 0.2122 | 3700 | 5.3849 | - | - | - | - | - |
683
+ | 0.2180 | 3800 | 5.4828 | - | - | - | - | - |
684
+ | 0.2237 | 3900 | 5.9982 | - | - | - | - | - |
685
+ | 0.2294 | 4000 | 5.6842 | - | - | - | - | - |
686
+ | 0.2352 | 4100 | 5.1627 | - | - | - | - | - |
687
+ | 0.2409 | 4200 | 5.154 | - | - | - | - | - |
688
+ | 0.2467 | 4300 | 5.7932 | - | - | - | - | - |
689
+ | 0.2524 | 4400 | 5.5758 | - | - | - | - | - |
690
+ | 0.2581 | 4500 | 5.5212 | - | - | - | - | - |
691
+ | 0.2639 | 4600 | 5.5692 | - | - | - | - | - |
692
+ | 0.2696 | 4700 | 5.2699 | - | - | - | - | - |
693
+ | 0.2753 | 4800 | 5.4919 | - | - | - | - | - |
694
+ | 0.2811 | 4900 | 5.0754 | - | - | - | - | - |
695
+ | 0.2868 | 5000 | 5.1514 | - | - | - | - | - |
696
+ | 0.2925 | 5100 | 5.0241 | - | - | - | - | - |
697
+ | 0.2983 | 5200 | 5.2679 | - | - | - | - | - |
698
+ | 0.3040 | 5300 | 5.3576 | - | - | - | - | - |
699
+ | 0.3098 | 5400 | 5.3454 | - | - | - | - | - |
700
+ | 0.3155 | 5500 | 5.2142 | - | - | - | - | - |
701
+ | 0.3212 | 5600 | 4.8418 | - | - | - | - | - |
702
+ | 0.3270 | 5700 | 4.9597 | - | - | - | - | - |
703
+ | 0.3327 | 5800 | 5.1989 | - | - | - | - | - |
704
+ | 0.3384 | 5900 | 5.2624 | - | - | - | - | - |
705
+ | 0.3442 | 6000 | 5.0705 | - | - | - | - | - |
706
+ | 0.3499 | 6100 | 5.232 | - | - | - | - | - |
707
+ | 0.3556 | 6200 | 5.2428 | - | - | - | - | - |
708
+ | 0.3614 | 6300 | 4.755 | - | - | - | - | - |
709
+ | 0.3671 | 6400 | 4.7266 | - | - | - | - | - |
710
+ | 0.3729 | 6500 | 4.6452 | - | - | - | - | - |
711
+ | 0.3786 | 6600 | 5.1431 | - | - | - | - | - |
712
+ | 0.3843 | 6700 | 4.5343 | - | - | - | - | - |
713
+ | 0.3901 | 6800 | 4.698 | - | - | - | - | - |
714
+ | 0.3958 | 6900 | 4.6944 | - | - | - | - | - |
715
+ | 0.4015 | 7000 | 4.6255 | - | - | - | - | - |
716
+ | 0.4073 | 7100 | 5.0211 | - | - | - | - | - |
717
+ | 0.4130 | 7200 | 4.6974 | - | - | - | - | - |
718
+ | 0.4187 | 7300 | 4.9182 | - | - | - | - | - |
719
+ | 0.4245 | 7400 | 4.652 | - | - | - | - | - |
720
+ | 0.4302 | 7500 | 5.1015 | - | - | - | - | - |
721
+ | 0.4360 | 7600 | 4.5249 | - | - | - | - | - |
722
+ | 0.4417 | 7700 | 4.455 | - | - | - | - | - |
723
+ | 0.4474 | 7800 | 4.8153 | - | - | - | - | - |
724
+ | 0.4532 | 7900 | 4.7665 | - | - | - | - | - |
725
+ | 0.4589 | 8000 | 4.3413 | - | - | - | - | - |
726
+ | 0.4646 | 8100 | 4.4697 | - | - | - | - | - |
727
+ | 0.4704 | 8200 | 4.6776 | - | - | - | - | - |
728
+ | 0.4761 | 8300 | 4.2868 | - | - | - | - | - |
729
+ | 0.4818 | 8400 | 4.7052 | - | - | - | - | - |
730
+ | 0.4876 | 8500 | 4.4721 | - | - | - | - | - |
731
+ | 0.4933 | 8600 | 4.6926 | - | - | - | - | - |
732
+ | 0.4991 | 8700 | 4.9891 | - | - | - | - | - |
733
+ | 0.5048 | 8800 | 4.4837 | - | - | - | - | - |
734
+ | 0.5105 | 8900 | 4.8127 | - | - | - | - | - |
735
+ | 0.5163 | 9000 | 4.3438 | - | - | - | - | - |
736
+ | 0.5220 | 9100 | 4.4743 | - | - | - | - | - |
737
+ | 0.5277 | 9200 | 4.6879 | - | - | - | - | - |
738
+ | 0.5335 | 9300 | 4.3593 | - | - | - | - | - |
739
+ | 0.5392 | 9400 | 4.3023 | - | - | - | - | - |
740
+ | 0.5449 | 9500 | 4.8188 | - | - | - | - | - |
741
+ | 0.5507 | 9600 | 4.6142 | - | - | - | - | - |
742
+ | 0.5564 | 9700 | 4.7679 | - | - | - | - | - |
743
+ | 0.5622 | 9800 | 4.6224 | - | - | - | - | - |
744
+ | 0.5679 | 9900 | 4.9154 | - | - | - | - | - |
745
+ | 0.5736 | 10000 | 4.7557 | - | - | - | - | - |
746
+ | 0.5794 | 10100 | 4.6395 | - | - | - | - | - |
747
+ | 0.5851 | 10200 | 4.7977 | - | - | - | - | - |
748
+ | 0.5908 | 10300 | 4.915 | - | - | - | - | - |
749
+ | 0.5966 | 10400 | 4.4854 | - | - | - | - | - |
750
+ | 0.6023 | 10500 | 4.3973 | - | - | - | - | - |
751
+ | 0.6080 | 10600 | 4.6964 | - | - | - | - | - |
752
+ | 0.6138 | 10700 | 4.8853 | - | - | - | - | - |
753
+ | 0.6195 | 10800 | 4.786 | - | - | - | - | - |
754
+ | 0.6253 | 10900 | 4.5482 | - | - | - | - | - |
755
+ | 0.6310 | 11000 | 4.4857 | - | - | - | - | - |
756
+ | 0.6367 | 11100 | 4.7415 | - | - | - | - | - |
757
+ | 0.6425 | 11200 | 4.2596 | - | - | - | - | - |
758
+ | 0.6482 | 11300 | 4.8578 | - | - | - | - | - |
759
+ | 0.6539 | 11400 | 4.5471 | - | - | - | - | - |
760
+ | 0.6597 | 11500 | 4.8337 | - | - | - | - | - |
761
+ | 0.6654 | 11600 | 4.2244 | - | - | - | - | - |
762
+ | 0.6711 | 11700 | 4.9619 | - | - | - | - | - |
763
+ | 0.6769 | 11800 | 4.9369 | - | - | - | - | - |
764
+ | 0.6826 | 11900 | 4.2697 | - | - | - | - | - |
765
+ | 0.6883 | 12000 | 4.2711 | - | - | - | - | - |
766
+ | 0.6941 | 12100 | 4.6396 | - | - | - | - | - |
767
+ | 0.6998 | 12200 | 4.5626 | - | - | - | - | - |
768
+ | 0.7056 | 12300 | 4.5767 | - | - | - | - | - |
769
+ | 0.7113 | 12400 | 4.6449 | - | - | - | - | - |
770
+ | 0.7170 | 12500 | 4.4217 | - | - | - | - | - |
771
+ | 0.7228 | 12600 | 4.0203 | - | - | - | - | - |
772
+ | 0.7285 | 12700 | 4.5381 | - | - | - | - | - |
773
+ | 0.7342 | 12800 | 4.5865 | - | - | - | - | - |
774
+ | 0.7400 | 12900 | 4.4203 | - | - | - | - | - |
775
+ | 0.7457 | 13000 | 4.3761 | - | - | - | - | - |
776
+ | 0.7514 | 13100 | 4.093 | - | - | - | - | - |
777
+ | 0.7572 | 13200 | 5.9235 | - | - | - | - | - |
778
+ | 0.7629 | 13300 | 5.4098 | - | - | - | - | - |
779
+ | 0.7687 | 13400 | 5.3079 | - | - | - | - | - |
780
+ | 0.7744 | 13500 | 5.0946 | - | - | - | - | - |
781
+ | 0.7801 | 13600 | 4.7098 | - | - | - | - | - |
782
+ | 0.7859 | 13700 | 4.9471 | - | - | - | - | - |
783
+ | 0.7916 | 13800 | 4.5742 | - | - | - | - | - |
784
+ | 0.7973 | 13900 | 4.6178 | - | - | - | - | - |
785
+ | 0.8031 | 14000 | 4.4516 | - | - | - | - | - |
786
+ | 0.8088 | 14100 | 4.429 | - | - | - | - | - |
787
+ | 0.8145 | 14200 | 4.3812 | - | - | - | - | - |
788
+ | 0.8203 | 14300 | 4.3739 | - | - | - | - | - |
789
+ | 0.8260 | 14400 | 4.3821 | - | - | - | - | - |
790
+ | 0.8318 | 14500 | 4.4396 | - | - | - | - | - |
791
+ | 0.8375 | 14600 | 4.2667 | - | - | - | - | - |
792
+ | 0.8432 | 14700 | 4.1963 | - | - | - | - | - |
793
+ | 0.8490 | 14800 | 4.1298 | - | - | - | - | - |
794
+ | 0.8547 | 14900 | 4.1843 | - | - | - | - | - |
795
+ | 0.8604 | 15000 | 4.0735 | - | - | - | - | - |
796
+ | 0.8662 | 15100 | 3.9319 | - | - | - | - | - |
797
+ | 0.8719 | 15200 | 4.1544 | - | - | - | - | - |
798
+ | 0.8776 | 15300 | 4.105 | - | - | - | - | - |
799
+ | 0.8834 | 15400 | 4.014 | - | - | - | - | - |
800
+ | 0.8891 | 15500 | 4.0345 | - | - | - | - | - |
801
+ | 0.8949 | 15600 | 3.9127 | - | - | - | - | - |
802
+ | 0.9006 | 15700 | 4.1002 | - | - | - | - | - |
803
+ | 0.9063 | 15800 | 3.8564 | - | - | - | - | - |
804
+ | 0.9121 | 15900 | 3.9297 | - | - | - | - | - |
805
+ | 0.9178 | 16000 | 3.8487 | - | - | - | - | - |
806
+ | 0.9235 | 16100 | 3.7099 | - | - | - | - | - |
807
+ | 0.9293 | 16200 | 3.8545 | - | - | - | - | - |
808
+ | 0.9350 | 16300 | 3.8122 | - | - | - | - | - |
809
+ | 0.9407 | 16400 | 3.8951 | - | - | - | - | - |
810
+ | 0.9465 | 16500 | 3.6996 | - | - | - | - | - |
811
+ | 0.9522 | 16600 | 3.9081 | - | - | - | - | - |
812
+ | 0.9580 | 16700 | 3.8603 | - | - | - | - | - |
813
+ | 0.9637 | 16800 | 3.8534 | - | - | - | - | - |
814
+ | 0.9694 | 16900 | 3.8145 | - | - | - | - | - |
815
+ | 0.9752 | 17000 | 3.9858 | - | - | - | - | - |
816
+ | 0.9809 | 17100 | 3.8224 | - | - | - | - | - |
817
+ | 0.9866 | 17200 | 3.7469 | - | - | - | - | - |
818
+ | 0.9924 | 17300 | 3.9066 | - | - | - | - | - |
819
+ | 0.9981 | 17400 | 3.6754 | - | - | - | - | - |
820
+ | 1.0 | 17433 | - | 0.6795 | 0.6817 | 0.6847 | 0.6691 | 0.6873 |
821
+
822
+ </details>
823
+
824
+ ### Framework Versions
825
+ - Python: 3.11.9
826
+ - Sentence Transformers: 3.0.1
827
+ - Transformers: 4.40.1
828
+ - PyTorch: 2.3.0+cu121
829
+ - Accelerate: 0.29.3
830
+ - Datasets: 2.19.0
831
+ - Tokenizers: 0.19.1
832
+
833
+ ## Citation
834
+
835
+ ### BibTeX
836
+
837
+ #### Sentence Transformers
838
+ ```bibtex
839
+ @inproceedings{reimers-2019-sentence-bert,
840
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
841
+ author = "Reimers, Nils and Gurevych, Iryna",
842
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
843
+ month = "11",
844
+ year = "2019",
845
+ publisher = "Association for Computational Linguistics",
846
+ url = "https://arxiv.org/abs/1908.10084",
847
+ }
848
+ ```
849
+
850
+ #### MatryoshkaLoss
851
+ ```bibtex
852
+ @misc{kusupati2024matryoshka,
853
+ title={Matryoshka Representation Learning},
854
+ 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},
855
+ year={2024},
856
+ eprint={2205.13147},
857
+ archivePrefix={arXiv},
858
+ primaryClass={cs.LG}
859
+ }
860
+ ```
861
+
862
+ #### MultipleNegativesRankingLoss
863
+ ```bibtex
864
+ @misc{henderson2017efficient,
865
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
866
+ 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},
867
+ year={2017},
868
+ eprint={1705.00652},
869
+ archivePrefix={arXiv},
870
+ primaryClass={cs.CL}
871
+ }
872
+ ```
873
+
874
+ <!--
875
+ ## Glossary
876
+
877
+ *Clearly define terms in order to be accessible across audiences.*
878
+ -->
879
+
880
+ <!--
881
+ ## Model Card Authors
882
+
883
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
884
+ -->
885
+
886
+ <!--
887
+ ## Model Card Contact
888
+
889
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
890
+ -->
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Geotrend/bert-base-sw-cased",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 0,
21
+ "pooler_fc_size": 768,
22
+ "pooler_num_attention_heads": 12,
23
+ "pooler_num_fc_layers": 3,
24
+ "pooler_size_per_head": 128,
25
+ "pooler_type": "first_token_transform",
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.40.1",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 16632
32
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.40.1",
5
+ "pytorch": "2.3.0+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 sha256:662acea46800babde5dbde49f2a65172c936e7910cfec63aa39628b70e259b56
3
+ size 395281192
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
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
+ "10": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "11": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "12": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "13": {
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": false,
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