Mollel commited on
Commit
5b15e6f
1 Parent(s): db6d43a

Add new SentenceTransformer model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": 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 +1,948 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: nomic-ai/nomic-embed-text-v1.5
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 nomic-ai/nomic-embed-text-v1.5
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: 0.6944960057464138
70
+ name: Pearson Cosine
71
+ - type: spearman_cosine
72
+ value: 0.6872396378196957
73
+ name: Spearman Cosine
74
+ - type: pearson_manhattan
75
+ value: 0.7086043588614903
76
+ name: Pearson Manhattan
77
+ - type: spearman_manhattan
78
+ value: 0.7136479613274518
79
+ name: Spearman Manhattan
80
+ - type: pearson_euclidean
81
+ value: 0.7084460037709435
82
+ name: Pearson Euclidean
83
+ - type: spearman_euclidean
84
+ value: 0.7128357831285198
85
+ name: Spearman Euclidean
86
+ - type: pearson_dot
87
+ value: 0.481902874304561
88
+ name: Pearson Dot
89
+ - type: spearman_dot
90
+ value: 0.46588918379526945
91
+ name: Spearman Dot
92
+ - type: pearson_max
93
+ value: 0.7086043588614903
94
+ name: Pearson Max
95
+ - type: spearman_max
96
+ value: 0.7136479613274518
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: 0.6925787246105148
107
+ name: Pearson Cosine
108
+ - type: spearman_cosine
109
+ value: 0.6859479129419207
110
+ name: Spearman Cosine
111
+ - type: pearson_manhattan
112
+ value: 0.7087290093387656
113
+ name: Pearson Manhattan
114
+ - type: spearman_manhattan
115
+ value: 0.7127968133455542
116
+ name: Spearman Manhattan
117
+ - type: pearson_euclidean
118
+ value: 0.7088805484816247
119
+ name: Pearson Euclidean
120
+ - type: spearman_euclidean
121
+ value: 0.7123606046721803
122
+ name: Spearman Euclidean
123
+ - type: pearson_dot
124
+ value: 0.4684333245586192
125
+ name: Pearson Dot
126
+ - type: spearman_dot
127
+ value: 0.45257836578849003
128
+ name: Spearman Dot
129
+ - type: pearson_max
130
+ value: 0.7088805484816247
131
+ name: Pearson Max
132
+ - type: spearman_max
133
+ value: 0.7127968133455542
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: 0.6876956481856266
144
+ name: Pearson Cosine
145
+ - type: spearman_cosine
146
+ value: 0.6814892249857147
147
+ name: Spearman Cosine
148
+ - type: pearson_manhattan
149
+ value: 0.7083882582081078
150
+ name: Pearson Manhattan
151
+ - type: spearman_manhattan
152
+ value: 0.7097524143994903
153
+ name: Spearman Manhattan
154
+ - type: pearson_euclidean
155
+ value: 0.7094190252305796
156
+ name: Pearson Euclidean
157
+ - type: spearman_euclidean
158
+ value: 0.7104287347206688
159
+ name: Spearman Euclidean
160
+ - type: pearson_dot
161
+ value: 0.4438925722484721
162
+ name: Pearson Dot
163
+ - type: spearman_dot
164
+ value: 0.4255299982188107
165
+ name: Spearman Dot
166
+ - type: pearson_max
167
+ value: 0.7094190252305796
168
+ name: Pearson Max
169
+ - type: spearman_max
170
+ value: 0.7104287347206688
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: 0.6708560165075523
181
+ name: Pearson Cosine
182
+ - type: spearman_cosine
183
+ value: 0.6669935075512006
184
+ name: Spearman Cosine
185
+ - type: pearson_manhattan
186
+ value: 0.7041961281711793
187
+ name: Pearson Manhattan
188
+ - type: spearman_manhattan
189
+ value: 0.7000807688296651
190
+ name: Spearman Manhattan
191
+ - type: pearson_euclidean
192
+ value: 0.7055061381768357
193
+ name: Pearson Euclidean
194
+ - type: spearman_euclidean
195
+ value: 0.7022686907818495
196
+ name: Spearman Euclidean
197
+ - type: pearson_dot
198
+ value: 0.37855771167572094
199
+ name: Pearson Dot
200
+ - type: spearman_dot
201
+ value: 0.35930717422088765
202
+ name: Spearman Dot
203
+ - type: pearson_max
204
+ value: 0.7055061381768357
205
+ name: Pearson Max
206
+ - type: spearman_max
207
+ value: 0.7022686907818495
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: 0.6533817775144477
218
+ name: Pearson Cosine
219
+ - type: spearman_cosine
220
+ value: 0.6523997361414113
221
+ name: Spearman Cosine
222
+ - type: pearson_manhattan
223
+ value: 0.6919834348567717
224
+ name: Pearson Manhattan
225
+ - type: spearman_manhattan
226
+ value: 0.6857245312336051
227
+ name: Spearman Manhattan
228
+ - type: pearson_euclidean
229
+ value: 0.6950438027503257
230
+ name: Pearson Euclidean
231
+ - type: spearman_euclidean
232
+ value: 0.6899151458827059
233
+ name: Spearman Euclidean
234
+ - type: pearson_dot
235
+ value: 0.33502302384042637
236
+ name: Pearson Dot
237
+ - type: spearman_dot
238
+ value: 0.3097469345046609
239
+ name: Spearman Dot
240
+ - type: pearson_max
241
+ value: 0.6950438027503257
242
+ name: Pearson Max
243
+ - type: spearman_max
244
+ value: 0.6899151458827059
245
+ name: Spearman Max
246
+ ---
247
+
248
+ # SentenceTransformer based on nomic-ai/nomic-embed-text-v1.5
249
+
250
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) 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:** [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) <!-- at revision b0753ae76394dd36bcfb912a46018088bca48be0 -->
257
+ - **Maximum Sequence Length:** 8192 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': 8192, 'do_lower_case': False}) with Transformer model: NomicBertModel
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-nomic-embed-text-v1.5-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 | 0.6945 |
347
+ | **spearman_cosine** | **0.6872** |
348
+ | pearson_manhattan | 0.7086 |
349
+ | spearman_manhattan | 0.7136 |
350
+ | pearson_euclidean | 0.7084 |
351
+ | spearman_euclidean | 0.7128 |
352
+ | pearson_dot | 0.4819 |
353
+ | spearman_dot | 0.4659 |
354
+ | pearson_max | 0.7086 |
355
+ | spearman_max | 0.7136 |
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 | 0.6926 |
364
+ | **spearman_cosine** | **0.6859** |
365
+ | pearson_manhattan | 0.7087 |
366
+ | spearman_manhattan | 0.7128 |
367
+ | pearson_euclidean | 0.7089 |
368
+ | spearman_euclidean | 0.7124 |
369
+ | pearson_dot | 0.4684 |
370
+ | spearman_dot | 0.4526 |
371
+ | pearson_max | 0.7089 |
372
+ | spearman_max | 0.7128 |
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 | 0.6877 |
381
+ | **spearman_cosine** | **0.6815** |
382
+ | pearson_manhattan | 0.7084 |
383
+ | spearman_manhattan | 0.7098 |
384
+ | pearson_euclidean | 0.7094 |
385
+ | spearman_euclidean | 0.7104 |
386
+ | pearson_dot | 0.4439 |
387
+ | spearman_dot | 0.4255 |
388
+ | pearson_max | 0.7094 |
389
+ | spearman_max | 0.7104 |
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 | 0.6709 |
398
+ | **spearman_cosine** | **0.667** |
399
+ | pearson_manhattan | 0.7042 |
400
+ | spearman_manhattan | 0.7001 |
401
+ | pearson_euclidean | 0.7055 |
402
+ | spearman_euclidean | 0.7023 |
403
+ | pearson_dot | 0.3786 |
404
+ | spearman_dot | 0.3593 |
405
+ | pearson_max | 0.7055 |
406
+ | spearman_max | 0.7023 |
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 | 0.6534 |
415
+ | **spearman_cosine** | **0.6524** |
416
+ | pearson_manhattan | 0.692 |
417
+ | spearman_manhattan | 0.6857 |
418
+ | pearson_euclidean | 0.695 |
419
+ | spearman_euclidean | 0.6899 |
420
+ | pearson_dot | 0.335 |
421
+ | spearman_dot | 0.3097 |
422
+ | pearson_max | 0.695 |
423
+ | spearman_max | 0.6899 |
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: 7 tokens</li><li>mean: 15.18 tokens</li><li>max: 80 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 18.53 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 17.8 tokens</li><li>max: 53 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: 6 tokens</li><li>mean: 26.43 tokens</li><li>max: 94 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.37 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.7 tokens</li><li>max: 54 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`: 24
523
+ - `per_device_eval_batch_size`: 24
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`: 24
537
+ - `per_device_eval_batch_size`: 24
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
+ | 0.0043 | 100 | 10.0627 | - | - | - | - | - |
647
+ | 0.0086 | 200 | 8.2355 | - | - | - | - | - |
648
+ | 0.0129 | 300 | 6.7233 | - | - | - | - | - |
649
+ | 0.0172 | 400 | 6.5832 | - | - | - | - | - |
650
+ | 0.0215 | 500 | 6.7512 | - | - | - | - | - |
651
+ | 0.0258 | 600 | 6.7634 | - | - | - | - | - |
652
+ | 0.0301 | 700 | 6.5592 | - | - | - | - | - |
653
+ | 0.0344 | 800 | 5.0689 | - | - | - | - | - |
654
+ | 0.0387 | 900 | 4.7079 | - | - | - | - | - |
655
+ | 0.0430 | 1000 | 4.6359 | - | - | - | - | - |
656
+ | 0.0473 | 1100 | 4.4513 | - | - | - | - | - |
657
+ | 0.0516 | 1200 | 4.2328 | - | - | - | - | - |
658
+ | 0.0559 | 1300 | 3.7454 | - | - | - | - | - |
659
+ | 0.0602 | 1400 | 3.9198 | - | - | - | - | - |
660
+ | 0.0645 | 1500 | 4.0727 | - | - | - | - | - |
661
+ | 0.0688 | 1600 | 3.8923 | - | - | - | - | - |
662
+ | 0.0731 | 1700 | 3.8137 | - | - | - | - | - |
663
+ | 0.0774 | 1800 | 4.1512 | - | - | - | - | - |
664
+ | 0.0817 | 1900 | 4.1304 | - | - | - | - | - |
665
+ | 0.0860 | 2000 | 4.0195 | - | - | - | - | - |
666
+ | 0.0903 | 2100 | 3.6836 | - | - | - | - | - |
667
+ | 0.0946 | 2200 | 2.9968 | - | - | - | - | - |
668
+ | 0.0990 | 2300 | 2.8909 | - | - | - | - | - |
669
+ | 0.1033 | 2400 | 3.0884 | - | - | - | - | - |
670
+ | 0.1076 | 2500 | 3.3081 | - | - | - | - | - |
671
+ | 0.1119 | 2600 | 3.6266 | - | - | - | - | - |
672
+ | 0.1162 | 2700 | 4.3754 | - | - | - | - | - |
673
+ | 0.1205 | 2800 | 4.0218 | - | - | - | - | - |
674
+ | 0.1248 | 2900 | 3.7167 | - | - | - | - | - |
675
+ | 0.1291 | 3000 | 3.4815 | - | - | - | - | - |
676
+ | 0.1334 | 3100 | 3.6446 | - | - | - | - | - |
677
+ | 0.1377 | 3200 | 3.44 | - | - | - | - | - |
678
+ | 0.1420 | 3300 | 3.6725 | - | - | - | - | - |
679
+ | 0.1463 | 3400 | 3.4699 | - | - | - | - | - |
680
+ | 0.1506 | 3500 | 3.076 | - | - | - | - | - |
681
+ | 0.1549 | 3600 | 3.1179 | - | - | - | - | - |
682
+ | 0.1592 | 3700 | 3.1704 | - | - | - | - | - |
683
+ | 0.1635 | 3800 | 3.4614 | - | - | - | - | - |
684
+ | 0.1678 | 3900 | 4.1157 | - | - | - | - | - |
685
+ | 0.1721 | 4000 | 4.1584 | - | - | - | - | - |
686
+ | 0.1764 | 4100 | 4.5602 | - | - | - | - | - |
687
+ | 0.1807 | 4200 | 3.6875 | - | - | - | - | - |
688
+ | 0.1850 | 4300 | 4.1521 | - | - | - | - | - |
689
+ | 0.1893 | 4400 | 3.5475 | - | - | - | - | - |
690
+ | 0.1936 | 4500 | 3.4036 | - | - | - | - | - |
691
+ | 0.1979 | 4600 | 3.0564 | - | - | - | - | - |
692
+ | 0.2022 | 4700 | 3.7761 | - | - | - | - | - |
693
+ | 0.2065 | 4800 | 3.6857 | - | - | - | - | - |
694
+ | 0.2108 | 4900 | 3.3534 | - | - | - | - | - |
695
+ | 0.2151 | 5000 | 4.1137 | - | - | - | - | - |
696
+ | 0.2194 | 5100 | 3.5239 | - | - | - | - | - |
697
+ | 0.2237 | 5200 | 4.1297 | - | - | - | - | - |
698
+ | 0.2280 | 5300 | 3.5339 | - | - | - | - | - |
699
+ | 0.2323 | 5400 | 3.9294 | - | - | - | - | - |
700
+ | 0.2366 | 5500 | 3.717 | - | - | - | - | - |
701
+ | 0.2409 | 5600 | 3.3346 | - | - | - | - | - |
702
+ | 0.2452 | 5700 | 4.0495 | - | - | - | - | - |
703
+ | 0.2495 | 5800 | 3.7869 | - | - | - | - | - |
704
+ | 0.2538 | 5900 | 3.9533 | - | - | - | - | - |
705
+ | 0.2581 | 6000 | 4.1135 | - | - | - | - | - |
706
+ | 0.2624 | 6100 | 3.6655 | - | - | - | - | - |
707
+ | 0.2667 | 6200 | 3.9111 | - | - | - | - | - |
708
+ | 0.2710 | 6300 | 3.8582 | - | - | - | - | - |
709
+ | 0.2753 | 6400 | 3.7712 | - | - | - | - | - |
710
+ | 0.2796 | 6500 | 3.6536 | - | - | - | - | - |
711
+ | 0.2839 | 6600 | 3.4516 | - | - | - | - | - |
712
+ | 0.2882 | 6700 | 3.7151 | - | - | - | - | - |
713
+ | 0.2925 | 6800 | 3.7659 | - | - | - | - | - |
714
+ | 0.2969 | 6900 | 3.3159 | - | - | - | - | - |
715
+ | 0.3012 | 7000 | 3.5753 | - | - | - | - | - |
716
+ | 0.3055 | 7100 | 4.2095 | - | - | - | - | - |
717
+ | 0.3098 | 7200 | 3.718 | - | - | - | - | - |
718
+ | 0.3141 | 7300 | 4.0709 | - | - | - | - | - |
719
+ | 0.3184 | 7400 | 3.8079 | - | - | - | - | - |
720
+ | 0.3227 | 7500 | 3.3735 | - | - | - | - | - |
721
+ | 0.3270 | 7600 | 3.7303 | - | - | - | - | - |
722
+ | 0.3313 | 7700 | 3.2693 | - | - | - | - | - |
723
+ | 0.3356 | 7800 | 3.6564 | - | - | - | - | - |
724
+ | 0.3399 | 7900 | 3.6702 | - | - | - | - | - |
725
+ | 0.3442 | 8000 | 3.7274 | - | - | - | - | - |
726
+ | 0.3485 | 8100 | 3.8536 | - | - | - | - | - |
727
+ | 0.3528 | 8200 | 3.9516 | - | - | - | - | - |
728
+ | 0.3571 | 8300 | 3.7351 | - | - | - | - | - |
729
+ | 0.3614 | 8400 | 3.649 | - | - | - | - | - |
730
+ | 0.3657 | 8500 | 3.5913 | - | - | - | - | - |
731
+ | 0.3700 | 8600 | 3.7733 | - | - | - | - | - |
732
+ | 0.3743 | 8700 | 3.6359 | - | - | - | - | - |
733
+ | 0.3786 | 8800 | 4.2983 | - | - | - | - | - |
734
+ | 0.3829 | 8900 | 3.6692 | - | - | - | - | - |
735
+ | 0.3872 | 9000 | 3.7309 | - | - | - | - | - |
736
+ | 0.3915 | 9100 | 3.8886 | - | - | - | - | - |
737
+ | 0.3958 | 9200 | 3.8999 | - | - | - | - | - |
738
+ | 0.4001 | 9300 | 3.5528 | - | - | - | - | - |
739
+ | 0.4044 | 9400 | 3.6309 | - | - | - | - | - |
740
+ | 0.4087 | 9500 | 4.2475 | - | - | - | - | - |
741
+ | 0.4130 | 9600 | 3.793 | - | - | - | - | - |
742
+ | 0.4173 | 9700 | 3.6575 | - | - | - | - | - |
743
+ | 0.4216 | 9800 | 3.84 | - | - | - | - | - |
744
+ | 0.4259 | 9900 | 3.3721 | - | - | - | - | - |
745
+ | 0.4302 | 10000 | 4.3743 | - | - | - | - | - |
746
+ | 0.4345 | 10100 | 3.5054 | - | - | - | - | - |
747
+ | 0.4388 | 10200 | 3.54 | - | - | - | - | - |
748
+ | 0.4431 | 10300 | 3.6197 | - | - | - | - | - |
749
+ | 0.4474 | 10400 | 3.7567 | - | - | - | - | - |
750
+ | 0.4517 | 10500 | 3.9814 | - | - | - | - | - |
751
+ | 0.4560 | 10600 | 3.6277 | - | - | - | - | - |
752
+ | 0.4603 | 10700 | 3.5071 | - | - | - | - | - |
753
+ | 0.4646 | 10800 | 3.8348 | - | - | - | - | - |
754
+ | 0.4689 | 10900 | 3.8674 | - | - | - | - | - |
755
+ | 0.4732 | 11000 | 3.0325 | - | - | - | - | - |
756
+ | 0.4775 | 11100 | 3.7262 | - | - | - | - | - |
757
+ | 0.4818 | 11200 | 3.6921 | - | - | - | - | - |
758
+ | 0.4861 | 11300 | 3.4946 | - | - | - | - | - |
759
+ | 0.4904 | 11400 | 3.7541 | - | - | - | - | - |
760
+ | 0.4948 | 11500 | 3.6751 | - | - | - | - | - |
761
+ | 0.4991 | 11600 | 3.8765 | - | - | - | - | - |
762
+ | 0.5034 | 11700 | 3.5058 | - | - | - | - | - |
763
+ | 0.5077 | 11800 | 3.5135 | - | - | - | - | - |
764
+ | 0.5120 | 11900 | 3.8052 | - | - | - | - | - |
765
+ | 0.5163 | 12000 | 3.3015 | - | - | - | - | - |
766
+ | 0.5206 | 12100 | 3.5389 | - | - | - | - | - |
767
+ | 0.5249 | 12200 | 3.5226 | - | - | - | - | - |
768
+ | 0.5292 | 12300 | 3.6715 | - | - | - | - | - |
769
+ | 0.5335 | 12400 | 3.2256 | - | - | - | - | - |
770
+ | 0.5378 | 12500 | 3.3447 | - | - | - | - | - |
771
+ | 0.5421 | 12600 | 3.6315 | - | - | - | - | - |
772
+ | 0.5464 | 12700 | 3.8674 | - | - | - | - | - |
773
+ | 0.5507 | 12800 | 3.4066 | - | - | - | - | - |
774
+ | 0.5550 | 12900 | 3.7356 | - | - | - | - | - |
775
+ | 0.5593 | 13000 | 3.5742 | - | - | - | - | - |
776
+ | 0.5636 | 13100 | 3.7676 | - | - | - | - | - |
777
+ | 0.5679 | 13200 | 3.7907 | - | - | - | - | - |
778
+ | 0.5722 | 13300 | 3.8089 | - | - | - | - | - |
779
+ | 0.5765 | 13400 | 3.4742 | - | - | - | - | - |
780
+ | 0.5808 | 13500 | 3.6536 | - | - | - | - | - |
781
+ | 0.5851 | 13600 | 3.7736 | - | - | - | - | - |
782
+ | 0.5894 | 13700 | 3.9072 | - | - | - | - | - |
783
+ | 0.5937 | 13800 | 3.7386 | - | - | - | - | - |
784
+ | 0.5980 | 13900 | 3.3387 | - | - | - | - | - |
785
+ | 0.6023 | 14000 | 3.5509 | - | - | - | - | - |
786
+ | 0.6066 | 14100 | 3.7056 | - | - | - | - | - |
787
+ | 0.6109 | 14200 | 3.7283 | - | - | - | - | - |
788
+ | 0.6152 | 14300 | 3.7301 | - | - | - | - | - |
789
+ | 0.6195 | 14400 | 3.8027 | - | - | - | - | - |
790
+ | 0.6238 | 14500 | 3.5606 | - | - | - | - | - |
791
+ | 0.6281 | 14600 | 3.9467 | - | - | - | - | - |
792
+ | 0.6324 | 14700 | 3.3394 | - | - | - | - | - |
793
+ | 0.6367 | 14800 | 4.1254 | - | - | - | - | - |
794
+ | 0.6410 | 14900 | 3.7121 | - | - | - | - | - |
795
+ | 0.6453 | 15000 | 3.9167 | - | - | - | - | - |
796
+ | 0.6496 | 15100 | 3.8084 | - | - | - | - | - |
797
+ | 0.6539 | 15200 | 3.7794 | - | - | - | - | - |
798
+ | 0.6582 | 15300 | 3.7664 | - | - | - | - | - |
799
+ | 0.6625 | 15400 | 3.4378 | - | - | - | - | - |
800
+ | 0.6668 | 15500 | 3.6632 | - | - | - | - | - |
801
+ | 0.6711 | 15600 | 3.8493 | - | - | - | - | - |
802
+ | 0.6754 | 15700 | 4.1475 | - | - | - | - | - |
803
+ | 0.6797 | 15800 | 3.5782 | - | - | - | - | - |
804
+ | 0.6840 | 15900 | 3.4341 | - | - | - | - | - |
805
+ | 0.6883 | 16000 | 3.3295 | - | - | - | - | - |
806
+ | 0.6927 | 16100 | 3.8165 | - | - | - | - | - |
807
+ | 0.6970 | 16200 | 3.9702 | - | - | - | - | - |
808
+ | 0.7013 | 16300 | 3.6555 | - | - | - | - | - |
809
+ | 0.7056 | 16400 | 3.6946 | - | - | - | - | - |
810
+ | 0.7099 | 16500 | 3.8027 | - | - | - | - | - |
811
+ | 0.7142 | 16600 | 3.4523 | - | - | - | - | - |
812
+ | 0.7185 | 16700 | 3.461 | - | - | - | - | - |
813
+ | 0.7228 | 16800 | 3.4403 | - | - | - | - | - |
814
+ | 0.7271 | 16900 | 3.6398 | - | - | - | - | - |
815
+ | 0.7314 | 17000 | 3.8443 | - | - | - | - | - |
816
+ | 0.7357 | 17100 | 3.6012 | - | - | - | - | - |
817
+ | 0.7400 | 17200 | 3.6645 | - | - | - | - | - |
818
+ | 0.7443 | 17300 | 3.4899 | - | - | - | - | - |
819
+ | 0.7486 | 17400 | 3.7186 | - | - | - | - | - |
820
+ | 0.7529 | 17500 | 3.6199 | - | - | - | - | - |
821
+ | 0.7572 | 17600 | 4.4274 | - | - | - | - | - |
822
+ | 0.7615 | 17700 | 4.0262 | - | - | - | - | - |
823
+ | 0.7658 | 17800 | 3.9325 | - | - | - | - | - |
824
+ | 0.7701 | 17900 | 3.6338 | - | - | - | - | - |
825
+ | 0.7744 | 18000 | 3.6136 | - | - | - | - | - |
826
+ | 0.7787 | 18100 | 3.4514 | - | - | - | - | - |
827
+ | 0.7830 | 18200 | 3.4427 | - | - | - | - | - |
828
+ | 0.7873 | 18300 | 3.3601 | - | - | - | - | - |
829
+ | 0.7916 | 18400 | 3.313 | - | - | - | - | - |
830
+ | 0.7959 | 18500 | 3.4062 | - | - | - | - | - |
831
+ | 0.8002 | 18600 | 3.098 | - | - | - | - | - |
832
+ | 0.8045 | 18700 | 3.183 | - | - | - | - | - |
833
+ | 0.8088 | 18800 | 3.1482 | - | - | - | - | - |
834
+ | 0.8131 | 18900 | 3.0122 | - | - | - | - | - |
835
+ | 0.8174 | 19000 | 3.0828 | - | - | - | - | - |
836
+ | 0.8217 | 19100 | 3.063 | - | - | - | - | - |
837
+ | 0.8260 | 19200 | 2.9688 | - | - | - | - | - |
838
+ | 0.8303 | 19300 | 3.0425 | - | - | - | - | - |
839
+ | 0.8346 | 19400 | 3.2018 | - | - | - | - | - |
840
+ | 0.8389 | 19500 | 2.9111 | - | - | - | - | - |
841
+ | 0.8432 | 19600 | 2.9516 | - | - | - | - | - |
842
+ | 0.8475 | 19700 | 2.9115 | - | - | - | - | - |
843
+ | 0.8518 | 19800 | 2.9323 | - | - | - | - | - |
844
+ | 0.8561 | 19900 | 2.8753 | - | - | - | - | - |
845
+ | 0.8604 | 20000 | 2.8344 | - | - | - | - | - |
846
+ | 0.8647 | 20100 | 2.7665 | - | - | - | - | - |
847
+ | 0.8690 | 20200 | 2.7732 | - | - | - | - | - |
848
+ | 0.8733 | 20300 | 2.8622 | - | - | - | - | - |
849
+ | 0.8776 | 20400 | 2.8749 | - | - | - | - | - |
850
+ | 0.8819 | 20500 | 2.8534 | - | - | - | - | - |
851
+ | 0.8863 | 20600 | 2.9254 | - | - | - | - | - |
852
+ | 0.8906 | 20700 | 2.7366 | - | - | - | - | - |
853
+ | 0.8949 | 20800 | 2.7287 | - | - | - | - | - |
854
+ | 0.8992 | 20900 | 2.9469 | - | - | - | - | - |
855
+ | 0.9035 | 21000 | 2.9052 | - | - | - | - | - |
856
+ | 0.9078 | 21100 | 2.7256 | - | - | - | - | - |
857
+ | 0.9121 | 21200 | 2.8469 | - | - | - | - | - |
858
+ | 0.9164 | 21300 | 2.6626 | - | - | - | - | - |
859
+ | 0.9207 | 21400 | 2.6796 | - | - | - | - | - |
860
+ | 0.9250 | 21500 | 2.6927 | - | - | - | - | - |
861
+ | 0.9293 | 21600 | 2.7125 | - | - | - | - | - |
862
+ | 0.9336 | 21700 | 2.6734 | - | - | - | - | - |
863
+ | 0.9379 | 21800 | 2.7199 | - | - | - | - | - |
864
+ | 0.9422 | 21900 | 2.6635 | - | - | - | - | - |
865
+ | 0.9465 | 22000 | 2.5218 | - | - | - | - | - |
866
+ | 0.9508 | 22100 | 2.7595 | - | - | - | - | - |
867
+ | 0.9551 | 22200 | 2.6821 | - | - | - | - | - |
868
+ | 0.9594 | 22300 | 2.6578 | - | - | - | - | - |
869
+ | 0.9637 | 22400 | 2.568 | - | - | - | - | - |
870
+ | 0.9680 | 22500 | 2.5527 | - | - | - | - | - |
871
+ | 0.9723 | 22600 | 2.6857 | - | - | - | - | - |
872
+ | 0.9766 | 22700 | 2.6637 | - | - | - | - | - |
873
+ | 0.9809 | 22800 | 2.6311 | - | - | - | - | - |
874
+ | 0.9852 | 22900 | 2.4635 | - | - | - | - | - |
875
+ | 0.9895 | 23000 | 2.6239 | - | - | - | - | - |
876
+ | 0.9938 | 23100 | 2.6873 | - | - | - | - | - |
877
+ | 0.9981 | 23200 | 2.5138 | - | - | - | - | - |
878
+ | 1.0 | 23244 | - | 0.6670 | 0.6815 | 0.6859 | 0.6524 | 0.6872 |
879
+
880
+ </details>
881
+
882
+ ### Framework Versions
883
+ - Python: 3.11.9
884
+ - Sentence Transformers: 3.0.1
885
+ - Transformers: 4.40.1
886
+ - PyTorch: 2.3.0+cu121
887
+ - Accelerate: 0.29.3
888
+ - Datasets: 2.19.0
889
+ - Tokenizers: 0.19.1
890
+
891
+ ## Citation
892
+
893
+ ### BibTeX
894
+
895
+ #### Sentence Transformers
896
+ ```bibtex
897
+ @inproceedings{reimers-2019-sentence-bert,
898
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
899
+ author = "Reimers, Nils and Gurevych, Iryna",
900
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
901
+ month = "11",
902
+ year = "2019",
903
+ publisher = "Association for Computational Linguistics",
904
+ url = "https://arxiv.org/abs/1908.10084",
905
+ }
906
+ ```
907
+
908
+ #### MatryoshkaLoss
909
+ ```bibtex
910
+ @misc{kusupati2024matryoshka,
911
+ title={Matryoshka Representation Learning},
912
+ 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},
913
+ year={2024},
914
+ eprint={2205.13147},
915
+ archivePrefix={arXiv},
916
+ primaryClass={cs.LG}
917
+ }
918
+ ```
919
+
920
+ #### MultipleNegativesRankingLoss
921
+ ```bibtex
922
+ @misc{henderson2017efficient,
923
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
924
+ 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},
925
+ year={2017},
926
+ eprint={1705.00652},
927
+ archivePrefix={arXiv},
928
+ primaryClass={cs.CL}
929
+ }
930
+ ```
931
+
932
+ <!--
933
+ ## Glossary
934
+
935
+ *Clearly define terms in order to be accessible across audiences.*
936
+ -->
937
+
938
+ <!--
939
+ ## Model Card Authors
940
+
941
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
942
+ -->
943
+
944
+ <!--
945
+ ## Model Card Contact
946
+
947
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
948
+ -->
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nomic-ai/nomic-embed-text-v1.5",
3
+ "activation_function": "swiglu",
4
+ "architectures": [
5
+ "NomicBertModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "nomic-ai/nomic-bert-2048--configuration_hf_nomic_bert.NomicBertConfig",
10
+ "AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
11
+ "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining"
12
+ },
13
+ "bos_token_id": null,
14
+ "causal": false,
15
+ "dense_seq_output": true,
16
+ "embd_pdrop": 0.0,
17
+ "eos_token_id": null,
18
+ "fused_bias_fc": true,
19
+ "fused_dropout_add_ln": true,
20
+ "initializer_range": 0.02,
21
+ "layer_norm_epsilon": 1e-12,
22
+ "max_trained_positions": 2048,
23
+ "mlp_fc1_bias": false,
24
+ "mlp_fc2_bias": false,
25
+ "model_type": "nomic_bert",
26
+ "n_embd": 768,
27
+ "n_head": 12,
28
+ "n_inner": 3072,
29
+ "n_layer": 12,
30
+ "n_positions": 8192,
31
+ "pad_vocab_size_multiple": 64,
32
+ "parallel_block": false,
33
+ "parallel_block_tied_norm": false,
34
+ "prenorm": false,
35
+ "qkv_proj_bias": false,
36
+ "reorder_and_upcast_attn": false,
37
+ "resid_pdrop": 0.0,
38
+ "rotary_emb_base": 1000,
39
+ "rotary_emb_fraction": 1.0,
40
+ "rotary_emb_interleaved": false,
41
+ "rotary_emb_scale_base": null,
42
+ "rotary_scaling_factor": null,
43
+ "scale_attn_by_inverse_layer_idx": false,
44
+ "scale_attn_weights": true,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.0,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.40.1",
52
+ "type_vocab_size": 2,
53
+ "use_cache": true,
54
+ "use_flash_attn": true,
55
+ "use_rms_norm": false,
56
+ "use_xentropy": true,
57
+ "vocab_size": 30528
58
+ }
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 sha256:4f364eab736622029e58b114f30517fc96b8cee8629453678c9036f44de6e88e
3
+ size 546938168
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": 8192,
3
+ "do_lower_case": false
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 8192,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff