Hugging Face's logo

ve88ifz2
/
mmlw-roberta-base-klej-dyk-v0.1

Sentence Similarity
sentence-transformers
Safetensors
English
roberta
feature-extraction
dataset_size:1K<n<10K
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
ve88ifz2 commited on
Commit
ba0354e
•
1 Parent(s): e482d2d

Add new SentenceTransformer model.

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +1072 -0
  3. config.json +28 -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 +51 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +64 -0
  11. unigram.json +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,1072 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: sdadas/mmlw-roberta-base
3
+ language:
4
+ - en
5
+ library_name: sentence-transformers
6
+ license: apache-2.0
7
+ metrics:
8
+ - cosine_accuracy@1
9
+ - cosine_accuracy@3
10
+ - cosine_accuracy@5
11
+ - cosine_accuracy@10
12
+ - cosine_precision@1
13
+ - cosine_precision@3
14
+ - cosine_precision@5
15
+ - cosine_precision@10
16
+ - cosine_recall@1
17
+ - cosine_recall@3
18
+ - cosine_recall@5
19
+ - cosine_recall@10
20
+ - cosine_ndcg@10
21
+ - cosine_mrr@10
22
+ - cosine_map@100
23
+ pipeline_tag: sentence-similarity
24
+ tags:
25
+ - sentence-transformers
26
+ - sentence-similarity
27
+ - feature-extraction
28
+ - dataset_size:1K<n<10K
29
+ - loss:MatryoshkaLoss
30
+ - loss:MultipleNegativesRankingLoss
31
+ widget:
32
+ - source_sentence: Żywot św. Stanisława
33
+ sentences:
34
+ - czym różni się Żywot św. Stanisława od Legendy św. Stanisława?
35
+ - w którym kraju w noc sylwestrową je się oliebollen?
36
+ - Pierwsze bloki mieszkalne powstały pod koniec lat 80.
37
+ - source_sentence: Herkules na rozstajach
38
+ sentences:
39
+ - jak zinterpretować wymowę obrazu Herkules na rozstajach?
40
+ - gdzie zginął przedwojenny minister Antoni Olszewski?
41
+ - kiedy konsekrowano katedrę św. Teresy z Avili w Požedze?
42
+ - source_sentence: gdzie rośnie bokkonia?
43
+ sentences:
44
+ - gdzie występuje rogownica szerokolistna?
45
+ - Ochrzcił w sierpniu 1982 ich syna księcia Wilhelma.
46
+ - Pośmiertnie został odznaczony Krzyżem Virtuti Militari.
47
+ - source_sentence: czym jest Kompas Sztuki?
48
+ sentences:
49
+ - ' Projekt Kompas Sztuki: Galeria m2 (m kwadrat).'
50
+ - 'Do rodzaju Caraipa zaliczanych jest ok. 55 gatunków:'
51
+ - kto jest aktualnym rekordzistą Chorwacji w skoku w dal?
52
+ - source_sentence: Dalsze losy relikwii
53
+ sentences:
54
+ - Losy relikwii świętego
55
+ - czemu gra The Saboteur wywołała wiele kontrowersji?
56
+ - kto jest pierwszym rosyjskim kierowcą wyścigowym startującym w Formule 1?
57
+ model-index:
58
+ - name: mmlw-roberta-base-klej-dyk-v0.1
59
+ results:
60
+ - task:
61
+ type: information-retrieval
62
+ name: Information Retrieval
63
+ dataset:
64
+ name: dim 768
65
+ type: dim_768
66
+ metrics:
67
+ - type: cosine_accuracy@1
68
+ value: 0.18990384615384615
69
+ name: Cosine Accuracy@1
70
+ - type: cosine_accuracy@3
71
+ value: 0.5865384615384616
72
+ name: Cosine Accuracy@3
73
+ - type: cosine_accuracy@5
74
+ value: 0.7692307692307693
75
+ name: Cosine Accuracy@5
76
+ - type: cosine_accuracy@10
77
+ value: 0.8533653846153846
78
+ name: Cosine Accuracy@10
79
+ - type: cosine_precision@1
80
+ value: 0.18990384615384615
81
+ name: Cosine Precision@1
82
+ - type: cosine_precision@3
83
+ value: 0.1955128205128205
84
+ name: Cosine Precision@3
85
+ - type: cosine_precision@5
86
+ value: 0.15384615384615383
87
+ name: Cosine Precision@5
88
+ - type: cosine_precision@10
89
+ value: 0.08533653846153846
90
+ name: Cosine Precision@10
91
+ - type: cosine_recall@1
92
+ value: 0.18990384615384615
93
+ name: Cosine Recall@1
94
+ - type: cosine_recall@3
95
+ value: 0.5865384615384616
96
+ name: Cosine Recall@3
97
+ - type: cosine_recall@5
98
+ value: 0.7692307692307693
99
+ name: Cosine Recall@5
100
+ - type: cosine_recall@10
101
+ value: 0.8533653846153846
102
+ name: Cosine Recall@10
103
+ - type: cosine_ndcg@10
104
+ value: 0.5204892782178483
105
+ name: Cosine Ndcg@10
106
+ - type: cosine_mrr@10
107
+ value: 0.4127814026251526
108
+ name: Cosine Mrr@10
109
+ - type: cosine_map@100
110
+ value: 0.418150211843158
111
+ name: Cosine Map@100
112
+ - task:
113
+ type: information-retrieval
114
+ name: Information Retrieval
115
+ dataset:
116
+ name: dim 512
117
+ type: dim_512
118
+ metrics:
119
+ - type: cosine_accuracy@1
120
+ value: 0.1875
121
+ name: Cosine Accuracy@1
122
+ - type: cosine_accuracy@3
123
+ value: 0.5889423076923077
124
+ name: Cosine Accuracy@3
125
+ - type: cosine_accuracy@5
126
+ value: 0.7596153846153846
127
+ name: Cosine Accuracy@5
128
+ - type: cosine_accuracy@10
129
+ value: 0.8629807692307693
130
+ name: Cosine Accuracy@10
131
+ - type: cosine_precision@1
132
+ value: 0.1875
133
+ name: Cosine Precision@1
134
+ - type: cosine_precision@3
135
+ value: 0.19631410256410253
136
+ name: Cosine Precision@3
137
+ - type: cosine_precision@5
138
+ value: 0.15192307692307688
139
+ name: Cosine Precision@5
140
+ - type: cosine_precision@10
141
+ value: 0.08629807692307694
142
+ name: Cosine Precision@10
143
+ - type: cosine_recall@1
144
+ value: 0.1875
145
+ name: Cosine Recall@1
146
+ - type: cosine_recall@3
147
+ value: 0.5889423076923077
148
+ name: Cosine Recall@3
149
+ - type: cosine_recall@5
150
+ value: 0.7596153846153846
151
+ name: Cosine Recall@5
152
+ - type: cosine_recall@10
153
+ value: 0.8629807692307693
154
+ name: Cosine Recall@10
155
+ - type: cosine_ndcg@10
156
+ value: 0.5204340563935984
157
+ name: Cosine Ndcg@10
158
+ - type: cosine_mrr@10
159
+ value: 0.4100885225885227
160
+ name: Cosine Mrr@10
161
+ - type: cosine_map@100
162
+ value: 0.4147514658961434
163
+ name: Cosine Map@100
164
+ - task:
165
+ type: information-retrieval
166
+ name: Information Retrieval
167
+ dataset:
168
+ name: dim 256
169
+ type: dim_256
170
+ metrics:
171
+ - type: cosine_accuracy@1
172
+ value: 0.19471153846153846
173
+ name: Cosine Accuracy@1
174
+ - type: cosine_accuracy@3
175
+ value: 0.5649038461538461
176
+ name: Cosine Accuracy@3
177
+ - type: cosine_accuracy@5
178
+ value: 0.7451923076923077
179
+ name: Cosine Accuracy@5
180
+ - type: cosine_accuracy@10
181
+ value: 0.8461538461538461
182
+ name: Cosine Accuracy@10
183
+ - type: cosine_precision@1
184
+ value: 0.19471153846153846
185
+ name: Cosine Precision@1
186
+ - type: cosine_precision@3
187
+ value: 0.18830128205128205
188
+ name: Cosine Precision@3
189
+ - type: cosine_precision@5
190
+ value: 0.1490384615384615
191
+ name: Cosine Precision@5
192
+ - type: cosine_precision@10
193
+ value: 0.08461538461538462
194
+ name: Cosine Precision@10
195
+ - type: cosine_recall@1
196
+ value: 0.19471153846153846
197
+ name: Cosine Recall@1
198
+ - type: cosine_recall@3
199
+ value: 0.5649038461538461
200
+ name: Cosine Recall@3
201
+ - type: cosine_recall@5
202
+ value: 0.7451923076923077
203
+ name: Cosine Recall@5
204
+ - type: cosine_recall@10
205
+ value: 0.8461538461538461
206
+ name: Cosine Recall@10
207
+ - type: cosine_ndcg@10
208
+ value: 0.5144907264607753
209
+ name: Cosine Ndcg@10
210
+ - type: cosine_mrr@10
211
+ value: 0.4078373015873016
212
+ name: Cosine Mrr@10
213
+ - type: cosine_map@100
214
+ value: 0.413093644747221
215
+ name: Cosine Map@100
216
+ - task:
217
+ type: information-retrieval
218
+ name: Information Retrieval
219
+ dataset:
220
+ name: dim 128
221
+ type: dim_128
222
+ metrics:
223
+ - type: cosine_accuracy@1
224
+ value: 0.18269230769230768
225
+ name: Cosine Accuracy@1
226
+ - type: cosine_accuracy@3
227
+ value: 0.5192307692307693
228
+ name: Cosine Accuracy@3
229
+ - type: cosine_accuracy@5
230
+ value: 0.7163461538461539
231
+ name: Cosine Accuracy@5
232
+ - type: cosine_accuracy@10
233
+ value: 0.8293269230769231
234
+ name: Cosine Accuracy@10
235
+ - type: cosine_precision@1
236
+ value: 0.18269230769230768
237
+ name: Cosine Precision@1
238
+ - type: cosine_precision@3
239
+ value: 0.17307692307692307
240
+ name: Cosine Precision@3
241
+ - type: cosine_precision@5
242
+ value: 0.14326923076923076
243
+ name: Cosine Precision@5
244
+ - type: cosine_precision@10
245
+ value: 0.08293269230769229
246
+ name: Cosine Precision@10
247
+ - type: cosine_recall@1
248
+ value: 0.18269230769230768
249
+ name: Cosine Recall@1
250
+ - type: cosine_recall@3
251
+ value: 0.5192307692307693
252
+ name: Cosine Recall@3
253
+ - type: cosine_recall@5
254
+ value: 0.7163461538461539
255
+ name: Cosine Recall@5
256
+ - type: cosine_recall@10
257
+ value: 0.8293269230769231
258
+ name: Cosine Recall@10
259
+ - type: cosine_ndcg@10
260
+ value: 0.4955346842225082
261
+ name: Cosine Ndcg@10
262
+ - type: cosine_mrr@10
263
+ value: 0.38889652014651993
264
+ name: Cosine Mrr@10
265
+ - type: cosine_map@100
266
+ value: 0.39396452853345754
267
+ name: Cosine Map@100
268
+ - task:
269
+ type: information-retrieval
270
+ name: Information Retrieval
271
+ dataset:
272
+ name: dim 64
273
+ type: dim_64
274
+ metrics:
275
+ - type: cosine_accuracy@1
276
+ value: 0.1778846153846154
277
+ name: Cosine Accuracy@1
278
+ - type: cosine_accuracy@3
279
+ value: 0.4831730769230769
280
+ name: Cosine Accuracy@3
281
+ - type: cosine_accuracy@5
282
+ value: 0.6514423076923077
283
+ name: Cosine Accuracy@5
284
+ - type: cosine_accuracy@10
285
+ value: 0.7740384615384616
286
+ name: Cosine Accuracy@10
287
+ - type: cosine_precision@1
288
+ value: 0.1778846153846154
289
+ name: Cosine Precision@1
290
+ - type: cosine_precision@3
291
+ value: 0.16105769230769232
292
+ name: Cosine Precision@3
293
+ - type: cosine_precision@5
294
+ value: 0.13028846153846152
295
+ name: Cosine Precision@5
296
+ - type: cosine_precision@10
297
+ value: 0.07740384615384614
298
+ name: Cosine Precision@10
299
+ - type: cosine_recall@1
300
+ value: 0.1778846153846154
301
+ name: Cosine Recall@1
302
+ - type: cosine_recall@3
303
+ value: 0.4831730769230769
304
+ name: Cosine Recall@3
305
+ - type: cosine_recall@5
306
+ value: 0.6514423076923077
307
+ name: Cosine Recall@5
308
+ - type: cosine_recall@10
309
+ value: 0.7740384615384616
310
+ name: Cosine Recall@10
311
+ - type: cosine_ndcg@10
312
+ value: 0.4639263641936578
313
+ name: Cosine Ndcg@10
314
+ - type: cosine_mrr@10
315
+ value: 0.36540083180708166
316
+ name: Cosine Mrr@10
317
+ - type: cosine_map@100
318
+ value: 0.3728380879103276
319
+ name: Cosine Map@100
320
+ ---
321
+
322
+ # mmlw-roberta-base-klej-dyk-v0.1
323
+
324
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sdadas/mmlw-roberta-base](https://huggingface.co/sdadas/mmlw-roberta-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
325
+
326
+ ## Model Details
327
+
328
+ ### Model Description
329
+ - **Model Type:** Sentence Transformer
330
+ - **Base model:** [sdadas/mmlw-roberta-base](https://huggingface.co/sdadas/mmlw-roberta-base) <!-- at revision 57e19d8314b983137ebe25ce734880af0dc98a9e -->
331
+ - **Maximum Sequence Length:** 512 tokens
332
+ - **Output Dimensionality:** 768 tokens
333
+ - **Similarity Function:** Cosine Similarity
334
+ <!-- - **Training Dataset:** Unknown -->
335
+ - **Language:** en
336
+ - **License:** apache-2.0
337
+
338
+ ### Model Sources
339
+
340
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
341
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
342
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
343
+
344
+ ### Full Model Architecture
345
+
346
+ ```
347
+ SentenceTransformer(
348
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
349
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
350
+ )
351
+ ```
352
+
353
+ ## Usage
354
+
355
+ ### Direct Usage (Sentence Transformers)
356
+
357
+ First install the Sentence Transformers library:
358
+
359
+ ```bash
360
+ pip install -U sentence-transformers
361
+ ```
362
+
363
+ Then you can load this model and run inference.
364
+ ```python
365
+ from sentence_transformers import SentenceTransformer
366
+
367
+ # Download from the 🤗 Hub
368
+ model = SentenceTransformer("sentence_transformers_model_id")
369
+ # Run inference
370
+ sentences = [
371
+ 'Dalsze losy relikwii',
372
+ 'Losy relikwii świętego',
373
+ 'czemu gra The Saboteur wywołała wiele kontrowersji?',
374
+ ]
375
+ embeddings = model.encode(sentences)
376
+ print(embeddings.shape)
377
+ # [3, 768]
378
+
379
+ # Get the similarity scores for the embeddings
380
+ similarities = model.similarity(embeddings, embeddings)
381
+ print(similarities.shape)
382
+ # [3, 3]
383
+ ```
384
+
385
+ <!--
386
+ ### Direct Usage (Transformers)
387
+
388
+ <details><summary>Click to see the direct usage in Transformers</summary>
389
+
390
+ </details>
391
+ -->
392
+
393
+ <!--
394
+ ### Downstream Usage (Sentence Transformers)
395
+
396
+ You can finetune this model on your own dataset.
397
+
398
+ <details><summary>Click to expand</summary>
399
+
400
+ </details>
401
+ -->
402
+
403
+ <!--
404
+ ### Out-of-Scope Use
405
+
406
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
407
+ -->
408
+
409
+ ## Evaluation
410
+
411
+ ### Metrics
412
+
413
+ #### Information Retrieval
414
+ * Dataset: `dim_768`
415
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
416
+
417
+ | Metric | Value |
418
+ |:--------------------|:-----------|
419
+ | cosine_accuracy@1 | 0.1899 |
420
+ | cosine_accuracy@3 | 0.5865 |
421
+ | cosine_accuracy@5 | 0.7692 |
422
+ | cosine_accuracy@10 | 0.8534 |
423
+ | cosine_precision@1 | 0.1899 |
424
+ | cosine_precision@3 | 0.1955 |
425
+ | cosine_precision@5 | 0.1538 |
426
+ | cosine_precision@10 | 0.0853 |
427
+ | cosine_recall@1 | 0.1899 |
428
+ | cosine_recall@3 | 0.5865 |
429
+ | cosine_recall@5 | 0.7692 |
430
+ | cosine_recall@10 | 0.8534 |
431
+ | cosine_ndcg@10 | 0.5205 |
432
+ | cosine_mrr@10 | 0.4128 |
433
+ | **cosine_map@100** | **0.4182** |
434
+
435
+ #### Information Retrieval
436
+ * Dataset: `dim_512`
437
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
438
+
439
+ | Metric | Value |
440
+ |:--------------------|:-----------|
441
+ | cosine_accuracy@1 | 0.1875 |
442
+ | cosine_accuracy@3 | 0.5889 |
443
+ | cosine_accuracy@5 | 0.7596 |
444
+ | cosine_accuracy@10 | 0.863 |
445
+ | cosine_precision@1 | 0.1875 |
446
+ | cosine_precision@3 | 0.1963 |
447
+ | cosine_precision@5 | 0.1519 |
448
+ | cosine_precision@10 | 0.0863 |
449
+ | cosine_recall@1 | 0.1875 |
450
+ | cosine_recall@3 | 0.5889 |
451
+ | cosine_recall@5 | 0.7596 |
452
+ | cosine_recall@10 | 0.863 |
453
+ | cosine_ndcg@10 | 0.5204 |
454
+ | cosine_mrr@10 | 0.4101 |
455
+ | **cosine_map@100** | **0.4148** |
456
+
457
+ #### Information Retrieval
458
+ * Dataset: `dim_256`
459
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
460
+
461
+ | Metric | Value |
462
+ |:--------------------|:-----------|
463
+ | cosine_accuracy@1 | 0.1947 |
464
+ | cosine_accuracy@3 | 0.5649 |
465
+ | cosine_accuracy@5 | 0.7452 |
466
+ | cosine_accuracy@10 | 0.8462 |
467
+ | cosine_precision@1 | 0.1947 |
468
+ | cosine_precision@3 | 0.1883 |
469
+ | cosine_precision@5 | 0.149 |
470
+ | cosine_precision@10 | 0.0846 |
471
+ | cosine_recall@1 | 0.1947 |
472
+ | cosine_recall@3 | 0.5649 |
473
+ | cosine_recall@5 | 0.7452 |
474
+ | cosine_recall@10 | 0.8462 |
475
+ | cosine_ndcg@10 | 0.5145 |
476
+ | cosine_mrr@10 | 0.4078 |
477
+ | **cosine_map@100** | **0.4131** |
478
+
479
+ #### Information Retrieval
480
+ * Dataset: `dim_128`
481
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
482
+
483
+ | Metric | Value |
484
+ |:--------------------|:----------|
485
+ | cosine_accuracy@1 | 0.1827 |
486
+ | cosine_accuracy@3 | 0.5192 |
487
+ | cosine_accuracy@5 | 0.7163 |
488
+ | cosine_accuracy@10 | 0.8293 |
489
+ | cosine_precision@1 | 0.1827 |
490
+ | cosine_precision@3 | 0.1731 |
491
+ | cosine_precision@5 | 0.1433 |
492
+ | cosine_precision@10 | 0.0829 |
493
+ | cosine_recall@1 | 0.1827 |
494
+ | cosine_recall@3 | 0.5192 |
495
+ | cosine_recall@5 | 0.7163 |
496
+ | cosine_recall@10 | 0.8293 |
497
+ | cosine_ndcg@10 | 0.4955 |
498
+ | cosine_mrr@10 | 0.3889 |
499
+ | **cosine_map@100** | **0.394** |
500
+
501
+ #### Information Retrieval
502
+ * Dataset: `dim_64`
503
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
504
+
505
+ | Metric | Value |
506
+ |:--------------------|:-----------|
507
+ | cosine_accuracy@1 | 0.1779 |
508
+ | cosine_accuracy@3 | 0.4832 |
509
+ | cosine_accuracy@5 | 0.6514 |
510
+ | cosine_accuracy@10 | 0.774 |
511
+ | cosine_precision@1 | 0.1779 |
512
+ | cosine_precision@3 | 0.1611 |
513
+ | cosine_precision@5 | 0.1303 |
514
+ | cosine_precision@10 | 0.0774 |
515
+ | cosine_recall@1 | 0.1779 |
516
+ | cosine_recall@3 | 0.4832 |
517
+ | cosine_recall@5 | 0.6514 |
518
+ | cosine_recall@10 | 0.774 |
519
+ | cosine_ndcg@10 | 0.4639 |
520
+ | cosine_mrr@10 | 0.3654 |
521
+ | **cosine_map@100** | **0.3728** |
522
+
523
+ <!--
524
+ ## Bias, Risks and Limitations
525
+
526
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
527
+ -->
528
+
529
+ <!--
530
+ ### Recommendations
531
+
532
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
533
+ -->
534
+
535
+ ## Training Details
536
+
537
+ ### Training Dataset
538
+
539
+ #### Unnamed Dataset
540
+
541
+
542
+ * Size: 3,738 training samples
543
+ * Columns: <code>positive</code> and <code>anchor</code>
544
+ * Approximate statistics based on the first 1000 samples:
545
+ | | positive | anchor |
546
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
547
+ | type | string | string |
548
+ | details | <ul><li>min: 5 tokens</li><li>mean: 50.1 tokens</li><li>max: 466 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.62 tokens</li><li>max: 49 tokens</li></ul> |
549
+ * Samples:
550
+ | positive | anchor |
551
+ |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------|
552
+ | <code>Zespół Blaua (zespół Jabsa, ang. Blau syndrome, BS) – rzadka choroba genetyczna o dziedziczeniu autosomalnym dominującym, charakteryzująca się ziarniniakowym zapaleniem stawów o wczesnym początku, zapaleniem jagodówki (uveitis) i wysypką skórną, a także kamptodaktylią.</code> | <code>jakie choroby genetyczne dziedziczą się autosomalnie dominująco?</code> |
553
+ | <code>Gorgippia Gorgippia – starożytne miasto bosporańskie nad Morzem Czarnym, którego pozostałości znajdują się obecnie pod współczesną zabudową centralnej części miasta Anapa w Kraju Krasnodarskim w Rosji.</code> | <code>gdzie obecnie znajduje się starożytne miasto Gorgippia?</code> |
554
+ | <code>Ulubionym dystansem Rücker było 400 metrów i to na nim notowała największe indywidualne sukcesy : srebrny medal Mistrzostw Europy juniorów w lekkoatletyce (Saloniki 1991) 6. miejsce w Pucharze Świata w Lekkoatletyce (Hawana 1992) 5. miejsce na Mistrzostwach Europy w Lekkoatletyce (Helsinki 1994) srebro podczas Mistrzostw Świata w Lekkoatletyce (Sewilla 1999) złota medalistka mistrzostw Niemiec Duże sukcesy odnosiła także w sztafecie 4 x 400 metrów : złoto Mistrzostw Europy juniorów w lekkoatletyce (Varaždin 1989) złoty medal Mistrzostw Europy juniorów w lekkoatletyce (Saloniki 1991) brąz na Mistrzostwach Europy w Lekkoatletyce (Helsinki 1994) brązowy medal podczas Igrzysk Olimpijskich (Atlanta 1996) brąz na Halowych Mistrzostwach Świata w Lekkoatletyce (Paryż 1997) złoto Mistrzostw Świata w Lekkoatletyce (Ateny 1997) brązowy medal Mistrzostw Świata w Lekkoatletyce (Sewilla 1999)</code> | <code>kto zaprojektował medale, które będą wręczane podczas tegorocznych mistrzostw Europy juniorów w lekkoatletyce?</code> |
555
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
556
+ ```json
557
+ {
558
+ "loss": "MultipleNegativesRankingLoss",
559
+ "matryoshka_dims": [
560
+ 768,
561
+ 512,
562
+ 256,
563
+ 128,
564
+ 64
565
+ ],
566
+ "matryoshka_weights": [
567
+ 1,
568
+ 1,
569
+ 1,
570
+ 1,
571
+ 1
572
+ ],
573
+ "n_dims_per_step": -1
574
+ }
575
+ ```
576
+
577
+ ### Training Hyperparameters
578
+ #### Non-Default Hyperparameters
579
+
580
+ - `eval_strategy`: epoch
581
+ - `gradient_accumulation_steps`: 8
582
+ - `learning_rate`: 2e-05
583
+ - `num_train_epochs`: 5
584
+ - `lr_scheduler_type`: cosine
585
+ - `warmup_ratio`: 0.1
586
+ - `bf16`: True
587
+ - `tf32`: True
588
+ - `load_best_model_at_end`: True
589
+ - `optim`: adamw_torch_fused
590
+ - `batch_sampler`: no_duplicates
591
+
592
+ #### All Hyperparameters
593
+ <details><summary>Click to expand</summary>
594
+
595
+ - `overwrite_output_dir`: False
596
+ - `do_predict`: False
597
+ - `eval_strategy`: epoch
598
+ - `prediction_loss_only`: True
599
+ - `per_device_train_batch_size`: 8
600
+ - `per_device_eval_batch_size`: 8
601
+ - `per_gpu_train_batch_size`: None
602
+ - `per_gpu_eval_batch_size`: None
603
+ - `gradient_accumulation_steps`: 8
604
+ - `eval_accumulation_steps`: None
605
+ - `learning_rate`: 2e-05
606
+ - `weight_decay`: 0.0
607
+ - `adam_beta1`: 0.9
608
+ - `adam_beta2`: 0.999
609
+ - `adam_epsilon`: 1e-08
610
+ - `max_grad_norm`: 1.0
611
+ - `num_train_epochs`: 5
612
+ - `max_steps`: -1
613
+ - `lr_scheduler_type`: cosine
614
+ - `lr_scheduler_kwargs`: {}
615
+ - `warmup_ratio`: 0.1
616
+ - `warmup_steps`: 0
617
+ - `log_level`: passive
618
+ - `log_level_replica`: warning
619
+ - `log_on_each_node`: True
620
+ - `logging_nan_inf_filter`: True
621
+ - `save_safetensors`: True
622
+ - `save_on_each_node`: False
623
+ - `save_only_model`: False
624
+ - `restore_callback_states_from_checkpoint`: False
625
+ - `no_cuda`: False
626
+ - `use_cpu`: False
627
+ - `use_mps_device`: False
628
+ - `seed`: 42
629
+ - `data_seed`: None
630
+ - `jit_mode_eval`: False
631
+ - `use_ipex`: False
632
+ - `bf16`: True
633
+ - `fp16`: False
634
+ - `fp16_opt_level`: O1
635
+ - `half_precision_backend`: auto
636
+ - `bf16_full_eval`: False
637
+ - `fp16_full_eval`: False
638
+ - `tf32`: True
639
+ - `local_rank`: 0
640
+ - `ddp_backend`: None
641
+ - `tpu_num_cores`: None
642
+ - `tpu_metrics_debug`: False
643
+ - `debug`: []
644
+ - `dataloader_drop_last`: False
645
+ - `dataloader_num_workers`: 0
646
+ - `dataloader_prefetch_factor`: None
647
+ - `past_index`: -1
648
+ - `disable_tqdm`: False
649
+ - `remove_unused_columns`: True
650
+ - `label_names`: None
651
+ - `load_best_model_at_end`: True
652
+ - `ignore_data_skip`: False
653
+ - `fsdp`: []
654
+ - `fsdp_min_num_params`: 0
655
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
656
+ - `fsdp_transformer_layer_cls_to_wrap`: None
657
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
658
+ - `deepspeed`: None
659
+ - `label_smoothing_factor`: 0.0
660
+ - `optim`: adamw_torch_fused
661
+ - `optim_args`: None
662
+ - `adafactor`: False
663
+ - `group_by_length`: False
664
+ - `length_column_name`: length
665
+ - `ddp_find_unused_parameters`: None
666
+ - `ddp_bucket_cap_mb`: None
667
+ - `ddp_broadcast_buffers`: False
668
+ - `dataloader_pin_memory`: True
669
+ - `dataloader_persistent_workers`: False
670
+ - `skip_memory_metrics`: True
671
+ - `use_legacy_prediction_loop`: False
672
+ - `push_to_hub`: False
673
+ - `resume_from_checkpoint`: None
674
+ - `hub_model_id`: None
675
+ - `hub_strategy`: every_save
676
+ - `hub_private_repo`: False
677
+ - `hub_always_push`: False
678
+ - `gradient_checkpointing`: False
679
+ - `gradient_checkpointing_kwargs`: None
680
+ - `include_inputs_for_metrics`: False
681
+ - `eval_do_concat_batches`: True
682
+ - `fp16_backend`: auto
683
+ - `push_to_hub_model_id`: None
684
+ - `push_to_hub_organization`: None
685
+ - `mp_parameters`:
686
+ - `auto_find_batch_size`: False
687
+ - `full_determinism`: False
688
+ - `torchdynamo`: None
689
+ - `ray_scope`: last
690
+ - `ddp_timeout`: 1800
691
+ - `torch_compile`: False
692
+ - `torch_compile_backend`: None
693
+ - `torch_compile_mode`: None
694
+ - `dispatch_batches`: None
695
+ - `split_batches`: None
696
+ - `include_tokens_per_second`: False
697
+ - `include_num_input_tokens_seen`: False
698
+ - `neftune_noise_alpha`: None
699
+ - `optim_target_modules`: None
700
+ - `batch_eval_metrics`: False
701
+ - `batch_sampler`: no_duplicates
702
+ - `multi_dataset_batch_sampler`: proportional
703
+
704
+ </details>
705
+
706
+ ### Training Logs
707
+ <details><summary>Click to expand</summary>
708
+
709
+ | 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 |
710
+ |:-------:|:-------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
711
+ | 0 | 0 | - | 0.3475 | 0.3675 | 0.3753 | 0.2982 | 0.3798 |
712
+ | 0.0171 | 1 | 2.6683 | - | - | - | - | - |
713
+ | 0.0342 | 2 | 3.2596 | - | - | - | - | - |
714
+ | 0.0513 | 3 | 3.4541 | - | - | - | - | - |
715
+ | 0.0684 | 4 | 2.4201 | - | - | - | - | - |
716
+ | 0.0855 | 5 | 3.5911 | - | - | - | - | - |
717
+ | 0.1026 | 6 | 3.0902 | - | - | - | - | - |
718
+ | 0.1197 | 7 | 2.5999 | - | - | - | - | - |
719
+ | 0.1368 | 8 | 2.892 | - | - | - | - | - |
720
+ | 0.1538 | 9 | 2.8722 | - | - | - | - | - |
721
+ | 0.1709 | 10 | 2.3703 | - | - | - | - | - |
722
+ | 0.1880 | 11 | 2.6833 | - | - | - | - | - |
723
+ | 0.2051 | 12 | 1.9814 | - | - | - | - | - |
724
+ | 0.2222 | 13 | 1.6643 | - | - | - | - | - |
725
+ | 0.2393 | 14 | 1.8493 | - | - | - | - | - |
726
+ | 0.2564 | 15 | 1.5136 | - | - | - | - | - |
727
+ | 0.2735 | 16 | 1.9726 | - | - | - | - | - |
728
+ | 0.2906 | 17 | 1.1505 | - | - | - | - | - |
729
+ | 0.3077 | 18 | 1.3834 | - | - | - | - | - |
730
+ | 0.3248 | 19 | 1.2244 | - | - | - | - | - |
731
+ | 0.3419 | 20 | 1.2107 | - | - | - | - | - |
732
+ | 0.3590 | 21 | 0.8936 | - | - | - | - | - |
733
+ | 0.3761 | 22 | 0.8144 | - | - | - | - | - |
734
+ | 0.3932 | 23 | 0.8353 | - | - | - | - | - |
735
+ | 0.4103 | 24 | 1.572 | - | - | - | - | - |
736
+ | 0.4274 | 25 | 0.9257 | - | - | - | - | - |
737
+ | 0.4444 | 26 | 0.8405 | - | - | - | - | - |
738
+ | 0.4615 | 27 | 0.5621 | - | - | - | - | - |
739
+ | 0.4786 | 28 | 0.4241 | - | - | - | - | - |
740
+ | 0.4957 | 29 | 0.6171 | - | - | - | - | - |
741
+ | 0.5128 | 30 | 0.5989 | - | - | - | - | - |
742
+ | 0.5299 | 31 | 0.2767 | - | - | - | - | - |
743
+ | 0.5470 | 32 | 0.5599 | - | - | - | - | - |
744
+ | 0.5641 | 33 | 0.5964 | - | - | - | - | - |
745
+ | 0.5812 | 34 | 0.9778 | - | - | - | - | - |
746
+ | 0.5983 | 35 | 0.772 | - | - | - | - | - |
747
+ | 0.6154 | 36 | 1.0341 | - | - | - | - | - |
748
+ | 0.6325 | 37 | 0.3503 | - | - | - | - | - |
749
+ | 0.6496 | 38 | 0.8229 | - | - | - | - | - |
750
+ | 0.6667 | 39 | 0.969 | - | - | - | - | - |
751
+ | 0.6838 | 40 | 1.7993 | - | - | - | - | - |
752
+ | 0.7009 | 41 | 0.5542 | - | - | - | - | - |
753
+ | 0.7179 | 42 | 1.332 | - | - | - | - | - |
754
+ | 0.7350 | 43 | 1.1516 | - | - | - | - | - |
755
+ | 0.7521 | 44 | 1.3183 | - | - | - | - | - |
756
+ | 0.7692 | 45 | 1.0865 | - | - | - | - | - |
757
+ | 0.7863 | 46 | 0.6204 | - | - | - | - | - |
758
+ | 0.8034 | 47 | 0.7541 | - | - | - | - | - |
759
+ | 0.8205 | 48 | 0.9362 | - | - | - | - | - |
760
+ | 0.8376 | 49 | 0.3979 | - | - | - | - | - |
761
+ | 0.8547 | 50 | 0.7187 | - | - | - | - | - |
762
+ | 0.8718 | 51 | 0.9217 | - | - | - | - | - |
763
+ | 0.8889 | 52 | 0.4866 | - | - | - | - | - |
764
+ | 0.9060 | 53 | 0.355 | - | - | - | - | - |
765
+ | 0.9231 | 54 | 0.7172 | - | - | - | - | - |
766
+ | 0.9402 | 55 | 0.6007 | - | - | - | - | - |
767
+ | 0.9573 | 56 | 1.1547 | - | - | - | - | - |
768
+ | 0.9744 | 57 | 0.5713 | - | - | - | - | - |
769
+ | 0.9915 | 58 | 0.9089 | 0.3985 | 0.4164 | 0.4264 | 0.3642 | 0.4255 |
770
+ | 1.0085 | 59 | 0.594 | - | - | - | - | - |
771
+ | 1.0256 | 60 | 0.6554 | - | - | - | - | - |
772
+ | 1.0427 | 61 | 0.2794 | - | - | - | - | - |
773
+ | 1.0598 | 62 | 0.8654 | - | - | - | - | - |
774
+ | 1.0769 | 63 | 0.9698 | - | - | - | - | - |
775
+ | 1.0940 | 64 | 1.4827 | - | - | - | - | - |
776
+ | 1.1111 | 65 | 0.3159 | - | - | - | - | - |
777
+ | 1.1282 | 66 | 0.255 | - | - | - | - | - |
778
+ | 1.1453 | 67 | 0.9819 | - | - | - | - | - |
779
+ | 1.1624 | 68 | 0.7442 | - | - | - | - | - |
780
+ | 1.1795 | 69 | 0.8199 | - | - | - | - | - |
781
+ | 1.1966 | 70 | 0.2647 | - | - | - | - | - |
782
+ | 1.2137 | 71 | 0.4098 | - | - | - | - | - |
783
+ | 1.2308 | 72 | 0.1608 | - | - | - | - | - |
784
+ | 1.2479 | 73 | 0.2092 | - | - | - | - | - |
785
+ | 1.2650 | 74 | 0.1231 | - | - | - | - | - |
786
+ | 1.2821 | 75 | 0.3203 | - | - | - | - | - |
787
+ | 1.2991 | 76 | 0.1435 | - | - | - | - | - |
788
+ | 1.3162 | 77 | 0.2293 | - | - | - | - | - |
789
+ | 1.3333 | 78 | 0.131 | - | - | - | - | - |
790
+ | 1.3504 | 79 | 0.1662 | - | - | - | - | - |
791
+ | 1.3675 | 80 | 0.094 | - | - | - | - | - |
792
+ | 1.3846 | 81 | 0.1454 | - | - | - | - | - |
793
+ | 1.4017 | 82 | 0.3096 | - | - | - | - | - |
794
+ | 1.4188 | 83 | 0.3188 | - | - | - | - | - |
795
+ | 1.4359 | 84 | 0.1156 | - | - | - | - | - |
796
+ | 1.4530 | 85 | 0.0581 | - | - | - | - | - |
797
+ | 1.4701 | 86 | 0.0543 | - | - | - | - | - |
798
+ | 1.4872 | 87 | 0.0427 | - | - | - | - | - |
799
+ | 1.5043 | 88 | 0.07 | - | - | - | - | - |
800
+ | 1.5214 | 89 | 0.0451 | - | - | - | - | - |
801
+ | 1.5385 | 90 | 0.0646 | - | - | - | - | - |
802
+ | 1.5556 | 91 | 0.1152 | - | - | - | - | - |
803
+ | 1.5726 | 92 | 0.1292 | - | - | - | - | - |
804
+ | 1.5897 | 93 | 0.1591 | - | - | - | - | - |
805
+ | 1.6068 | 94 | 0.1194 | - | - | - | - | - |
806
+ | 1.6239 | 95 | 0.0876 | - | - | - | - | - |
807
+ | 1.6410 | 96 | 0.1018 | - | - | - | - | - |
808
+ | 1.6581 | 97 | 0.3309 | - | - | - | - | - |
809
+ | 1.6752 | 98 | 0.2214 | - | - | - | - | - |
810
+ | 1.6923 | 99 | 0.1536 | - | - | - | - | - |
811
+ | 1.7094 | 100 | 0.1543 | - | - | - | - | - |
812
+ | 1.7265 | 101 | 0.3663 | - | - | - | - | - |
813
+ | 1.7436 | 102 | 0.2719 | - | - | - | - | - |
814
+ | 1.7607 | 103 | 0.1379 | - | - | - | - | - |
815
+ | 1.7778 | 104 | 0.0479 | - | - | - | - | - |
816
+ | 1.7949 | 105 | 0.0757 | - | - | - | - | - |
817
+ | 1.8120 | 106 | 0.059 | - | - | - | - | - |
818
+ | 1.8291 | 107 | 0.119 | - | - | - | - | - |
819
+ | 1.8462 | 108 | 0.1295 | - | - | - | - | - |
820
+ | 1.8632 | 109 | 0.115 | - | - | - | - | - |
821
+ | 1.8803 | 110 | 0.142 | - | - | - | - | - |
822
+ | 1.8974 | 111 | 0.1064 | - | - | - | - | - |
823
+ | 1.9145 | 112 | 0.0959 | - | - | - | - | - |
824
+ | 1.9316 | 113 | 0.0839 | - | - | - | - | - |
825
+ | 1.9487 | 114 | 0.1762 | - | - | - | - | - |
826
+ | 1.9658 | 115 | 0.1986 | - | - | - | - | - |
827
+ | 1.9829 | 116 | 0.0599 | - | - | - | - | - |
828
+ | 2.0 | 117 | 0.1145 | 0.3869 | 0.4095 | 0.4135 | 0.3664 | 0.4195 |
829
+ | 2.0171 | 118 | 0.0815 | - | - | - | - | - |
830
+ | 2.0342 | 119 | 0.1052 | - | - | - | - | - |
831
+ | 2.0513 | 120 | 0.1348 | - | - | - | - | - |
832
+ | 2.0684 | 121 | 0.255 | - | - | - | - | - |
833
+ | 2.0855 | 122 | 0.251 | - | - | - | - | - |
834
+ | 2.1026 | 123 | 0.3033 | - | - | - | - | - |
835
+ | 2.1197 | 124 | 0.0385 | - | - | - | - | - |
836
+ | 2.1368 | 125 | 0.0687 | - | - | - | - | - |
837
+ | 2.1538 | 126 | 0.1682 | - | - | - | - | - |
838
+ | 2.1709 | 127 | 0.0774 | - | - | - | - | - |
839
+ | 2.1880 | 128 | 0.0944 | - | - | - | - | - |
840
+ | 2.2051 | 129 | 0.036 | - | - | - | - | - |
841
+ | 2.2222 | 130 | 0.0393 | - | - | - | - | - |
842
+ | 2.2393 | 131 | 0.0387 | - | - | - | - | - |
843
+ | 2.2564 | 132 | 0.0273 | - | - | - | - | - |
844
+ | 2.2735 | 133 | 0.056 | - | - | - | - | - |
845
+ | 2.2906 | 134 | 0.0279 | - | - | - | - | - |
846
+ | 2.3077 | 135 | 0.0557 | - | - | - | - | - |
847
+ | 2.3248 | 136 | 0.0197 | - | - | - | - | - |
848
+ | 2.3419 | 137 | 0.0216 | - | - | - | - | - |
849
+ | 2.3590 | 138 | 0.0212 | - | - | - | - | - |
850
+ | 2.3761 | 139 | 0.0239 | - | - | - | - | - |
851
+ | 2.3932 | 140 | 0.0526 | - | - | - | - | - |
852
+ | 2.4103 | 141 | 0.1072 | - | - | - | - | - |
853
+ | 2.4274 | 142 | 0.0347 | - | - | - | - | - |
854
+ | 2.4444 | 143 | 0.024 | - | - | - | - | - |
855
+ | 2.4615 | 144 | 0.0128 | - | - | - | - | - |
856
+ | 2.4786 | 145 | 0.0089 | - | - | - | - | - |
857
+ | 2.4957 | 146 | 0.0101 | - | - | - | - | - |
858
+ | 2.5128 | 147 | 0.0124 | - | - | - | - | - |
859
+ | 2.5299 | 148 | 0.011 | - | - | - | - | - |
860
+ | 2.5470 | 149 | 0.0182 | - | - | - | - | - |
861
+ | 2.5641 | 150 | 0.0379 | - | - | - | - | - |
862
+ | 2.5812 | 151 | 0.0395 | - | - | - | - | - |
863
+ | 2.5983 | 152 | 0.0372 | - | - | - | - | - |
864
+ | 2.6154 | 153 | 0.031 | - | - | - | - | - |
865
+ | 2.6325 | 154 | 0.0136 | - | - | - | - | - |
866
+ | 2.6496 | 155 | 0.0355 | - | - | - | - | - |
867
+ | 2.6667 | 156 | 0.0296 | - | - | - | - | - |
868
+ | 2.6838 | 157 | 0.0473 | - | - | - | - | - |
869
+ | 2.7009 | 158 | 0.0295 | - | - | - | - | - |
870
+ | 2.7179 | 159 | 0.0576 | - | - | - | - | - |
871
+ | 2.7350 | 160 | 0.0592 | - | - | - | - | - |
872
+ | 2.7521 | 161 | 0.0571 | - | - | - | - | - |
873
+ | 2.7692 | 162 | 0.0221 | - | - | - | - | - |
874
+ | 2.7863 | 163 | 0.0179 | - | - | - | - | - |
875
+ | 2.8034 | 164 | 0.0195 | - | - | - | - | - |
876
+ | 2.8205 | 165 | 0.0291 | - | - | - | - | - |
877
+ | 2.8376 | 166 | 0.024 | - | - | - | - | - |
878
+ | 2.8547 | 167 | 0.0396 | - | - | - | - | - |
879
+ | 2.8718 | 168 | 0.0352 | - | - | - | - | - |
880
+ | 2.8889 | 169 | 0.0431 | - | - | - | - | - |
881
+ | 2.9060 | 170 | 0.0222 | - | - | - | - | - |
882
+ | 2.9231 | 171 | 0.016 | - | - | - | - | - |
883
+ | 2.9402 | 172 | 0.0307 | - | - | - | - | - |
884
+ | 2.9573 | 173 | 0.0439 | - | - | - | - | - |
885
+ | 2.9744 | 174 | 0.0197 | - | - | - | - | - |
886
+ | 2.9915 | 175 | 0.0181 | 0.3928 | 0.4120 | 0.4152 | 0.3717 | 0.4180 |
887
+ | 3.0085 | 176 | 0.03 | - | - | - | - | - |
888
+ | 3.0256 | 177 | 0.0325 | - | - | - | - | - |
889
+ | 3.0427 | 178 | 0.0286 | - | - | - | - | - |
890
+ | 3.0598 | 179 | 0.0746 | - | - | - | - | - |
891
+ | 3.0769 | 180 | 0.0677 | - | - | - | - | - |
892
+ | 3.0940 | 181 | 0.0574 | - | - | - | - | - |
893
+ | 3.1111 | 182 | 0.0158 | - | - | - | - | - |
894
+ | 3.1282 | 183 | 0.0092 | - | - | - | - | - |
895
+ | 3.1453 | 184 | 0.0412 | - | - | - | - | - |
896
+ | 3.1624 | 185 | 0.0308 | - | - | - | - | - |
897
+ | 3.1795 | 186 | 0.022 | - | - | - | - | - |
898
+ | 3.1966 | 187 | 0.0157 | - | - | - | - | - |
899
+ | 3.2137 | 188 | 0.0109 | - | - | - | - | - |
900
+ | 3.2308 | 189 | 0.0059 | - | - | - | - | - |
901
+ | 3.2479 | 190 | 0.0206 | - | - | - | - | - |
902
+ | 3.2650 | 191 | 0.0135 | - | - | - | - | - |
903
+ | 3.2821 | 192 | 0.0199 | - | - | - | - | - |
904
+ | 3.2991 | 193 | 0.0124 | - | - | - | - | - |
905
+ | 3.3162 | 194 | 0.0081 | - | - | - | - | - |
906
+ | 3.3333 | 195 | 0.0052 | - | - | - | - | - |
907
+ | 3.3504 | 196 | 0.006 | - | - | - | - | - |
908
+ | 3.3675 | 197 | 0.0074 | - | - | - | - | - |
909
+ | 3.3846 | 198 | 0.0085 | - | - | - | - | - |
910
+ | 3.4017 | 199 | 0.0273 | - | - | - | - | - |
911
+ | 3.4188 | 200 | 0.0363 | - | - | - | - | - |
912
+ | 3.4359 | 201 | 0.0077 | - | - | - | - | - |
913
+ | 3.4530 | 202 | 0.0046 | - | - | - | - | - |
914
+ | 3.4701 | 203 | 0.0067 | - | - | - | - | - |
915
+ | 3.4872 | 204 | 0.0054 | - | - | - | - | - |
916
+ | 3.5043 | 205 | 0.0055 | - | - | - | - | - |
917
+ | 3.5214 | 206 | 0.0052 | - | - | - | - | - |
918
+ | 3.5385 | 207 | 0.004 | - | - | - | - | - |
919
+ | 3.5556 | 208 | 0.0102 | - | - | - | - | - |
920
+ | 3.5726 | 209 | 0.0228 | - | - | - | - | - |
921
+ | 3.5897 | 210 | 0.0315 | - | - | - | - | - |
922
+ | 3.6068 | 211 | 0.0095 | - | - | - | - | - |
923
+ | 3.6239 | 212 | 0.0069 | - | - | - | - | - |
924
+ | 3.6410 | 213 | 0.0066 | - | - | - | - | - |
925
+ | 3.6581 | 214 | 0.0395 | - | - | - | - | - |
926
+ | 3.6752 | 215 | 0.0176 | - | - | - | - | - |
927
+ | 3.6923 | 216 | 0.0156 | - | - | - | - | - |
928
+ | 3.7094 | 217 | 0.0168 | - | - | - | - | - |
929
+ | 3.7265 | 218 | 0.0376 | - | - | - | - | - |
930
+ | 3.7436 | 219 | 0.0149 | - | - | - | - | - |
931
+ | 3.7607 | 220 | 0.0179 | - | - | - | - | - |
932
+ | 3.7778 | 221 | 0.0059 | - | - | - | - | - |
933
+ | 3.7949 | 222 | 0.013 | - | - | - | - | - |
934
+ | 3.8120 | 223 | 0.0081 | - | - | - | - | - |
935
+ | 3.8291 | 224 | 0.0136 | - | - | - | - | - |
936
+ | 3.8462 | 225 | 0.0129 | - | - | - | - | - |
937
+ | 3.8632 | 226 | 0.0132 | - | - | - | - | - |
938
+ | 3.8803 | 227 | 0.0228 | - | - | - | - | - |
939
+ | 3.8974 | 228 | 0.0091 | - | - | - | - | - |
940
+ | 3.9145 | 229 | 0.0112 | - | - | - | - | - |
941
+ | 3.9316 | 230 | 0.0124 | - | - | - | - | - |
942
+ | 3.9487 | 231 | 0.0224 | - | - | - | - | - |
943
+ | 3.9658 | 232 | 0.0191 | - | - | - | - | - |
944
+ | 3.9829 | 233 | 0.0078 | - | - | - | - | - |
945
+ | **4.0** | **234** | **0.0145** | **0.3959** | **0.411** | **0.4154** | **0.3741** | **0.4179** |
946
+ | 4.0171 | 235 | 0.0089 | - | - | - | - | - |
947
+ | 4.0342 | 236 | 0.0157 | - | - | - | - | - |
948
+ | 4.0513 | 237 | 0.019 | - | - | - | - | - |
949
+ | 4.0684 | 238 | 0.0315 | - | - | - | - | - |
950
+ | 4.0855 | 239 | 0.0311 | - | - | - | - | - |
951
+ | 4.1026 | 240 | 0.0155 | - | - | - | - | - |
952
+ | 4.1197 | 241 | 0.0078 | - | - | - | - | - |
953
+ | 4.1368 | 242 | 0.0069 | - | - | - | - | - |
954
+ | 4.1538 | 243 | 0.0246 | - | - | - | - | - |
955
+ | 4.1709 | 244 | 0.011 | - | - | - | - | - |
956
+ | 4.1880 | 245 | 0.0169 | - | - | - | - | - |
957
+ | 4.2051 | 246 | 0.0065 | - | - | - | - | - |
958
+ | 4.2222 | 247 | 0.0093 | - | - | - | - | - |
959
+ | 4.2393 | 248 | 0.0059 | - | - | - | - | - |
960
+ | 4.2564 | 249 | 0.0072 | - | - | - | - | - |
961
+ | 4.2735 | 250 | 0.0114 | - | - | - | - | - |
962
+ | 4.2906 | 251 | 0.0048 | - | - | - | - | - |
963
+ | 4.3077 | 252 | 0.0099 | - | - | - | - | - |
964
+ | 4.3248 | 253 | 0.0061 | - | - | - | - | - |
965
+ | 4.3419 | 254 | 0.005 | - | - | - | - | - |
966
+ | 4.3590 | 255 | 0.0077 | - | - | - | - | - |
967
+ | 4.3761 | 256 | 0.0057 | - | - | - | - | - |
968
+ | 4.3932 | 257 | 0.0106 | - | - | - | - | - |
969
+ | 4.4103 | 258 | 0.0176 | - | - | - | - | - |
970
+ | 4.4274 | 259 | 0.0085 | - | - | - | - | - |
971
+ | 4.4444 | 260 | 0.0059 | - | - | - | - | - |
972
+ | 4.4615 | 261 | 0.0063 | - | - | - | - | - |
973
+ | 4.4786 | 262 | 0.003 | - | - | - | - | - |
974
+ | 4.4957 | 263 | 0.0041 | - | - | - | - | - |
975
+ | 4.5128 | 264 | 0.0048 | - | - | - | - | - |
976
+ | 4.5299 | 265 | 0.0037 | - | - | - | - | - |
977
+ | 4.5470 | 266 | 0.0052 | - | - | - | - | - |
978
+ | 4.5641 | 267 | 0.0084 | - | - | - | - | - |
979
+ | 4.5812 | 268 | 0.0183 | - | - | - | - | - |
980
+ | 4.5983 | 269 | 0.0065 | - | - | - | - | - |
981
+ | 4.6154 | 270 | 0.0074 | - | - | - | - | - |
982
+ | 4.6325 | 271 | 0.0046 | - | - | - | - | - |
983
+ | 4.6496 | 272 | 0.009 | - | - | - | - | - |
984
+ | 4.6667 | 273 | 0.01 | - | - | - | - | - |
985
+ | 4.6838 | 274 | 0.0158 | - | - | - | - | - |
986
+ | 4.7009 | 275 | 0.0077 | - | - | - | - | - |
987
+ | 4.7179 | 276 | 0.0259 | - | - | - | - | - |
988
+ | 4.7350 | 277 | 0.0204 | - | - | - | - | - |
989
+ | 4.7521 | 278 | 0.0155 | - | - | - | - | - |
990
+ | 4.7692 | 279 | 0.0101 | - | - | - | - | - |
991
+ | 4.7863 | 280 | 0.0062 | - | - | - | - | - |
992
+ | 4.8034 | 281 | 0.0065 | - | - | - | - | - |
993
+ | 4.8205 | 282 | 0.0115 | - | - | - | - | - |
994
+ | 4.8376 | 283 | 0.0088 | - | - | - | - | - |
995
+ | 4.8547 | 284 | 0.0157 | - | - | - | - | - |
996
+ | 4.8718 | 285 | 0.0145 | - | - | - | - | - |
997
+ | 4.8889 | 286 | 0.0122 | - | - | - | - | - |
998
+ | 4.9060 | 287 | 0.007 | - | - | - | - | - |
999
+ | 4.9231 | 288 | 0.0126 | - | - | - | - | - |
1000
+ | 4.9402 | 289 | 0.0094 | - | - | - | - | - |
1001
+ | 4.9573 | 290 | 0.016 | 0.3940 | 0.4131 | 0.4148 | 0.3728 | 0.4182 |
1002
+
1003
+ * The bold row denotes the saved checkpoint.
1004
+ </details>
1005
+
1006
+ ### Framework Versions
1007
+ - Python: 3.12.2
1008
+ - Sentence Transformers: 3.0.0
1009
+ - Transformers: 4.41.2
1010
+ - PyTorch: 2.3.1
1011
+ - Accelerate: 0.27.2
1012
+ - Datasets: 2.19.1
1013
+ - Tokenizers: 0.19.1
1014
+
1015
+ ## Citation
1016
+
1017
+ ### BibTeX
1018
+
1019
+ #### Sentence Transformers
1020
+ ```bibtex
1021
+ @inproceedings{reimers-2019-sentence-bert,
1022
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
1023
+ author = "Reimers, Nils and Gurevych, Iryna",
1024
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
1025
+ month = "11",
1026
+ year = "2019",
1027
+ publisher = "Association for Computational Linguistics",
1028
+ url = "https://arxiv.org/abs/1908.10084",
1029
+ }
1030
+ ```
1031
+
1032
+ #### MatryoshkaLoss
1033
+ ```bibtex
1034
+ @misc{kusupati2024matryoshka,
1035
+ title={Matryoshka Representation Learning},
1036
+ 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},
1037
+ year={2024},
1038
+ eprint={2205.13147},
1039
+ archivePrefix={arXiv},
1040
+ primaryClass={cs.LG}
1041
+ }
1042
+ ```
1043
+
1044
+ #### MultipleNegativesRankingLoss
1045
+ ```bibtex
1046
+ @misc{henderson2017efficient,
1047
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
1048
+ 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},
1049
+ year={2017},
1050
+ eprint={1705.00652},
1051
+ archivePrefix={arXiv},
1052
+ primaryClass={cs.CL}
1053
+ }
1054
+ ```
1055
+
1056
+ <!--
1057
+ ## Glossary
1058
+
1059
+ *Clearly define terms in order to be accessible across audiences.*
1060
+ -->
1061
+
1062
+ <!--
1063
+ ## Model Card Authors
1064
+
1065
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
1066
+ -->
1067
+
1068
+ <!--
1069
+ ## Model Card Contact
1070
+
1071
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
1072
+ -->
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/mmlw-roberta-base-klej-dyk-v0.1",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.41.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50001
28
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.2",
4
+ "transformers": "4.32.1",
5
+ "pytorch": "2.1.0a0+b5021ba"
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 sha256:07988420ce3c18d05c5a6842210ae79103c934f88e7143eb4158026d944f79d0
3
+ size 497793896
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50000": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_length": 512,
52
+ "model_max_length": 512,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "RobertaTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "<unk>"
64
+ }
unigram.json ADDED
The diff for this file is too large to render. See raw diff