Hugging Face's logo

dat-ai
/
bge-base-for_text2sql

Sentence Similarity
sentence-transformers
Safetensors
English
bert
feature-extraction
Generated from Trainer
dataset_size:56355
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Model card Files
xet
Community
dat-ai commited on
Commit
7e5e2ff
·
verified ·
1 Parent(s): 51260a9

Add new SentenceTransformer model

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +890 -0
  3. config.json +32 -0
  4. config_sentence_transformers.json +10 -0
  5. model.safetensors +3 -0
  6. modules.json +20 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +37 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +57 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": 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 +1,890 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BAAI/bge-base-en-v1.5
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
+ - generated_from_trainer
29
+ - dataset_size:56355
30
+ - loss:MatryoshkaLoss
31
+ - loss:MultipleNegativesRankingLoss
32
+ widget:
33
+ - source_sentence: "\n Given the Column informations, generate an SQL query for\
34
+ \ the following question:\n Column: Finishing position | Points awarded (Platinum)\
35
+ \ | Points awarded (Gold) | Points awarded (Silver) | Points awarded (Satellite)\n\
36
+ \ Question: How many platinum points were awarded when 6 gold points were awarded?\n\
37
+ \ SQL Query: SELECT MAX Points awarded (Platinum) FROM table WHERE Points awarded\
38
+ \ (Gold) = 6\n "
39
+ sentences:
40
+ - How many platinum points were awarded when 6 gold points were awarded?
41
+ - Did any team score games that totaled up to 860.5?
42
+ - Who had the pole position at the German Grand Prix?
43
+ - source_sentence: "\n Given the Column informations, generate an SQL query for\
44
+ \ the following question:\n Column: Player | No. | Nationality | Position | Years\
45
+ \ in Toronto | School/Club Team\n Question: What's Dell Curry nationality?\n\
46
+ \ SQL Query: SELECT Nationality FROM table WHERE Player = Dell Curry\n "
47
+ sentences:
48
+ - What is the title when original air date is may15,2008?
49
+ - What's Dell Curry nationality?
50
+ - What's the minimum total attendance of the Premier League association football?
51
+ - source_sentence: "\n Given the Column informations, generate an SQL query for\
52
+ \ the following question:\n Column: Sepal length | Sepal width | Petal length\
53
+ \ | Petal width | Species\n Question: Name the species when petal width is 2.0\
54
+ \ and petal length is 4.9\n SQL Query: SELECT Species FROM table WHERE Petal\
55
+ \ width = 2.0 AND Petal length = 4.9\n "
56
+ sentences:
57
+ - What year was the championship in Wimbledon (2)?
58
+ - Who wrote Series 38?
59
+ - Name the species when petal width is 2.0 and petal length is 4.9
60
+ - source_sentence: "\n Given the Column informations, generate an SQL query for\
61
+ \ the following question:\n Column: No. in season | No. in series | Title | Directed\
62
+ \ by | Written by | Original air date | U.S. viewers (million)\n Question: How\
63
+ \ many millions of U.S. viewers watched the episode that first aired on March\
64
+ \ 31, 2013?\n SQL Query: SELECT U.S. viewers (million) FROM table WHERE Original\
65
+ \ air date = March 31, 2013\n "
66
+ sentences:
67
+ - How many millions of U.S. viewers watched the episode that first aired on March
68
+ 31, 2013?
69
+ - How many viewers were there for the premier with 34
70
+ - What is Bruce Cerone overall?
71
+ - source_sentence: "\n Given the Column informations, generate an SQL query for\
72
+ \ the following question:\n Column: Nomination | Actors Name | Film Name | Director\
73
+ \ | Country\n Question: What was the film Falling up nominated for?\n SQL Query:\
74
+ \ SELECT Nomination FROM table WHERE Film Name = Falling Up\n "
75
+ sentences:
76
+ - What was the film Falling up nominated for?
77
+ - Who wrote an episode watched by 19.01 million US viewers?
78
+ - What player is on the Montreal Alouettes CFl team?
79
+ model-index:
80
+ - name: BGE base SQL Matryoshka
81
+ results:
82
+ - task:
83
+ type: information-retrieval
84
+ name: Information Retrieval
85
+ dataset:
86
+ name: dim 768
87
+ type: dim_768
88
+ metrics:
89
+ - type: cosine_accuracy@1
90
+ value: 0.4676281647562665
91
+ name: Cosine Accuracy@1
92
+ - type: cosine_accuracy@3
93
+ value: 0.4697065121551833
94
+ name: Cosine Accuracy@3
95
+ - type: cosine_accuracy@5
96
+ value: 0.4697065121551833
97
+ name: Cosine Accuracy@5
98
+ - type: cosine_accuracy@10
99
+ value: 0.4697065121551833
100
+ name: Cosine Accuracy@10
101
+ - type: cosine_precision@1
102
+ value: 0.4676281647562665
103
+ name: Cosine Precision@1
104
+ - type: cosine_precision@3
105
+ value: 0.15656883738506108
106
+ name: Cosine Precision@3
107
+ - type: cosine_precision@5
108
+ value: 0.09394130243103667
109
+ name: Cosine Precision@5
110
+ - type: cosine_precision@10
111
+ value: 0.046970651215518334
112
+ name: Cosine Precision@10
113
+ - type: cosine_recall@1
114
+ value: 0.4676281647562665
115
+ name: Cosine Recall@1
116
+ - type: cosine_recall@3
117
+ value: 0.4697065121551833
118
+ name: Cosine Recall@3
119
+ - type: cosine_recall@5
120
+ value: 0.4697065121551833
121
+ name: Cosine Recall@5
122
+ - type: cosine_recall@10
123
+ value: 0.4697065121551833
124
+ name: Cosine Recall@10
125
+ - type: cosine_ndcg@10
126
+ value: 0.46889822604232273
127
+ name: Cosine Ndcg@10
128
+ - type: cosine_mrr@10
129
+ value: 0.4686148549355503
130
+ name: Cosine Mrr@10
131
+ - type: cosine_map@100
132
+ value: 0.4686406337350657
133
+ name: Cosine Map@100
134
+ - task:
135
+ type: information-retrieval
136
+ name: Information Retrieval
137
+ dataset:
138
+ name: dim 512
139
+ type: dim_512
140
+ metrics:
141
+ - type: cosine_accuracy@1
142
+ value: 0.46775412520468573
143
+ name: Cosine Accuracy@1
144
+ - type: cosine_accuracy@3
145
+ value: 0.4697065121551833
146
+ name: Cosine Accuracy@3
147
+ - type: cosine_accuracy@5
148
+ value: 0.4697065121551833
149
+ name: Cosine Accuracy@5
150
+ - type: cosine_accuracy@10
151
+ value: 0.4697065121551833
152
+ name: Cosine Accuracy@10
153
+ - type: cosine_precision@1
154
+ value: 0.46775412520468573
155
+ name: Cosine Precision@1
156
+ - type: cosine_precision@3
157
+ value: 0.15656883738506108
158
+ name: Cosine Precision@3
159
+ - type: cosine_precision@5
160
+ value: 0.09394130243103667
161
+ name: Cosine Precision@5
162
+ - type: cosine_precision@10
163
+ value: 0.046970651215518334
164
+ name: Cosine Precision@10
165
+ - type: cosine_recall@1
166
+ value: 0.46775412520468573
167
+ name: Cosine Recall@1
168
+ - type: cosine_recall@3
169
+ value: 0.4697065121551833
170
+ name: Cosine Recall@3
171
+ - type: cosine_recall@5
172
+ value: 0.4697065121551833
173
+ name: Cosine Recall@5
174
+ - type: cosine_recall@10
175
+ value: 0.4697065121551833
176
+ name: Cosine Recall@10
177
+ - type: cosine_ndcg@10
178
+ value: 0.4689612062665323
179
+ name: Cosine Ndcg@10
180
+ - type: cosine_mrr@10
181
+ value: 0.46869882856782963
182
+ name: Cosine Mrr@10
183
+ - type: cosine_map@100
184
+ value: 0.4687237988187482
185
+ name: Cosine Map@100
186
+ - task:
187
+ type: information-retrieval
188
+ name: Information Retrieval
189
+ dataset:
190
+ name: dim 256
191
+ type: dim_256
192
+ metrics:
193
+ - type: cosine_accuracy@1
194
+ value: 0.46750220430784734
195
+ name: Cosine Accuracy@1
196
+ - type: cosine_accuracy@3
197
+ value: 0.4697065121551833
198
+ name: Cosine Accuracy@3
199
+ - type: cosine_accuracy@5
200
+ value: 0.4697065121551833
201
+ name: Cosine Accuracy@5
202
+ - type: cosine_accuracy@10
203
+ value: 0.46976949237939286
204
+ name: Cosine Accuracy@10
205
+ - type: cosine_precision@1
206
+ value: 0.46750220430784734
207
+ name: Cosine Precision@1
208
+ - type: cosine_precision@3
209
+ value: 0.15656883738506108
210
+ name: Cosine Precision@3
211
+ - type: cosine_precision@5
212
+ value: 0.09394130243103667
213
+ name: Cosine Precision@5
214
+ - type: cosine_precision@10
215
+ value: 0.04697694923793929
216
+ name: Cosine Precision@10
217
+ - type: cosine_recall@1
218
+ value: 0.46750220430784734
219
+ name: Cosine Recall@1
220
+ - type: cosine_recall@3
221
+ value: 0.4697065121551833
222
+ name: Cosine Recall@3
223
+ - type: cosine_recall@5
224
+ value: 0.4697065121551833
225
+ name: Cosine Recall@5
226
+ - type: cosine_recall@10
227
+ value: 0.46976949237939286
228
+ name: Cosine Recall@10
229
+ - type: cosine_ndcg@10
230
+ value: 0.4688906637675648
231
+ name: Cosine Ndcg@10
232
+ - type: cosine_mrr@10
233
+ value: 0.4685833648234455
234
+ name: Cosine Mrr@10
235
+ - type: cosine_map@100
236
+ value: 0.468602927990512
237
+ name: Cosine Map@100
238
+ - task:
239
+ type: information-retrieval
240
+ name: Information Retrieval
241
+ dataset:
242
+ name: dim 128
243
+ type: dim_128
244
+ metrics:
245
+ - type: cosine_accuracy@1
246
+ value: 0.46769114498047615
247
+ name: Cosine Accuracy@1
248
+ - type: cosine_accuracy@3
249
+ value: 0.4696435319309737
250
+ name: Cosine Accuracy@3
251
+ - type: cosine_accuracy@5
252
+ value: 0.46976949237939286
253
+ name: Cosine Accuracy@5
254
+ - type: cosine_accuracy@10
255
+ value: 0.46976949237939286
256
+ name: Cosine Accuracy@10
257
+ - type: cosine_precision@1
258
+ value: 0.46769114498047615
259
+ name: Cosine Precision@1
260
+ - type: cosine_precision@3
261
+ value: 0.1565478439769912
262
+ name: Cosine Precision@3
263
+ - type: cosine_precision@5
264
+ value: 0.09395389847587858
265
+ name: Cosine Precision@5
266
+ - type: cosine_precision@10
267
+ value: 0.04697694923793929
268
+ name: Cosine Precision@10
269
+ - type: cosine_recall@1
270
+ value: 0.46769114498047615
271
+ name: Cosine Recall@1
272
+ - type: cosine_recall@3
273
+ value: 0.4696435319309737
274
+ name: Cosine Recall@3
275
+ - type: cosine_recall@5
276
+ value: 0.46976949237939286
277
+ name: Cosine Recall@5
278
+ - type: cosine_recall@10
279
+ value: 0.46976949237939286
280
+ name: Cosine Recall@10
281
+ - type: cosine_ndcg@10
282
+ value: 0.4689469541953942
283
+ name: Cosine Ndcg@10
284
+ - type: cosine_mrr@10
285
+ value: 0.468661040433304
286
+ name: Cosine Mrr@10
287
+ - type: cosine_map@100
288
+ value: 0.4686773555936371
289
+ name: Cosine Map@100
290
+ - task:
291
+ type: information-retrieval
292
+ name: Information Retrieval
293
+ dataset:
294
+ name: dim 64
295
+ type: dim_64
296
+ metrics:
297
+ - type: cosine_accuracy@1
298
+ value: 0.46775412520468573
299
+ name: Cosine Accuracy@1
300
+ - type: cosine_accuracy@3
301
+ value: 0.4696435319309737
302
+ name: Cosine Accuracy@3
303
+ - type: cosine_accuracy@5
304
+ value: 0.4696435319309737
305
+ name: Cosine Accuracy@5
306
+ - type: cosine_accuracy@10
307
+ value: 0.4697065121551833
308
+ name: Cosine Accuracy@10
309
+ - type: cosine_precision@1
310
+ value: 0.46775412520468573
311
+ name: Cosine Precision@1
312
+ - type: cosine_precision@3
313
+ value: 0.1565478439769912
314
+ name: Cosine Precision@3
315
+ - type: cosine_precision@5
316
+ value: 0.09392870638619474
317
+ name: Cosine Precision@5
318
+ - type: cosine_precision@10
319
+ value: 0.046970651215518334
320
+ name: Cosine Precision@10
321
+ - type: cosine_recall@1
322
+ value: 0.46775412520468573
323
+ name: Cosine Recall@1
324
+ - type: cosine_recall@3
325
+ value: 0.4696435319309737
326
+ name: Cosine Recall@3
327
+ - type: cosine_recall@5
328
+ value: 0.4696435319309737
329
+ name: Cosine Recall@5
330
+ - type: cosine_recall@10
331
+ value: 0.4697065121551833
332
+ name: Cosine Recall@10
333
+ - type: cosine_ndcg@10
334
+ value: 0.4689578301883334
335
+ name: Cosine Ndcg@10
336
+ - type: cosine_mrr@10
337
+ value: 0.468696204391821
338
+ name: Cosine Mrr@10
339
+ - type: cosine_map@100
340
+ value: 0.46870770760703784
341
+ name: Cosine Map@100
342
+ ---
343
+
344
+ # BGE base SQL Matryoshka
345
+
346
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the json 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.
347
+
348
+ ## Model Details
349
+
350
+ ### Model Description
351
+ - **Model Type:** Sentence Transformer
352
+ - **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
353
+ - **Maximum Sequence Length:** 512 tokens
354
+ - **Output Dimensionality:** 768 dimensions
355
+ - **Similarity Function:** Cosine Similarity
356
+ - **Training Dataset:**
357
+ - json
358
+ - **Language:** en
359
+ - **License:** apache-2.0
360
+
361
+ ### Model Sources
362
+
363
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
364
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
365
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
366
+
367
+ ### Full Model Architecture
368
+
369
+ ```
370
+ SentenceTransformer(
371
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
372
+ (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})
373
+ (2): Normalize()
374
+ )
375
+ ```
376
+
377
+ ## Usage
378
+
379
+ ### Direct Usage (Sentence Transformers)
380
+
381
+ First install the Sentence Transformers library:
382
+
383
+ ```bash
384
+ pip install -U sentence-transformers
385
+ ```
386
+
387
+ Then you can load this model and run inference.
388
+ ```python
389
+ from sentence_transformers import SentenceTransformer
390
+
391
+ # Download from the 🤗 Hub
392
+ model = SentenceTransformer("dat-ai/bge-base-for_text2sql")
393
+ # Run inference
394
+ sentences = [
395
+ '\n Given the Column informations, generate an SQL query for the following question:\n Column: Nomination | Actors Name | Film Name | Director | Country\n Question: What was the film Falling up nominated for?\n SQL Query: SELECT Nomination FROM table WHERE Film Name = Falling Up\n ',
396
+ 'What was the film Falling up nominated for?',
397
+ 'Who wrote an episode watched by 19.01 million US viewers?',
398
+ ]
399
+ embeddings = model.encode(sentences)
400
+ print(embeddings.shape)
401
+ # [3, 768]
402
+
403
+ # Get the similarity scores for the embeddings
404
+ similarities = model.similarity(embeddings, embeddings)
405
+ print(similarities.shape)
406
+ # [3, 3]
407
+ ```
408
+
409
+ <!--
410
+ ### Direct Usage (Transformers)
411
+
412
+ <details><summary>Click to see the direct usage in Transformers</summary>
413
+
414
+ </details>
415
+ -->
416
+
417
+ <!--
418
+ ### Downstream Usage (Sentence Transformers)
419
+
420
+ You can finetune this model on your own dataset.
421
+
422
+ <details><summary>Click to expand</summary>
423
+
424
+ </details>
425
+ -->
426
+
427
+ <!--
428
+ ### Out-of-Scope Use
429
+
430
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
431
+ -->
432
+
433
+ ## Evaluation
434
+
435
+ ### Metrics
436
+
437
+ #### Information Retrieval
438
+
439
+ * Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
440
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
441
+
442
+ | Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 |
443
+ |:--------------------|:-----------|:----------|:-----------|:-----------|:----------|
444
+ | cosine_accuracy@1 | 0.4676 | 0.4678 | 0.4675 | 0.4677 | 0.4678 |
445
+ | cosine_accuracy@3 | 0.4697 | 0.4697 | 0.4697 | 0.4696 | 0.4696 |
446
+ | cosine_accuracy@5 | 0.4697 | 0.4697 | 0.4697 | 0.4698 | 0.4696 |
447
+ | cosine_accuracy@10 | 0.4697 | 0.4697 | 0.4698 | 0.4698 | 0.4697 |
448
+ | cosine_precision@1 | 0.4676 | 0.4678 | 0.4675 | 0.4677 | 0.4678 |
449
+ | cosine_precision@3 | 0.1566 | 0.1566 | 0.1566 | 0.1565 | 0.1565 |
450
+ | cosine_precision@5 | 0.0939 | 0.0939 | 0.0939 | 0.094 | 0.0939 |
451
+ | cosine_precision@10 | 0.047 | 0.047 | 0.047 | 0.047 | 0.047 |
452
+ | cosine_recall@1 | 0.4676 | 0.4678 | 0.4675 | 0.4677 | 0.4678 |
453
+ | cosine_recall@3 | 0.4697 | 0.4697 | 0.4697 | 0.4696 | 0.4696 |
454
+ | cosine_recall@5 | 0.4697 | 0.4697 | 0.4697 | 0.4698 | 0.4696 |
455
+ | cosine_recall@10 | 0.4697 | 0.4697 | 0.4698 | 0.4698 | 0.4697 |
456
+ | **cosine_ndcg@10** | **0.4689** | **0.469** | **0.4689** | **0.4689** | **0.469** |
457
+ | cosine_mrr@10 | 0.4686 | 0.4687 | 0.4686 | 0.4687 | 0.4687 |
458
+ | cosine_map@100 | 0.4686 | 0.4687 | 0.4686 | 0.4687 | 0.4687 |
459
+
460
+ <!--
461
+ ## Bias, Risks and Limitations
462
+
463
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
464
+ -->
465
+
466
+ <!--
467
+ ### Recommendations
468
+
469
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
470
+ -->
471
+
472
+ ## Training Details
473
+
474
+ ### Training Dataset
475
+
476
+ #### json
477
+
478
+ * Dataset: json
479
+ * Size: 56,355 training samples
480
+ * Columns: <code>context</code> and <code>question</code>
481
+ * Approximate statistics based on the first 1000 samples:
482
+ | | context | question |
483
+ |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
484
+ | type | string | string |
485
+ | details | <ul><li>min: 45 tokens</li><li>mean: 72.61 tokens</li><li>max: 196 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 15.41 tokens</li><li>max: 36 tokens</li></ul> |
486
+ * Samples:
487
+ | context | question |
488
+ |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
489
+ | <code><br> Given the Column informations, generate an SQL query for the following question:<br> Column: State/territory | Text/background colour | Format | Current slogan | Current series | Notes<br> Question: Tell me what the notes are for South Australia <br> SQL Query: SELECT Notes FROM table WHERE Current slogan = SOUTH AUSTRALIA<br> </code> | <code>Tell me what the notes are for South Australia </code> |
490
+ | <code><br> Given the Column informations, generate an SQL query for the following question:<br> Column: State/territory | Text/background colour | Format | Current slogan | Current series | Notes<br> Question: What is the current series where the new series began in June 2011?<br> SQL Query: SELECT Current series FROM table WHERE Notes = New series began in June 2011<br> </code> | <code>What is the current series where the new series began in June 2011?</code> |
491
+ | <code><br> Given the Column informations, generate an SQL query for the following question:<br> Column: State/territory | Text/background colour | Format | Current slogan | Current series | Notes<br> Question: What is the format for South Australia?<br> SQL Query: SELECT Format FROM table WHERE State/territory = South Australia<br> </code> | <code>What is the format for South Australia?</code> |
492
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
493
+ ```json
494
+ {
495
+ "loss": "MultipleNegativesRankingLoss",
496
+ "matryoshka_dims": [
497
+ 768,
498
+ 512
499
+ ],
500
+ "matryoshka_weights": [
501
+ 1,
502
+ 1
503
+ ],
504
+ "n_dims_per_step": -1
505
+ }
506
+ ```
507
+
508
+ ### Training Hyperparameters
509
+ #### Non-Default Hyperparameters
510
+
511
+ - `eval_strategy`: epoch
512
+ - `per_device_train_batch_size`: 16
513
+ - `gradient_accumulation_steps`: 8
514
+ - `learning_rate`: 2e-05
515
+ - `num_train_epochs`: 4
516
+ - `lr_scheduler_type`: cosine
517
+ - `warmup_ratio`: 0.1
518
+ - `fp16`: True
519
+ - `load_best_model_at_end`: True
520
+ - `optim`: adamw_torch_fused
521
+ - `batch_sampler`: no_duplicates
522
+
523
+ #### All Hyperparameters
524
+ <details><summary>Click to expand</summary>
525
+
526
+ - `overwrite_output_dir`: False
527
+ - `do_predict`: False
528
+ - `eval_strategy`: epoch
529
+ - `prediction_loss_only`: True
530
+ - `per_device_train_batch_size`: 16
531
+ - `per_device_eval_batch_size`: 8
532
+ - `per_gpu_train_batch_size`: None
533
+ - `per_gpu_eval_batch_size`: None
534
+ - `gradient_accumulation_steps`: 8
535
+ - `eval_accumulation_steps`: None
536
+ - `learning_rate`: 2e-05
537
+ - `weight_decay`: 0.0
538
+ - `adam_beta1`: 0.9
539
+ - `adam_beta2`: 0.999
540
+ - `adam_epsilon`: 1e-08
541
+ - `max_grad_norm`: 1.0
542
+ - `num_train_epochs`: 4
543
+ - `max_steps`: -1
544
+ - `lr_scheduler_type`: cosine
545
+ - `lr_scheduler_kwargs`: {}
546
+ - `warmup_ratio`: 0.1
547
+ - `warmup_steps`: 0
548
+ - `log_level`: passive
549
+ - `log_level_replica`: warning
550
+ - `log_on_each_node`: True
551
+ - `logging_nan_inf_filter`: True
552
+ - `save_safetensors`: True
553
+ - `save_on_each_node`: False
554
+ - `save_only_model`: False
555
+ - `restore_callback_states_from_checkpoint`: False
556
+ - `no_cuda`: False
557
+ - `use_cpu`: False
558
+ - `use_mps_device`: False
559
+ - `seed`: 42
560
+ - `data_seed`: None
561
+ - `jit_mode_eval`: False
562
+ - `use_ipex`: False
563
+ - `bf16`: False
564
+ - `fp16`: True
565
+ - `fp16_opt_level`: O1
566
+ - `half_precision_backend`: auto
567
+ - `bf16_full_eval`: False
568
+ - `fp16_full_eval`: False
569
+ - `tf32`: None
570
+ - `local_rank`: 0
571
+ - `ddp_backend`: None
572
+ - `tpu_num_cores`: None
573
+ - `tpu_metrics_debug`: False
574
+ - `debug`: []
575
+ - `dataloader_drop_last`: False
576
+ - `dataloader_num_workers`: 0
577
+ - `dataloader_prefetch_factor`: None
578
+ - `past_index`: -1
579
+ - `disable_tqdm`: False
580
+ - `remove_unused_columns`: True
581
+ - `label_names`: None
582
+ - `load_best_model_at_end`: True
583
+ - `ignore_data_skip`: False
584
+ - `fsdp`: []
585
+ - `fsdp_min_num_params`: 0
586
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
587
+ - `fsdp_transformer_layer_cls_to_wrap`: None
588
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
589
+ - `deepspeed`: None
590
+ - `label_smoothing_factor`: 0.0
591
+ - `optim`: adamw_torch_fused
592
+ - `optim_args`: None
593
+ - `adafactor`: False
594
+ - `group_by_length`: False
595
+ - `length_column_name`: length
596
+ - `ddp_find_unused_parameters`: None
597
+ - `ddp_bucket_cap_mb`: None
598
+ - `ddp_broadcast_buffers`: False
599
+ - `dataloader_pin_memory`: True
600
+ - `dataloader_persistent_workers`: False
601
+ - `skip_memory_metrics`: True
602
+ - `use_legacy_prediction_loop`: False
603
+ - `push_to_hub`: False
604
+ - `resume_from_checkpoint`: None
605
+ - `hub_model_id`: None
606
+ - `hub_strategy`: every_save
607
+ - `hub_private_repo`: False
608
+ - `hub_always_push`: False
609
+ - `gradient_checkpointing`: False
610
+ - `gradient_checkpointing_kwargs`: None
611
+ - `include_inputs_for_metrics`: False
612
+ - `eval_do_concat_batches`: True
613
+ - `fp16_backend`: auto
614
+ - `push_to_hub_model_id`: None
615
+ - `push_to_hub_organization`: None
616
+ - `mp_parameters`:
617
+ - `auto_find_batch_size`: False
618
+ - `full_determinism`: False
619
+ - `torchdynamo`: None
620
+ - `ray_scope`: last
621
+ - `ddp_timeout`: 1800
622
+ - `torch_compile`: False
623
+ - `torch_compile_backend`: None
624
+ - `torch_compile_mode`: None
625
+ - `dispatch_batches`: None
626
+ - `split_batches`: None
627
+ - `include_tokens_per_second`: False
628
+ - `include_num_input_tokens_seen`: False
629
+ - `neftune_noise_alpha`: None
630
+ - `optim_target_modules`: None
631
+ - `batch_eval_metrics`: False
632
+ - `prompts`: None
633
+ - `batch_sampler`: no_duplicates
634
+ - `multi_dataset_batch_sampler`: proportional
635
+
636
+ </details>
637
+
638
+ ### Training Logs
639
+ <details><summary>Click to expand</summary>
640
+
641
+ | Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
642
+ |:----------:|:--------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
643
+ | 0.0227 | 10 | 1.773 | - | - | - | - | - |
644
+ | 0.0454 | 20 | 1.3231 | - | - | - | - | - |
645
+ | 0.0681 | 30 | 0.713 | - | - | - | - | - |
646
+ | 0.0908 | 40 | 0.286 | - | - | - | - | - |
647
+ | 0.1135 | 50 | 0.1013 | - | - | - | - | - |
648
+ | 0.1362 | 60 | 0.0635 | - | - | - | - | - |
649
+ | 0.1590 | 70 | 0.0453 | - | - | - | - | - |
650
+ | 0.1817 | 80 | 0.041 | - | - | - | - | - |
651
+ | 0.2044 | 90 | 0.039 | - | - | - | - | - |
652
+ | 0.2271 | 100 | 0.027 | - | - | - | - | - |
653
+ | 0.2498 | 110 | 0.0193 | - | - | - | - | - |
654
+ | 0.2725 | 120 | 0.0167 | - | - | - | - | - |
655
+ | 0.2952 | 130 | 0.016 | - | - | - | - | - |
656
+ | 0.3179 | 140 | 0.0197 | - | - | - | - | - |
657
+ | 0.3406 | 150 | 0.0217 | - | - | - | - | - |
658
+ | 0.3633 | 160 | 0.0162 | - | - | - | - | - |
659
+ | 0.3860 | 170 | 0.012 | - | - | - | - | - |
660
+ | 0.4087 | 180 | 0.013 | - | - | - | - | - |
661
+ | 0.4315 | 190 | 0.0255 | - | - | - | - | - |
662
+ | 0.4542 | 200 | 0.0229 | - | - | - | - | - |
663
+ | 0.4769 | 210 | 0.0181 | - | - | - | - | - |
664
+ | 0.4996 | 220 | 0.0195 | - | - | - | - | - |
665
+ | 0.5223 | 230 | 0.0199 | - | - | - | - | - |
666
+ | 0.5450 | 240 | 0.0144 | - | - | - | - | - |
667
+ | 0.5677 | 250 | 0.0102 | - | - | - | - | - |
668
+ | 0.5904 | 260 | 0.0101 | - | - | - | - | - |
669
+ | 0.6131 | 270 | 0.0095 | - | - | - | - | - |
670
+ | 0.6358 | 280 | 0.0173 | - | - | - | - | - |
671
+ | 0.6585 | 290 | 0.01 | - | - | - | - | - |
672
+ | 0.6812 | 300 | 0.0129 | - | - | - | - | - |
673
+ | 0.7039 | 310 | 0.0177 | - | - | - | - | - |
674
+ | 0.7267 | 320 | 0.0106 | - | - | - | - | - |
675
+ | 0.7494 | 330 | 0.0146 | - | - | - | - | - |
676
+ | 0.7721 | 340 | 0.0185 | - | - | - | - | - |
677
+ | 0.7948 | 350 | 0.0203 | - | - | - | - | - |
678
+ | 0.8175 | 360 | 0.0146 | - | - | - | - | - |
679
+ | 0.8402 | 370 | 0.0072 | - | - | - | - | - |
680
+ | 0.8629 | 380 | 0.0102 | - | - | - | - | - |
681
+ | 0.8856 | 390 | 0.0075 | - | - | - | - | - |
682
+ | 0.9083 | 400 | 0.0064 | - | - | - | - | - |
683
+ | 0.9310 | 410 | 0.0163 | - | - | - | - | - |
684
+ | 0.9537 | 420 | 0.0069 | - | - | - | - | - |
685
+ | 0.9764 | 430 | 0.0072 | - | - | - | - | - |
686
+ | 0.9991 | 440 | 0.0147 | 0.4688 | 0.4689 | 0.4688 | 0.4689 | 0.4689 |
687
+ | 1.0219 | 450 | 0.0151 | - | - | - | - | - |
688
+ | 1.0446 | 460 | 0.0135 | - | - | - | - | - |
689
+ | 1.0673 | 470 | 0.0189 | - | - | - | - | - |
690
+ | 1.0900 | 480 | 0.0121 | - | - | - | - | - |
691
+ | 1.1127 | 490 | 0.0064 | - | - | - | - | - |
692
+ | 1.1354 | 500 | 0.0111 | - | - | - | - | - |
693
+ | 1.1581 | 510 | 0.0103 | - | - | - | - | - |
694
+ | 1.1808 | 520 | 0.0144 | - | - | - | - | - |
695
+ | 1.2035 | 530 | 0.0151 | - | - | - | - | - |
696
+ | 1.2262 | 540 | 0.0062 | - | - | - | - | - |
697
+ | 1.2489 | 550 | 0.0104 | - | - | - | - | - |
698
+ | 1.2716 | 560 | 0.0046 | - | - | - | - | - |
699
+ | 1.2944 | 570 | 0.0056 | - | - | - | - | - |
700
+ | 1.3171 | 580 | 0.0073 | - | - | - | - | - |
701
+ | 1.3398 | 590 | 0.007 | - | - | - | - | - |
702
+ | 1.3625 | 600 | 0.0074 | - | - | - | - | - |
703
+ | 1.3852 | 610 | 0.0057 | - | - | - | - | - |
704
+ | 1.4079 | 620 | 0.0052 | - | - | - | - | - |
705
+ | 1.4306 | 630 | 0.0114 | - | - | - | - | - |
706
+ | 1.4533 | 640 | 0.0075 | - | - | - | - | - |
707
+ | 1.4760 | 650 | 0.0116 | - | - | - | - | - |
708
+ | 1.4987 | 660 | 0.0092 | - | - | - | - | - |
709
+ | 1.5214 | 670 | 0.0137 | - | - | - | - | - |
710
+ | 1.5441 | 680 | 0.0066 | - | - | - | - | - |
711
+ | 1.5668 | 690 | 0.0042 | - | - | - | - | - |
712
+ | 1.5896 | 700 | 0.0036 | - | - | - | - | - |
713
+ | 1.6123 | 710 | 0.0039 | - | - | - | - | - |
714
+ | 1.6350 | 720 | 0.0065 | - | - | - | - | - |
715
+ | 1.6577 | 730 | 0.0051 | - | - | - | - | - |
716
+ | 1.6804 | 740 | 0.0054 | - | - | - | - | - |
717
+ | 1.7031 | 750 | 0.0086 | - | - | - | - | - |
718
+ | 1.7258 | 760 | 0.0062 | - | - | - | - | - |
719
+ | 1.7485 | 770 | 0.0071 | - | - | - | - | - |
720
+ | 1.7712 | 780 | 0.0108 | - | - | - | - | - |
721
+ | 1.7939 | 790 | 0.009 | - | - | - | - | - |
722
+ | 1.8166 | 800 | 0.0075 | - | - | - | - | - |
723
+ | 1.8393 | 810 | 0.0039 | - | - | - | - | - |
724
+ | 1.8620 | 820 | 0.0047 | - | - | - | - | - |
725
+ | 1.8848 | 830 | 0.0037 | - | - | - | - | - |
726
+ | 1.9075 | 840 | 0.0037 | - | - | - | - | - |
727
+ | 1.9302 | 850 | 0.0064 | - | - | - | - | - |
728
+ | 1.9529 | 860 | 0.0047 | - | - | - | - | - |
729
+ | 1.9756 | 870 | 0.0034 | - | - | - | - | - |
730
+ | 1.9983 | 880 | 0.0061 | 0.4689 | 0.4689 | 0.4689 | 0.4690 | 0.4690 |
731
+ | 2.0210 | 890 | 0.0096 | - | - | - | - | - |
732
+ | 2.0437 | 900 | 0.0071 | - | - | - | - | - |
733
+ | 2.0664 | 910 | 0.0101 | - | - | - | - | - |
734
+ | 2.0891 | 920 | 0.0054 | - | - | - | - | - |
735
+ | 2.1118 | 930 | 0.0039 | - | - | - | - | - |
736
+ | 2.1345 | 940 | 0.0074 | - | - | - | - | - |
737
+ | 2.1573 | 950 | 0.0044 | - | - | - | - | - |
738
+ | 2.1800 | 960 | 0.0088 | - | - | - | - | - |
739
+ | 2.2027 | 970 | 0.0096 | - | - | - | - | - |
740
+ | 2.2254 | 980 | 0.0057 | - | - | - | - | - |
741
+ | 2.2481 | 990 | 0.0063 | - | - | - | - | - |
742
+ | 2.2708 | 1000 | 0.0026 | - | - | - | - | - |
743
+ | 2.2935 | 1010 | 0.0032 | - | - | - | - | - |
744
+ | 2.3162 | 1020 | 0.0027 | - | - | - | - | - |
745
+ | 2.3389 | 1030 | 0.0041 | - | - | - | - | - |
746
+ | 2.3616 | 1040 | 0.0052 | - | - | - | - | - |
747
+ | 2.3843 | 1050 | 0.0035 | - | - | - | - | - |
748
+ | 2.4070 | 1060 | 0.0025 | - | - | - | - | - |
749
+ | 2.4297 | 1070 | 0.0059 | - | - | - | - | - |
750
+ | 2.4525 | 1080 | 0.0048 | - | - | - | - | - |
751
+ | 2.4752 | 1090 | 0.0064 | - | - | - | - | - |
752
+ | 2.4979 | 1100 | 0.0066 | - | - | - | - | - |
753
+ | 2.5206 | 1110 | 0.0078 | - | - | - | - | - |
754
+ | 2.5433 | 1120 | 0.0057 | - | - | - | - | - |
755
+ | 2.5660 | 1130 | 0.0026 | - | - | - | - | - |
756
+ | 2.5887 | 1140 | 0.0021 | - | - | - | - | - |
757
+ | 2.6114 | 1150 | 0.0021 | - | - | - | - | - |
758
+ | 2.6341 | 1160 | 0.0047 | - | - | - | - | - |
759
+ | 2.6568 | 1170 | 0.0034 | - | - | - | - | - |
760
+ | 2.6795 | 1180 | 0.0044 | - | - | - | - | - |
761
+ | 2.7022 | 1190 | 0.0058 | - | - | - | - | - |
762
+ | 2.7250 | 1200 | 0.0043 | - | - | - | - | - |
763
+ | 2.7477 | 1210 | 0.0056 | - | - | - | - | - |
764
+ | 2.7704 | 1220 | 0.0076 | - | - | - | - | - |
765
+ | 2.7931 | 1230 | 0.0063 | - | - | - | - | - |
766
+ | 2.8158 | 1240 | 0.0033 | - | - | - | - | - |
767
+ | 2.8385 | 1250 | 0.0025 | - | - | - | - | - |
768
+ | 2.8612 | 1260 | 0.0019 | - | - | - | - | - |
769
+ | 2.8839 | 1270 | 0.0052 | - | - | - | - | - |
770
+ | 2.9066 | 1280 | 0.0021 | - | - | - | - | - |
771
+ | 2.9293 | 1290 | 0.0041 | - | - | - | - | - |
772
+ | 2.9520 | 1300 | 0.0035 | - | - | - | - | - |
773
+ | 2.9747 | 1310 | 0.0044 | - | - | - | - | - |
774
+ | 2.9974 | 1320 | 0.0035 | - | - | - | - | - |
775
+ | **2.9997** | **1321** | **-** | **0.469** | **0.469** | **0.469** | **0.469** | **0.469** |
776
+ | 3.0202 | 1330 | 0.0062 | - | - | - | - | - |
777
+ | 3.0429 | 1340 | 0.0047 | - | - | - | - | - |
778
+ | 3.0656 | 1350 | 0.008 | - | - | - | - | - |
779
+ | 3.0883 | 1360 | 0.0033 | - | - | - | - | - |
780
+ | 3.1110 | 1370 | 0.0025 | - | - | - | - | - |
781
+ | 3.1337 | 1380 | 0.0069 | - | - | - | - | - |
782
+ | 3.1564 | 1390 | 0.0035 | - | - | - | - | - |
783
+ | 3.1791 | 1400 | 0.0085 | - | - | - | - | - |
784
+ | 3.2018 | 1410 | 0.007 | - | - | - | - | - |
785
+ | 3.2245 | 1420 | 0.007 | - | - | - | - | - |
786
+ | 3.2472 | 1430 | 0.0052 | - | - | - | - | - |
787
+ | 3.2699 | 1440 | 0.0019 | - | - | - | - | - |
788
+ | 3.2926 | 1450 | 0.0022 | - | - | - | - | - |
789
+ | 3.3154 | 1460 | 0.0019 | - | - | - | - | - |
790
+ | 3.3381 | 1470 | 0.0028 | - | - | - | - | - |
791
+ | 3.3608 | 1480 | 0.0042 | - | - | - | - | - |
792
+ | 3.3835 | 1490 | 0.0023 | - | - | - | - | - |
793
+ | 3.4062 | 1500 | 0.0024 | - | - | - | - | - |
794
+ | 3.4289 | 1510 | 0.0036 | - | - | - | - | - |
795
+ | 3.4516 | 1520 | 0.0038 | - | - | - | - | - |
796
+ | 3.4743 | 1530 | 0.0063 | - | - | - | - | - |
797
+ | 3.4970 | 1540 | 0.0044 | - | - | - | - | - |
798
+ | 3.5197 | 1550 | 0.0064 | - | - | - | - | - |
799
+ | 3.5424 | 1560 | 0.0053 | - | - | - | - | - |
800
+ | 3.5651 | 1570 | 0.0019 | - | - | - | - | - |
801
+ | 3.5879 | 1580 | 0.0019 | - | - | - | - | - |
802
+ | 3.6106 | 1590 | 0.0017 | - | - | - | - | - |
803
+ | 3.6333 | 1600 | 0.004 | - | - | - | - | - |
804
+ | 3.6560 | 1610 | 0.0026 | - | - | - | - | - |
805
+ | 3.6787 | 1620 | 0.0031 | - | - | - | - | - |
806
+ | 3.7014 | 1630 | 0.0043 | - | - | - | - | - |
807
+ | 3.7241 | 1640 | 0.0032 | - | - | - | - | - |
808
+ | 3.7468 | 1650 | 0.0041 | - | - | - | - | - |
809
+ | 3.7695 | 1660 | 0.0069 | - | - | - | - | - |
810
+ | 3.7922 | 1670 | 0.0063 | - | - | - | - | - |
811
+ | 3.8149 | 1680 | 0.0038 | - | - | - | - | - |
812
+ | 3.8376 | 1690 | 0.0024 | - | - | - | - | - |
813
+ | 3.8603 | 1700 | 0.0018 | - | - | - | - | - |
814
+ | 3.8831 | 1710 | 0.0034 | - | - | - | - | - |
815
+ | 3.9058 | 1720 | 0.0016 | - | - | - | - | - |
816
+ | 3.9285 | 1730 | 0.0026 | - | - | - | - | - |
817
+ | 3.9512 | 1740 | 0.0037 | - | - | - | - | - |
818
+ | 3.9739 | 1750 | 0.0024 | - | - | - | - | - |
819
+ | 3.9966 | 1760 | 0.0027 | 0.4689 | 0.4690 | 0.4689 | 0.4689 | 0.4690 |
820
+
821
+ * The bold row denotes the saved checkpoint.
822
+ </details>
823
+
824
+ ### Framework Versions
825
+ - Python: 3.10.14
826
+ - Sentence Transformers: 3.3.0
827
+ - Transformers: 4.41.2
828
+ - PyTorch: 2.1.2+cu121
829
+ - Accelerate: 0.34.2
830
+ - Datasets: 2.19.1
831
+ - Tokenizers: 0.19.1
832
+
833
+ ## Citation
834
+
835
+ ### BibTeX
836
+
837
+ #### Sentence Transformers
838
+ ```bibtex
839
+ @inproceedings{reimers-2019-sentence-bert,
840
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
841
+ author = "Reimers, Nils and Gurevych, Iryna",
842
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
843
+ month = "11",
844
+ year = "2019",
845
+ publisher = "Association for Computational Linguistics",
846
+ url = "https://arxiv.org/abs/1908.10084",
847
+ }
848
+ ```
849
+
850
+ #### MatryoshkaLoss
851
+ ```bibtex
852
+ @misc{kusupati2024matryoshka,
853
+ title={Matryoshka Representation Learning},
854
+ author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
855
+ year={2024},
856
+ eprint={2205.13147},
857
+ archivePrefix={arXiv},
858
+ primaryClass={cs.LG}
859
+ }
860
+ ```
861
+
862
+ #### MultipleNegativesRankingLoss
863
+ ```bibtex
864
+ @misc{henderson2017efficient,
865
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
866
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
867
+ year={2017},
868
+ eprint={1705.00652},
869
+ archivePrefix={arXiv},
870
+ primaryClass={cs.CL}
871
+ }
872
+ ```
873
+
874
+ <!--
875
+ ## Glossary
876
+
877
+ *Clearly define terms in order to be accessible across audiences.*
878
+ -->
879
+
880
+ <!--
881
+ ## Model Card Authors
882
+
883
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
884
+ -->
885
+
886
+ <!--
887
+ ## Model Card Contact
888
+
889
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
890
+ -->
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BAAI/bge-base-en-v1.5",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.41.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30522
32
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.0",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.1.2+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91bef22259c8fd9581db2afdc97e854a816c6a0d3c879dfc721ae698bc8929d4
3
+ size 437951328
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": true
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff