MugheesAwan11 commited on
Commit
da0b33e
1 Parent(s): 222d680

Add new SentenceTransformer model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": 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 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BAAI/bge-base-en-v1.5
3
+ datasets: []
4
+ language:
5
+ - en
6
+ library_name: sentence-transformers
7
+ license: apache-2.0
8
+ metrics:
9
+ - cosine_accuracy@1
10
+ - cosine_accuracy@3
11
+ - cosine_accuracy@5
12
+ - cosine_accuracy@10
13
+ - cosine_precision@1
14
+ - cosine_precision@3
15
+ - cosine_precision@5
16
+ - cosine_precision@10
17
+ - cosine_recall@1
18
+ - cosine_recall@3
19
+ - cosine_recall@5
20
+ - cosine_recall@10
21
+ - cosine_ndcg@10
22
+ - cosine_ndcg@100
23
+ - cosine_mrr@10
24
+ - cosine_map@100
25
+ pipeline_tag: sentence-similarity
26
+ tags:
27
+ - sentence-transformers
28
+ - sentence-similarity
29
+ - feature-extraction
30
+ - generated_from_trainer
31
+ - dataset_size:10000
32
+ - loss:MatryoshkaLoss
33
+ - loss:MultipleNegativesRankingLoss
34
+ widget:
35
+ - source_sentence: Enzalutamide ( brand name Xtandi ) is a synthetic non-steroidal
36
+ antiandrogen ( NSAA ) which was developed by the pharmaceutical company Medivation
37
+ for the treatment of metastatic , castration-resistant prostate cancer . Medivation
38
+ has reported up to an 89 % decrease in serum prostate specific antigen ( PSA )
39
+ levels after a month of taking the drug . Research suggests that enzalutamide
40
+ may also be effective in the treatment of certain types of breast cancer . In
41
+ August 2012 , the United States ( U.S. ) Food and Drug Administration ( FDA )
42
+ approved enzalutamide for the treatment of castration-resistant prostate cancer
43
+ .
44
+ sentences:
45
+ - what type of cancer is enzalutamide
46
+ - who is simon cho
47
+ - who is dr william farone
48
+ - source_sentence: Sohel Rana is a Bangladeshi footballer who plays as a midfielder
49
+ . He currently plays for Sheikh Jamal Dhanmondi Club .
50
+ sentences:
51
+ - who is sohel rana
52
+ - who is olympicos
53
+ - who is roberto laserna
54
+ - source_sentence: Qarah Qayeh ( قره قيه , also Romanized as Qareh Qīyeh ) is a village
55
+ in Chaharduli Rural District , Keshavarz District , Shahin Dezh County , West
56
+ Azerbaijan Province , Iran . At the 2006 census , its population was 465 , in
57
+ 93 families .
58
+ sentences:
59
+ - what was the knoxville riot
60
+ - what language is kbif
61
+ - where is qarah qayeh
62
+ - source_sentence: Martin Severin Janus From ( 8 April 1828 -- 6 May 1895 ) was a
63
+ Danish chess master . Born in Nakskov , From received his first education at
64
+ the grammar school of Nykøbing Falster . He entered the army as a volunteer during
65
+ the Prussian-Danish War ( Schleswig-Holstein War of Succession ) , where he served
66
+ in the brigade of Major-General Olaf Rye and partook in the Battle of Fredericia
67
+ on July 6 , 1849 . After the war From settled in Copenhagen . He was employed
68
+ by the Statistical Bureau , where he met Magnus Oscar Møllerstrøm , then the strongest
69
+ chess player in Copenhagen . Next , he worked in the central office for prison
70
+ management , and in 1890 he became an inspector of the penitentiary of Christianshavn
71
+ . In 1891 he received the order Ridder af Dannebrog ( `` Knight of the Danish
72
+ cloth '' , i.e. flag of Denmark ) , which is the second highest of Danish orders
73
+ . In 1895 Severin From died of cancer . He is interred at Vestre Cemetery ,
74
+ Copenhagen .
75
+ sentences:
76
+ - when did martin from die
77
+ - what is hymenoxys lemmonii
78
+ - where is macomb square il
79
+ - source_sentence: The Recession of 1937 -- 1938 was an economic downturn that occurred
80
+ during the Great Depression in the United States . By the spring of 1937 , production
81
+ , profits , and wages had regained their 1929 levels . Unemployment remained high
82
+ , but it was slightly lower than the 25 % rate seen in 1933 . The American economy
83
+ took a sharp downturn in mid-1937 , lasting for 13 months through most of 1938
84
+ . Industrial production declined almost 30 percent and production of durable goods
85
+ fell even faster . Unemployment jumped from 14.3 % in 1937 to 19.0 % in 1938
86
+ . Manufacturing output fell by 37 % from the 1937 peak and was back to 1934 levels
87
+ . Producers reduced their expenditures on durable goods , and inventories declined
88
+ , but personal income was only 15 % lower than it had been at the peak in 1937
89
+ . In most sectors , hourly earnings continued to rise throughout the recession
90
+ , which partly compensated for the reduction in the number of hours worked . As
91
+ unemployment rose , consumers expenditures declined , thereby leading to further
92
+ cutbacks in production .
93
+ sentences:
94
+ - when did the great depression peak in the u.s. economy?
95
+ - what is tom mount's specialty
96
+ - where is poulton
97
+ model-index:
98
+ - name: SentenceTransformer based on BAAI/bge-base-en-v1.5
99
+ results:
100
+ - task:
101
+ type: information-retrieval
102
+ name: Information Retrieval
103
+ dataset:
104
+ name: dim 768
105
+ type: dim_768
106
+ metrics:
107
+ - type: cosine_accuracy@1
108
+ value: 0.906
109
+ name: Cosine Accuracy@1
110
+ - type: cosine_accuracy@3
111
+ value: 0.954
112
+ name: Cosine Accuracy@3
113
+ - type: cosine_accuracy@5
114
+ value: 0.962
115
+ name: Cosine Accuracy@5
116
+ - type: cosine_accuracy@10
117
+ value: 0.975
118
+ name: Cosine Accuracy@10
119
+ - type: cosine_precision@1
120
+ value: 0.906
121
+ name: Cosine Precision@1
122
+ - type: cosine_precision@3
123
+ value: 0.31799999999999995
124
+ name: Cosine Precision@3
125
+ - type: cosine_precision@5
126
+ value: 0.19240000000000004
127
+ name: Cosine Precision@5
128
+ - type: cosine_precision@10
129
+ value: 0.09750000000000003
130
+ name: Cosine Precision@10
131
+ - type: cosine_recall@1
132
+ value: 0.906
133
+ name: Cosine Recall@1
134
+ - type: cosine_recall@3
135
+ value: 0.954
136
+ name: Cosine Recall@3
137
+ - type: cosine_recall@5
138
+ value: 0.962
139
+ name: Cosine Recall@5
140
+ - type: cosine_recall@10
141
+ value: 0.975
142
+ name: Cosine Recall@10
143
+ - type: cosine_ndcg@10
144
+ value: 0.9422297521305668
145
+ name: Cosine Ndcg@10
146
+ - type: cosine_ndcg@100
147
+ value: 0.9458947974911144
148
+ name: Cosine Ndcg@100
149
+ - type: cosine_mrr@10
150
+ value: 0.9315763888888889
151
+ name: Cosine Mrr@10
152
+ - type: cosine_map@100
153
+ value: 0.9323383888065935
154
+ name: Cosine Map@100
155
+ ---
156
+
157
+ # SentenceTransformer based on BAAI/bge-base-en-v1.5
158
+
159
+ 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). 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.
160
+
161
+ ## Model Details
162
+
163
+ ### Model Description
164
+ - **Model Type:** Sentence Transformer
165
+ - **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
166
+ - **Maximum Sequence Length:** 512 tokens
167
+ - **Output Dimensionality:** 768 tokens
168
+ - **Similarity Function:** Cosine Similarity
169
+ <!-- - **Training Dataset:** Unknown -->
170
+ - **Language:** en
171
+ - **License:** apache-2.0
172
+
173
+ ### Model Sources
174
+
175
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
176
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
177
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
178
+
179
+ ### Full Model Architecture
180
+
181
+ ```
182
+ SentenceTransformer(
183
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
184
+ (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})
185
+ (2): Normalize()
186
+ )
187
+ ```
188
+
189
+ ## Usage
190
+
191
+ ### Direct Usage (Sentence Transformers)
192
+
193
+ First install the Sentence Transformers library:
194
+
195
+ ```bash
196
+ pip install -U sentence-transformers
197
+ ```
198
+
199
+ Then you can load this model and run inference.
200
+ ```python
201
+ from sentence_transformers import SentenceTransformer
202
+
203
+ # Download from the 🤗 Hub
204
+ model = SentenceTransformer("MugheesAwan11/bge-base-climate_fever-dataset-10k-2k-e2")
205
+ # Run inference
206
+ sentences = [
207
+ 'The Recession of 1937 -- 1938 was an economic downturn that occurred during the Great Depression in the United States . By the spring of 1937 , production , profits , and wages had regained their 1929 levels . Unemployment remained high , but it was slightly lower than the 25 % rate seen in 1933 . The American economy took a sharp downturn in mid-1937 , lasting for 13 months through most of 1938 . Industrial production declined almost 30 percent and production of durable goods fell even faster . Unemployment jumped from 14.3 % in 1937 to 19.0 % in 1938 . Manufacturing output fell by 37 % from the 1937 peak and was back to 1934 levels . Producers reduced their expenditures on durable goods , and inventories declined , but personal income was only 15 % lower than it had been at the peak in 1937 . In most sectors , hourly earnings continued to rise throughout the recession , which partly compensated for the reduction in the number of hours worked . As unemployment rose , consumers expenditures declined , thereby leading to further cutbacks in production .',
208
+ 'when did the great depression peak in the u.s. economy?',
209
+ 'where is poulton',
210
+ ]
211
+ embeddings = model.encode(sentences)
212
+ print(embeddings.shape)
213
+ # [3, 768]
214
+
215
+ # Get the similarity scores for the embeddings
216
+ similarities = model.similarity(embeddings, embeddings)
217
+ print(similarities.shape)
218
+ # [3, 3]
219
+ ```
220
+
221
+ <!--
222
+ ### Direct Usage (Transformers)
223
+
224
+ <details><summary>Click to see the direct usage in Transformers</summary>
225
+
226
+ </details>
227
+ -->
228
+
229
+ <!--
230
+ ### Downstream Usage (Sentence Transformers)
231
+
232
+ You can finetune this model on your own dataset.
233
+
234
+ <details><summary>Click to expand</summary>
235
+
236
+ </details>
237
+ -->
238
+
239
+ <!--
240
+ ### Out-of-Scope Use
241
+
242
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
243
+ -->
244
+
245
+ ## Evaluation
246
+
247
+ ### Metrics
248
+
249
+ #### Information Retrieval
250
+ * Dataset: `dim_768`
251
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
252
+
253
+ | Metric | Value |
254
+ |:--------------------|:-----------|
255
+ | cosine_accuracy@1 | 0.906 |
256
+ | cosine_accuracy@3 | 0.954 |
257
+ | cosine_accuracy@5 | 0.962 |
258
+ | cosine_accuracy@10 | 0.975 |
259
+ | cosine_precision@1 | 0.906 |
260
+ | cosine_precision@3 | 0.318 |
261
+ | cosine_precision@5 | 0.1924 |
262
+ | cosine_precision@10 | 0.0975 |
263
+ | cosine_recall@1 | 0.906 |
264
+ | cosine_recall@3 | 0.954 |
265
+ | cosine_recall@5 | 0.962 |
266
+ | cosine_recall@10 | 0.975 |
267
+ | cosine_ndcg@10 | 0.9422 |
268
+ | cosine_ndcg@100 | 0.9459 |
269
+ | cosine_mrr@10 | 0.9316 |
270
+ | **cosine_map@100** | **0.9323** |
271
+
272
+ <!--
273
+ ## Bias, Risks and Limitations
274
+
275
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
276
+ -->
277
+
278
+ <!--
279
+ ### Recommendations
280
+
281
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
282
+ -->
283
+
284
+ ## Training Details
285
+
286
+ ### Training Dataset
287
+
288
+ #### Unnamed Dataset
289
+
290
+
291
+ * Size: 10,000 training samples
292
+ * Columns: <code>positive</code> and <code>anchor</code>
293
+ * Approximate statistics based on the first 1000 samples:
294
+ | | positive | anchor |
295
+ |:--------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
296
+ | type | string | string |
297
+ | details | <ul><li>min: 2 tokens</li><li>mean: 116.45 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.6 tokens</li><li>max: 19 tokens</li></ul> |
298
+ * Samples:
299
+ | positive | anchor |
300
+ |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------|
301
+ | <code>Professor Maurice Cockrill , RA , FBA ( 8 October 1936 -- 1 December 2013 ) was a British painter and poet . Born in Hartlepool , County Durham , he studied at Wrexham School of Art , north east Wales , then Denbigh Technical College and later the University of Reading from 1960 -- 64 . In Liverpool , where he lived for nearly twenty years from 1964 , he taught at Liverpool College of Art and Liverpool Polytechnic . He was a central figure in Liverpool 's artistic life , regularly exhibiting at the Walker Art Gallery , before his departure for London in 1982 . Cockrill 's Liverpool work was in line with that of John Baum , Sam Walsh and Adrian Henri , employing Pop and Photo-Realist styles , but later he moved towards Romantic Expressionism , as it was shown in his retrospective at the Walker Art Gallery , Liverpool in 1995 . His poetry was published in magazines such as `` Ambit '' and `` Poetry Review '' . He was formerly the Keeper of the Royal Academy , and as such managed the RA Schools of the Establishment as well as being a member of the Board and Executive Committee .</code> | <code>who was maurice cockrill</code> |
302
+ | <code>Nowa Dąbrowa -LSB- ` nowa-dom ` browa -RSB- is a village in the administrative district of Gmina Kwilcz , within Międzychód County , Greater Poland Voivodeship , in west-central Poland . It lies approximately 16 km south-east of Międzychód and 59 km west of the regional capital Poznań . The village has a population of 40 .</code> | <code>where is nowa dbrowa poland</code> |
303
+ | <code>Hymenoxys lemmonii is a species of flowering plant in the daisy family known by the common names Lemmon 's rubberweed , Lemmon 's bitterweed , and alkali hymenoxys . It is native to the western United States in and around the Great Basin in Utah , Nevada , northern California , and southeastern Oregon . Hymenoxys lemmonii is a biennial or perennial herb with one or more branching stems growing erect to a maximum height near 50 centimeters ( 20 inches ) . It produces straight , dark green leaves up to 9 centimeters ( 3.6 inches ) long and divided into a number of narrow , pointed lobes . The foliage and stem may be hairless to quite woolly . The daisy-like flower head is generally at least 1.5 centimeters ( 0.6 inches ) wide , with a center of 50 -- 125 thick golden disc florets and a shaggy fringe of 9 -- 12 golden ray florets . The species is named for John Gill Lemmon , husband of prominent American botanist Sarah Plummer Lemmon .</code> | <code>what is hymenoxys lemmonii</code> |
304
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
305
+ ```json
306
+ {
307
+ "loss": "MultipleNegativesRankingLoss",
308
+ "matryoshka_dims": [
309
+ 768
310
+ ],
311
+ "matryoshka_weights": [
312
+ 1
313
+ ],
314
+ "n_dims_per_step": -1
315
+ }
316
+ ```
317
+
318
+ ### Training Hyperparameters
319
+ #### Non-Default Hyperparameters
320
+
321
+ - `eval_strategy`: epoch
322
+ - `per_device_train_batch_size`: 32
323
+ - `per_device_eval_batch_size`: 16
324
+ - `learning_rate`: 2e-05
325
+ - `num_train_epochs`: 2
326
+ - `lr_scheduler_type`: cosine
327
+ - `warmup_ratio`: 0.1
328
+ - `bf16`: True
329
+ - `tf32`: True
330
+ - `load_best_model_at_end`: True
331
+ - `optim`: adamw_torch_fused
332
+ - `batch_sampler`: no_duplicates
333
+
334
+ #### All Hyperparameters
335
+ <details><summary>Click to expand</summary>
336
+
337
+ - `overwrite_output_dir`: False
338
+ - `do_predict`: False
339
+ - `eval_strategy`: epoch
340
+ - `prediction_loss_only`: True
341
+ - `per_device_train_batch_size`: 32
342
+ - `per_device_eval_batch_size`: 16
343
+ - `per_gpu_train_batch_size`: None
344
+ - `per_gpu_eval_batch_size`: None
345
+ - `gradient_accumulation_steps`: 1
346
+ - `eval_accumulation_steps`: None
347
+ - `learning_rate`: 2e-05
348
+ - `weight_decay`: 0.0
349
+ - `adam_beta1`: 0.9
350
+ - `adam_beta2`: 0.999
351
+ - `adam_epsilon`: 1e-08
352
+ - `max_grad_norm`: 1.0
353
+ - `num_train_epochs`: 2
354
+ - `max_steps`: -1
355
+ - `lr_scheduler_type`: cosine
356
+ - `lr_scheduler_kwargs`: {}
357
+ - `warmup_ratio`: 0.1
358
+ - `warmup_steps`: 0
359
+ - `log_level`: passive
360
+ - `log_level_replica`: warning
361
+ - `log_on_each_node`: True
362
+ - `logging_nan_inf_filter`: True
363
+ - `save_safetensors`: True
364
+ - `save_on_each_node`: False
365
+ - `save_only_model`: False
366
+ - `restore_callback_states_from_checkpoint`: False
367
+ - `no_cuda`: False
368
+ - `use_cpu`: False
369
+ - `use_mps_device`: False
370
+ - `seed`: 42
371
+ - `data_seed`: None
372
+ - `jit_mode_eval`: False
373
+ - `use_ipex`: False
374
+ - `bf16`: True
375
+ - `fp16`: False
376
+ - `fp16_opt_level`: O1
377
+ - `half_precision_backend`: auto
378
+ - `bf16_full_eval`: False
379
+ - `fp16_full_eval`: False
380
+ - `tf32`: True
381
+ - `local_rank`: 0
382
+ - `ddp_backend`: None
383
+ - `tpu_num_cores`: None
384
+ - `tpu_metrics_debug`: False
385
+ - `debug`: []
386
+ - `dataloader_drop_last`: False
387
+ - `dataloader_num_workers`: 0
388
+ - `dataloader_prefetch_factor`: None
389
+ - `past_index`: -1
390
+ - `disable_tqdm`: False
391
+ - `remove_unused_columns`: True
392
+ - `label_names`: None
393
+ - `load_best_model_at_end`: True
394
+ - `ignore_data_skip`: False
395
+ - `fsdp`: []
396
+ - `fsdp_min_num_params`: 0
397
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
398
+ - `fsdp_transformer_layer_cls_to_wrap`: None
399
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
400
+ - `deepspeed`: None
401
+ - `label_smoothing_factor`: 0.0
402
+ - `optim`: adamw_torch_fused
403
+ - `optim_args`: None
404
+ - `adafactor`: False
405
+ - `group_by_length`: False
406
+ - `length_column_name`: length
407
+ - `ddp_find_unused_parameters`: None
408
+ - `ddp_bucket_cap_mb`: None
409
+ - `ddp_broadcast_buffers`: False
410
+ - `dataloader_pin_memory`: True
411
+ - `dataloader_persistent_workers`: False
412
+ - `skip_memory_metrics`: True
413
+ - `use_legacy_prediction_loop`: False
414
+ - `push_to_hub`: False
415
+ - `resume_from_checkpoint`: None
416
+ - `hub_model_id`: None
417
+ - `hub_strategy`: every_save
418
+ - `hub_private_repo`: False
419
+ - `hub_always_push`: False
420
+ - `gradient_checkpointing`: False
421
+ - `gradient_checkpointing_kwargs`: None
422
+ - `include_inputs_for_metrics`: False
423
+ - `eval_do_concat_batches`: True
424
+ - `fp16_backend`: auto
425
+ - `push_to_hub_model_id`: None
426
+ - `push_to_hub_organization`: None
427
+ - `mp_parameters`:
428
+ - `auto_find_batch_size`: False
429
+ - `full_determinism`: False
430
+ - `torchdynamo`: None
431
+ - `ray_scope`: last
432
+ - `ddp_timeout`: 1800
433
+ - `torch_compile`: False
434
+ - `torch_compile_backend`: None
435
+ - `torch_compile_mode`: None
436
+ - `dispatch_batches`: None
437
+ - `split_batches`: None
438
+ - `include_tokens_per_second`: False
439
+ - `include_num_input_tokens_seen`: False
440
+ - `neftune_noise_alpha`: None
441
+ - `optim_target_modules`: None
442
+ - `batch_eval_metrics`: False
443
+ - `batch_sampler`: no_duplicates
444
+ - `multi_dataset_batch_sampler`: proportional
445
+
446
+ </details>
447
+
448
+ ### Training Logs
449
+ | Epoch | Step | Training Loss | dim_768_cosine_map@100 |
450
+ |:-------:|:-------:|:-------------:|:----------------------:|
451
+ | 0.0319 | 10 | 0.1626 | - |
452
+ | 0.0639 | 20 | 0.1168 | - |
453
+ | 0.0958 | 30 | 0.0543 | - |
454
+ | 0.1278 | 40 | 0.1227 | - |
455
+ | 0.1597 | 50 | 0.061 | - |
456
+ | 0.1917 | 60 | 0.0537 | - |
457
+ | 0.2236 | 70 | 0.0693 | - |
458
+ | 0.2556 | 80 | 0.1115 | - |
459
+ | 0.2875 | 90 | 0.0541 | - |
460
+ | 0.3195 | 100 | 0.0774 | - |
461
+ | 0.3514 | 110 | 0.0639 | - |
462
+ | 0.3834 | 120 | 0.0639 | - |
463
+ | 0.4153 | 130 | 0.0567 | - |
464
+ | 0.4473 | 140 | 0.0385 | - |
465
+ | 0.4792 | 150 | 0.0452 | - |
466
+ | 0.5112 | 160 | 0.0641 | - |
467
+ | 0.5431 | 170 | 0.042 | - |
468
+ | 0.5751 | 180 | 0.0243 | - |
469
+ | 0.6070 | 190 | 0.0405 | - |
470
+ | 0.6390 | 200 | 0.062 | - |
471
+ | 0.6709 | 210 | 0.0366 | - |
472
+ | 0.7029 | 220 | 0.0399 | - |
473
+ | 0.7348 | 230 | 0.0382 | - |
474
+ | 0.7668 | 240 | 0.0387 | - |
475
+ | 0.7987 | 250 | 0.0575 | - |
476
+ | 0.8307 | 260 | 0.0391 | - |
477
+ | 0.8626 | 270 | 0.0776 | - |
478
+ | 0.8946 | 280 | 0.0258 | - |
479
+ | 0.9265 | 290 | 0.0493 | - |
480
+ | 0.9585 | 300 | 0.037 | - |
481
+ | 0.9904 | 310 | 0.0499 | - |
482
+ | **1.0** | **313** | **-** | **0.9397** |
483
+ | 0.0319 | 10 | 0.0111 | - |
484
+ | 0.0639 | 20 | 0.007 | - |
485
+ | 0.0958 | 30 | 0.0023 | - |
486
+ | 0.1278 | 40 | 0.0109 | - |
487
+ | 0.1597 | 50 | 0.0046 | - |
488
+ | 0.1917 | 60 | 0.0043 | - |
489
+ | 0.2236 | 70 | 0.0037 | - |
490
+ | 0.2556 | 80 | 0.0118 | - |
491
+ | 0.2875 | 90 | 0.0026 | - |
492
+ | 0.3195 | 100 | 0.0079 | - |
493
+ | 0.3514 | 110 | 0.0045 | - |
494
+ | 0.3834 | 120 | 0.0163 | - |
495
+ | 0.4153 | 130 | 0.0058 | - |
496
+ | 0.4473 | 140 | 0.0154 | - |
497
+ | 0.4792 | 150 | 0.0051 | - |
498
+ | 0.5112 | 160 | 0.0152 | - |
499
+ | 0.5431 | 170 | 0.0058 | - |
500
+ | 0.5751 | 180 | 0.0041 | - |
501
+ | 0.6070 | 190 | 0.0118 | - |
502
+ | 0.6390 | 200 | 0.0165 | - |
503
+ | 0.6709 | 210 | 0.0088 | - |
504
+ | 0.7029 | 220 | 0.014 | - |
505
+ | 0.7348 | 230 | 0.0195 | - |
506
+ | 0.7668 | 240 | 0.024 | - |
507
+ | 0.7987 | 250 | 0.0472 | - |
508
+ | 0.8307 | 260 | 0.0341 | - |
509
+ | 0.8626 | 270 | 0.0684 | - |
510
+ | 0.8946 | 280 | 0.0193 | - |
511
+ | 0.9265 | 290 | 0.0488 | - |
512
+ | 0.9585 | 300 | 0.0388 | - |
513
+ | 0.9904 | 310 | 0.0485 | - |
514
+ | **1.0** | **313** | **-** | **0.9349** |
515
+ | 1.0224 | 320 | 0.0119 | - |
516
+ | 1.0543 | 330 | 0.013 | - |
517
+ | 1.0863 | 340 | 0.0024 | - |
518
+ | 1.1182 | 350 | 0.012 | - |
519
+ | 1.1502 | 360 | 0.0042 | - |
520
+ | 1.1821 | 370 | 0.0091 | - |
521
+ | 1.2141 | 380 | 0.0041 | - |
522
+ | 1.2460 | 390 | 0.0096 | - |
523
+ | 1.2780 | 400 | 0.0053 | - |
524
+ | 1.3099 | 410 | 0.0043 | - |
525
+ | 1.3419 | 420 | 0.0059 | - |
526
+ | 1.3738 | 430 | 0.0138 | - |
527
+ | 1.4058 | 440 | 0.0132 | - |
528
+ | 1.4377 | 450 | 0.0124 | - |
529
+ | 1.4696 | 460 | 0.0049 | - |
530
+ | 1.5016 | 470 | 0.0043 | - |
531
+ | 1.5335 | 480 | 0.0045 | - |
532
+ | 1.5655 | 490 | 0.0037 | - |
533
+ | 1.5974 | 500 | 0.0081 | - |
534
+ | 1.6294 | 510 | 0.0038 | - |
535
+ | 1.6613 | 520 | 0.0055 | - |
536
+ | 1.6933 | 530 | 0.003 | - |
537
+ | 1.7252 | 540 | 0.0022 | - |
538
+ | 1.7572 | 550 | 0.0042 | - |
539
+ | 1.7891 | 560 | 0.0158 | - |
540
+ | 1.8211 | 570 | 0.0088 | - |
541
+ | 1.8530 | 580 | 0.0154 | - |
542
+ | 1.8850 | 590 | 0.0057 | - |
543
+ | 1.9169 | 600 | 0.0086 | - |
544
+ | 1.9489 | 610 | 0.0069 | - |
545
+ | 1.9808 | 620 | 0.0076 | - |
546
+ | 2.0 | 626 | - | 0.9323 |
547
+
548
+ * The bold row denotes the saved checkpoint.
549
+
550
+ ### Framework Versions
551
+ - Python: 3.10.14
552
+ - Sentence Transformers: 3.0.1
553
+ - Transformers: 4.41.2
554
+ - PyTorch: 2.1.2+cu121
555
+ - Accelerate: 0.31.0
556
+ - Datasets: 2.19.1
557
+ - Tokenizers: 0.19.1
558
+
559
+ ## Citation
560
+
561
+ ### BibTeX
562
+
563
+ #### Sentence Transformers
564
+ ```bibtex
565
+ @inproceedings{reimers-2019-sentence-bert,
566
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
567
+ author = "Reimers, Nils and Gurevych, Iryna",
568
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
569
+ month = "11",
570
+ year = "2019",
571
+ publisher = "Association for Computational Linguistics",
572
+ url = "https://arxiv.org/abs/1908.10084",
573
+ }
574
+ ```
575
+
576
+ #### MatryoshkaLoss
577
+ ```bibtex
578
+ @misc{kusupati2024matryoshka,
579
+ title={Matryoshka Representation Learning},
580
+ 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},
581
+ year={2024},
582
+ eprint={2205.13147},
583
+ archivePrefix={arXiv},
584
+ primaryClass={cs.LG}
585
+ }
586
+ ```
587
+
588
+ #### MultipleNegativesRankingLoss
589
+ ```bibtex
590
+ @misc{henderson2017efficient,
591
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
592
+ 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},
593
+ year={2017},
594
+ eprint={1705.00652},
595
+ archivePrefix={arXiv},
596
+ primaryClass={cs.CL}
597
+ }
598
+ ```
599
+
600
+ <!--
601
+ ## Glossary
602
+
603
+ *Clearly define terms in order to be accessible across audiences.*
604
+ -->
605
+
606
+ <!--
607
+ ## Model Card Authors
608
+
609
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
610
+ -->
611
+
612
+ <!--
613
+ ## Model Card Contact
614
+
615
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
616
+ -->
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": "3.0.1",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.1.2+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee3075ea0530ffc64ed00cc2c79521f3ac0362395f8ce932637df2586bb26876
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