Hugging Face's logo

fpc
/
bge-micro-smiles

Sentence Similarity
sentence-transformers
ONNX
Safetensors
English
bert
feature-extraction
Generated from Trainer
dataset_size:3210255
loss:CachedMultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
ferris commited on
Commit
82971ba
·
1 Parent(s): 85423af

v0.1.0

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +650 -3
  3. config.json +31 -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 +44 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +71 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md CHANGED
@@ -1,3 +1,650 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: TaylorAI/bge-micro
3
+ datasets: []
4
+ language:
5
+ - en
6
+ library_name: sentence-transformers
7
+ license: apache-2.0
8
+ metrics:
9
+ - pearson_cosine
10
+ - spearman_cosine
11
+ - pearson_manhattan
12
+ - spearman_manhattan
13
+ - pearson_euclidean
14
+ - spearman_euclidean
15
+ - pearson_dot
16
+ - spearman_dot
17
+ - pearson_max
18
+ - spearman_max
19
+ pipeline_tag: sentence-similarity
20
+ tags:
21
+ - sentence-transformers
22
+ - sentence-similarity
23
+ - feature-extraction
24
+ - generated_from_trainer
25
+ - dataset_size:3210255
26
+ - loss:CachedMultipleNegativesRankingLoss
27
+ widget:
28
+ - source_sentence: donepezil hydrochloride monohydrate
29
+ sentences:
30
+ - Cn1nccc1[C@H]1CC[C@H](O[Si](C)(C)C(C)(C)C)C[C@@H]1OC(=O)c1ccccc1
31
+ - COc1cc2c(cc1OC)C(=O)C(CC1CCN(Cc3ccccc3)CC1)C2.Cl.O
32
+ - C(=O)(OC)C1=CC=C(C=C1)CC(C)=O
33
+ - source_sentence: 6-Cyclopropylmethoxy-5-(3,3-difluoro-azetidin-1-yl)-pyridine-2-carboxylic
34
+ acid tert-butyl-(5-methyl-[1,3,4]oxadiazol-2-ylmethyl)-amide
35
+ sentences:
36
+ - Cc1nnc(CN(C(=O)c2ccc(N3CC(F)(F)C3)c(OCC3CC3)n2)C(C)(C)C)o1
37
+ - COc1cccc(CCCC=C(Br)Br)c1
38
+ - CN(C)CCNC(=O)c1ccc2oc(=O)n(Cc3ccc4[nH]c(=O)[nH]c4c3)c2c1
39
+ - source_sentence: N-(2-chlorophenyl)-6,8-difluoro-N-methyl-4H-thieno[3,2-c]chromene-2-carboxamide
40
+ sentences:
41
+ - CN(C(=O)c1cc2c(s1)-c1cc(F)cc(F)c1OC2)c1ccccc1Cl
42
+ - ClC(C(=O)OCCOCC1=CC=C(C=C1)F)C
43
+ - C(C)OC(\C=C(/C)\OC1=C(C(=CC=C1F)OC(C)C)F)=O
44
+ - source_sentence: 6-[2-[(3-chlorophenyl)methyl]-1,3,3a,4,6,6a-hexahydropyrrolo[3,4-c]pyrrol-5-yl]-3-(trifluoromethyl)-[1,2,4]triazolo[4,3-b]pyridazine
45
+ sentences:
46
+ - CC(=O)OCCOCn1cc(C)c(=O)[nH]c1=O
47
+ - NC1=C(C(=NN1C1=C(C=C(C=C1Cl)C(F)(F)F)Cl)C#N)S(=O)(=O)C
48
+ - ClC=1C=C(C=CC1)CN1CC2CN(CC2C1)C=1C=CC=2N(N1)C(=NN2)C(F)(F)F
49
+ - source_sentence: (±)-cis-2-(4-methoxyphenyl)-3-acetoxy-5-[2-(dimethylamino)ethyl]-8-chloro-2,3-dihydro-1,5-benzothiazepin-4(5H)-one
50
+ hydrochloride
51
+ sentences:
52
+ - N(=[N+]=[N-])C(C(=O)C1=NC(=C(C(=N1)C(C)(C)C)O)C(C)(C)C)C
53
+ - O[C@@H]1[C@H](O)[C@@H](Oc2nc(N3CCNCC3)nc3ccccc23)C[C@H]1O
54
+ - Cl.COC1=CC=C(C=C1)[C@@H]1SC2=C(N(C([C@@H]1OC(C)=O)=O)CCN(C)C)C=CC(=C2)Cl
55
+ model-index:
56
+ - name: MPNet base trained on AllNLI triplets
57
+ results:
58
+ - task:
59
+ type: semantic-similarity
60
+ name: Semantic Similarity
61
+ dataset:
62
+ name: bge micro test
63
+ type: bge-micro-test
64
+ metrics:
65
+ - type: pearson_cosine
66
+ value: .nan
67
+ name: Pearson Cosine
68
+ - type: spearman_cosine
69
+ value: .nan
70
+ name: Spearman Cosine
71
+ - type: pearson_manhattan
72
+ value: .nan
73
+ name: Pearson Manhattan
74
+ - type: spearman_manhattan
75
+ value: .nan
76
+ name: Spearman Manhattan
77
+ - type: pearson_euclidean
78
+ value: .nan
79
+ name: Pearson Euclidean
80
+ - type: spearman_euclidean
81
+ value: .nan
82
+ name: Spearman Euclidean
83
+ - type: pearson_dot
84
+ value: .nan
85
+ name: Pearson Dot
86
+ - type: spearman_dot
87
+ value: .nan
88
+ name: Spearman Dot
89
+ - type: pearson_max
90
+ value: .nan
91
+ name: Pearson Max
92
+ - type: spearman_max
93
+ value: .nan
94
+ name: Spearman Max
95
+ ---
96
+
97
+ # MPNet base trained on AllNLI triplets
98
+
99
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [TaylorAI/bge-micro](https://huggingface.co/TaylorAI/bge-micro). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
100
+
101
+ ## Model Details
102
+
103
+ ### Model Description
104
+ - **Model Type:** Sentence Transformer
105
+ - **Base model:** [TaylorAI/bge-micro](https://huggingface.co/TaylorAI/bge-micro) <!-- at revision 4bccbd43513eb9fecf444af6eecde76e55f4c839 -->
106
+ - **Maximum Sequence Length:** 512 tokens
107
+ - **Output Dimensionality:** 384 tokens
108
+ - **Similarity Function:** Cosine Similarity
109
+ <!-- - **Training Dataset:** Unknown -->
110
+ - **Language:** en
111
+ - **License:** apache-2.0
112
+
113
+ ### Model Sources
114
+
115
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
116
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
117
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
118
+
119
+ ### Full Model Architecture
120
+
121
+ ```
122
+ SentenceTransformer(
123
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
124
+ (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
125
+ )
126
+ ```
127
+
128
+ ## Usage
129
+
130
+ ### Direct Usage (Sentence Transformers)
131
+
132
+ First install the Sentence Transformers library:
133
+
134
+ ```bash
135
+ pip install -U sentence-transformers
136
+ ```
137
+
138
+ Then you can load this model and run inference.
139
+ ```python
140
+ from sentence_transformers import SentenceTransformer
141
+
142
+ # Download from the 🤗 Hub
143
+ model = SentenceTransformer("fpc/bge-micro-smiles")
144
+ # Run inference
145
+ sentences = [
146
+ '(±)-cis-2-(4-methoxyphenyl)-3-acetoxy-5-[2-(dimethylamino)ethyl]-8-chloro-2,3-dihydro-1,5-benzothiazepin-4(5H)-one hydrochloride',
147
+ 'Cl.COC1=CC=C(C=C1)[C@@H]1SC2=C(N(C([C@@H]1OC(C)=O)=O)CCN(C)C)C=CC(=C2)Cl',
148
+ 'O[C@@H]1[C@H](O)[C@@H](Oc2nc(N3CCNCC3)nc3ccccc23)C[C@H]1O',
149
+ ]
150
+ embeddings = model.encode(sentences)
151
+ print(embeddings.shape)
152
+ # [3, 384]
153
+
154
+ # Get the similarity scores for the embeddings
155
+ similarities = model.similarity(embeddings, embeddings)
156
+ print(similarities.shape)
157
+ # [3, 3]
158
+ ```
159
+
160
+ <!--
161
+ ### Direct Usage (Transformers)
162
+
163
+ <details><summary>Click to see the direct usage in Transformers</summary>
164
+
165
+ </details>
166
+ -->
167
+
168
+ <!--
169
+ ### Downstream Usage (Sentence Transformers)
170
+
171
+ You can finetune this model on your own dataset.
172
+
173
+ <details><summary>Click to expand</summary>
174
+
175
+ </details>
176
+ -->
177
+
178
+ <!--
179
+ ### Out-of-Scope Use
180
+
181
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
182
+ -->
183
+
184
+
185
+ ## Training Details
186
+
187
+ ### Training Dataset
188
+
189
+ #### Unnamed Dataset
190
+
191
+
192
+ * Size: 3,210,255 training samples
193
+ * Columns: <code>anchor</code> and <code>positive</code>
194
+ * Approximate statistics based on the first 1000 samples:
195
+ | | anchor | positive |
196
+ |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
197
+ | type | string | string |
198
+ | details | <ul><li>min: 5 tokens</li><li>mean: 42.57 tokens</li><li>max: 153 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 40.02 tokens</li><li>max: 325 tokens</li></ul> |
199
+ * Samples:
200
+ | anchor | positive |
201
+ |:--------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|
202
+ | <code>4-t-butylbromobenzene</code> | <code>C(C)(C)(C)C1=CC=C(C=C1)Br</code> |
203
+ | <code>1-methyl-4-(morpholine-4-carbonyl)-N-(2-phenyl-[1,2,4]triazolo[1,5-a]pyridin-7-yl)-1H-pyrazole-5-carboxamide</code> | <code>CN1N=CC(=C1C(=O)NC1=CC=2N(C=C1)N=C(N2)C2=CC=CC=C2)C(=O)N2CCOCC2</code> |
204
+ | <code>Phthalimide</code> | <code>C1(C=2C(C(N1)=O)=CC=CC2)=O</code> |
205
+ * Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
206
+ ```json
207
+ {
208
+ "scale": 20.0,
209
+ "similarity_fct": "cos_sim"
210
+ }
211
+ ```
212
+
213
+ ### Training Hyperparameters
214
+ #### Non-Default Hyperparameters
215
+
216
+ - `per_device_train_batch_size`: 512
217
+ - `learning_rate`: 2e-05
218
+ - `num_train_epochs`: 4
219
+ - `warmup_ratio`: 0.1
220
+ - `bf16`: True
221
+ - `batch_sampler`: no_duplicates
222
+
223
+ #### All Hyperparameters
224
+ <details><summary>Click to expand</summary>
225
+
226
+ - `overwrite_output_dir`: False
227
+ - `do_predict`: False
228
+ - `eval_strategy`: no
229
+ - `prediction_loss_only`: True
230
+ - `per_device_train_batch_size`: 512
231
+ - `per_device_eval_batch_size`: 8
232
+ - `per_gpu_train_batch_size`: None
233
+ - `per_gpu_eval_batch_size`: None
234
+ - `gradient_accumulation_steps`: 1
235
+ - `eval_accumulation_steps`: None
236
+ - `learning_rate`: 2e-05
237
+ - `weight_decay`: 0.0
238
+ - `adam_beta1`: 0.9
239
+ - `adam_beta2`: 0.999
240
+ - `adam_epsilon`: 1e-08
241
+ - `max_grad_norm`: 1.0
242
+ - `num_train_epochs`: 4
243
+ - `max_steps`: -1
244
+ - `lr_scheduler_type`: linear
245
+ - `lr_scheduler_kwargs`: {}
246
+ - `warmup_ratio`: 0.1
247
+ - `warmup_steps`: 0
248
+ - `log_level`: passive
249
+ - `log_level_replica`: warning
250
+ - `log_on_each_node`: True
251
+ - `logging_nan_inf_filter`: True
252
+ - `save_safetensors`: True
253
+ - `save_on_each_node`: False
254
+ - `save_only_model`: False
255
+ - `restore_callback_states_from_checkpoint`: False
256
+ - `no_cuda`: False
257
+ - `use_cpu`: False
258
+ - `use_mps_device`: False
259
+ - `seed`: 42
260
+ - `data_seed`: None
261
+ - `jit_mode_eval`: False
262
+ - `use_ipex`: False
263
+ - `bf16`: True
264
+ - `fp16`: False
265
+ - `fp16_opt_level`: O1
266
+ - `half_precision_backend`: auto
267
+ - `bf16_full_eval`: False
268
+ - `fp16_full_eval`: False
269
+ - `tf32`: None
270
+ - `local_rank`: 0
271
+ - `ddp_backend`: None
272
+ - `tpu_num_cores`: None
273
+ - `tpu_metrics_debug`: False
274
+ - `debug`: []
275
+ - `dataloader_drop_last`: False
276
+ - `dataloader_num_workers`: 0
277
+ - `dataloader_prefetch_factor`: None
278
+ - `past_index`: -1
279
+ - `disable_tqdm`: False
280
+ - `remove_unused_columns`: True
281
+ - `label_names`: None
282
+ - `load_best_model_at_end`: False
283
+ - `ignore_data_skip`: False
284
+ - `fsdp`: []
285
+ - `fsdp_min_num_params`: 0
286
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
287
+ - `fsdp_transformer_layer_cls_to_wrap`: None
288
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
289
+ - `deepspeed`: None
290
+ - `label_smoothing_factor`: 0.0
291
+ - `optim`: adamw_torch
292
+ - `optim_args`: None
293
+ - `adafactor`: False
294
+ - `group_by_length`: False
295
+ - `length_column_name`: length
296
+ - `ddp_find_unused_parameters`: None
297
+ - `ddp_bucket_cap_mb`: None
298
+ - `ddp_broadcast_buffers`: False
299
+ - `dataloader_pin_memory`: True
300
+ - `dataloader_persistent_workers`: False
301
+ - `skip_memory_metrics`: True
302
+ - `use_legacy_prediction_loop`: False
303
+ - `push_to_hub`: False
304
+ - `resume_from_checkpoint`: None
305
+ - `hub_model_id`: None
306
+ - `hub_strategy`: every_save
307
+ - `hub_private_repo`: False
308
+ - `hub_always_push`: False
309
+ - `gradient_checkpointing`: False
310
+ - `gradient_checkpointing_kwargs`: None
311
+ - `include_inputs_for_metrics`: False
312
+ - `eval_do_concat_batches`: True
313
+ - `fp16_backend`: auto
314
+ - `push_to_hub_model_id`: None
315
+ - `push_to_hub_organization`: None
316
+ - `mp_parameters`:
317
+ - `auto_find_batch_size`: False
318
+ - `full_determinism`: False
319
+ - `torchdynamo`: None
320
+ - `ray_scope`: last
321
+ - `ddp_timeout`: 1800
322
+ - `torch_compile`: False
323
+ - `torch_compile_backend`: None
324
+ - `torch_compile_mode`: None
325
+ - `dispatch_batches`: None
326
+ - `split_batches`: None
327
+ - `include_tokens_per_second`: False
328
+ - `include_num_input_tokens_seen`: False
329
+ - `neftune_noise_alpha`: None
330
+ - `optim_target_modules`: None
331
+ - `batch_eval_metrics`: False
332
+ - `batch_sampler`: no_duplicates
333
+ - `multi_dataset_batch_sampler`: proportional
334
+
335
+ </details>
336
+
337
+ ### Training Logs
338
+ <details><summary>Click to expand</summary>
339
+
340
+ | Epoch | Step | Training Loss | bge-micro-test_spearman_cosine |
341
+ |:------:|:-----:|:-------------:|:------------------------------:|
342
+ | 0.0159 | 100 | 6.1861 | - |
343
+ | 0.0319 | 200 | 6.0547 | - |
344
+ | 0.0478 | 300 | 5.6041 | - |
345
+ | 0.0638 | 400 | 4.9367 | - |
346
+ | 0.0797 | 500 | 4.3412 | - |
347
+ | 0.0957 | 600 | 3.8245 | - |
348
+ | 0.1116 | 700 | 3.3188 | - |
349
+ | 0.1276 | 800 | 2.869 | - |
350
+ | 0.1435 | 900 | 2.5149 | - |
351
+ | 0.1595 | 1000 | 2.2282 | - |
352
+ | 0.1754 | 1100 | 2.0046 | - |
353
+ | 0.1914 | 1200 | 1.8032 | - |
354
+ | 0.2073 | 1300 | 1.6289 | - |
355
+ | 0.2232 | 1400 | 1.4567 | - |
356
+ | 0.2392 | 1500 | 1.3326 | - |
357
+ | 0.2551 | 1600 | 1.2127 | - |
358
+ | 0.2711 | 1700 | 1.0909 | - |
359
+ | 0.2870 | 1800 | 1.0021 | - |
360
+ | 0.3030 | 1900 | 0.9135 | - |
361
+ | 0.3189 | 2000 | 0.8378 | - |
362
+ | 0.3349 | 2100 | 0.7758 | - |
363
+ | 0.3508 | 2200 | 0.7031 | - |
364
+ | 0.3668 | 2300 | 0.6418 | - |
365
+ | 0.3827 | 2400 | 0.5965 | - |
366
+ | 0.3987 | 2500 | 0.5461 | - |
367
+ | 0.4146 | 2600 | 0.5039 | - |
368
+ | 0.4306 | 2700 | 0.4674 | - |
369
+ | 0.4465 | 2800 | 0.4339 | - |
370
+ | 0.4624 | 2900 | 0.4045 | - |
371
+ | 0.4784 | 3000 | 0.373 | - |
372
+ | 0.4943 | 3100 | 0.3566 | - |
373
+ | 0.5103 | 3200 | 0.3348 | - |
374
+ | 0.5262 | 3300 | 0.3215 | - |
375
+ | 0.5422 | 3400 | 0.302 | - |
376
+ | 0.5581 | 3500 | 0.2826 | - |
377
+ | 0.5741 | 3600 | 0.2803 | - |
378
+ | 0.5900 | 3700 | 0.2616 | - |
379
+ | 0.6060 | 3800 | 0.2554 | - |
380
+ | 0.6219 | 3900 | 0.234 | - |
381
+ | 0.6379 | 4000 | 0.2306 | - |
382
+ | 0.6538 | 4100 | 0.2224 | - |
383
+ | 0.6697 | 4200 | 0.2141 | - |
384
+ | 0.6857 | 4300 | 0.2117 | - |
385
+ | 0.7016 | 4400 | 0.204 | - |
386
+ | 0.7176 | 4500 | 0.198 | - |
387
+ | 0.7335 | 4600 | 0.1986 | - |
388
+ | 0.7495 | 4700 | 0.1821 | - |
389
+ | 0.7654 | 4800 | 0.1813 | - |
390
+ | 0.7814 | 4900 | 0.1741 | - |
391
+ | 0.7973 | 5000 | 0.1697 | - |
392
+ | 0.8133 | 5100 | 0.1655 | - |
393
+ | 0.8292 | 5200 | 0.1623 | - |
394
+ | 0.8452 | 5300 | 0.1593 | - |
395
+ | 0.8611 | 5400 | 0.1566 | - |
396
+ | 0.8771 | 5500 | 0.151 | - |
397
+ | 0.8930 | 5600 | 0.1526 | - |
398
+ | 0.9089 | 5700 | 0.1453 | - |
399
+ | 0.9249 | 5800 | 0.1448 | - |
400
+ | 0.9408 | 5900 | 0.1369 | - |
401
+ | 0.9568 | 6000 | 0.1409 | - |
402
+ | 0.9727 | 6100 | 0.1373 | - |
403
+ | 0.9887 | 6200 | 0.133 | - |
404
+ | 1.0046 | 6300 | 0.1269 | - |
405
+ | 1.0206 | 6400 | 0.1274 | - |
406
+ | 1.0365 | 6500 | 0.1271 | - |
407
+ | 1.0525 | 6600 | 0.1216 | - |
408
+ | 1.0684 | 6700 | 0.1176 | - |
409
+ | 1.0844 | 6800 | 0.1208 | - |
410
+ | 1.1003 | 6900 | 0.1177 | - |
411
+ | 1.1162 | 7000 | 0.1175 | - |
412
+ | 1.1322 | 7100 | 0.1109 | - |
413
+ | 1.1481 | 7200 | 0.1118 | - |
414
+ | 1.1641 | 7300 | 0.1085 | - |
415
+ | 1.1800 | 7400 | 0.1155 | - |
416
+ | 1.1960 | 7500 | 0.1079 | - |
417
+ | 1.2119 | 7600 | 0.1087 | - |
418
+ | 1.2279 | 7700 | 0.1004 | - |
419
+ | 1.2438 | 7800 | 0.1084 | - |
420
+ | 1.2598 | 7900 | 0.1089 | - |
421
+ | 1.2757 | 8000 | 0.1012 | - |
422
+ | 1.2917 | 8100 | 0.1037 | - |
423
+ | 1.3076 | 8200 | 0.1004 | - |
424
+ | 1.3236 | 8300 | 0.0979 | - |
425
+ | 1.3395 | 8400 | 0.1007 | - |
426
+ | 1.3554 | 8500 | 0.0956 | - |
427
+ | 1.3714 | 8600 | 0.0972 | - |
428
+ | 1.3873 | 8700 | 0.0947 | - |
429
+ | 1.4033 | 8800 | 0.0931 | - |
430
+ | 1.4192 | 8900 | 0.0948 | - |
431
+ | 1.4352 | 9000 | 0.0925 | - |
432
+ | 1.4511 | 9100 | 0.0933 | - |
433
+ | 1.4671 | 9200 | 0.0888 | - |
434
+ | 1.4830 | 9300 | 0.0877 | - |
435
+ | 1.4990 | 9400 | 0.0889 | - |
436
+ | 1.5149 | 9500 | 0.0895 | - |
437
+ | 1.5309 | 9600 | 0.0892 | - |
438
+ | 1.5468 | 9700 | 0.089 | - |
439
+ | 1.5627 | 9800 | 0.0828 | - |
440
+ | 1.5787 | 9900 | 0.0906 | - |
441
+ | 1.5946 | 10000 | 0.0893 | - |
442
+ | 1.6106 | 10100 | 0.0849 | - |
443
+ | 1.6265 | 10200 | 0.0811 | - |
444
+ | 1.6425 | 10300 | 0.0823 | - |
445
+ | 1.6584 | 10400 | 0.0806 | - |
446
+ | 1.6744 | 10500 | 0.0815 | - |
447
+ | 1.6903 | 10600 | 0.0832 | - |
448
+ | 1.7063 | 10700 | 0.0856 | - |
449
+ | 1.7222 | 10800 | 0.081 | - |
450
+ | 1.7382 | 10900 | 0.0831 | - |
451
+ | 1.7541 | 11000 | 0.0767 | - |
452
+ | 1.7701 | 11100 | 0.0779 | - |
453
+ | 1.7860 | 11200 | 0.0792 | - |
454
+ | 1.8019 | 11300 | 0.0771 | - |
455
+ | 1.8179 | 11400 | 0.0783 | - |
456
+ | 1.8338 | 11500 | 0.0749 | - |
457
+ | 1.8498 | 11600 | 0.0755 | - |
458
+ | 1.8657 | 11700 | 0.0778 | - |
459
+ | 1.8817 | 11800 | 0.0753 | - |
460
+ | 1.8976 | 11900 | 0.0767 | - |
461
+ | 1.9136 | 12000 | 0.0725 | - |
462
+ | 1.9295 | 12100 | 0.0744 | - |
463
+ | 1.9455 | 12200 | 0.0743 | - |
464
+ | 1.9614 | 12300 | 0.0722 | - |
465
+ | 1.9774 | 12400 | 0.0712 | - |
466
+ | 1.9933 | 12500 | 0.0709 | - |
467
+ | 2.0092 | 12600 | 0.0694 | - |
468
+ | 2.0252 | 12700 | 0.0705 | - |
469
+ | 2.0411 | 12800 | 0.0715 | - |
470
+ | 2.0571 | 12900 | 0.0705 | - |
471
+ | 2.0730 | 13000 | 0.0653 | - |
472
+ | 2.0890 | 13100 | 0.0698 | - |
473
+ | 2.1049 | 13200 | 0.0676 | - |
474
+ | 2.1209 | 13300 | 0.0684 | - |
475
+ | 2.1368 | 13400 | 0.0644 | - |
476
+ | 2.1528 | 13500 | 0.0652 | - |
477
+ | 2.1687 | 13600 | 0.0673 | - |
478
+ | 2.1847 | 13700 | 0.067 | - |
479
+ | 2.2006 | 13800 | 0.0645 | - |
480
+ | 2.2166 | 13900 | 0.0633 | - |
481
+ | 2.2325 | 14000 | 0.0645 | - |
482
+ | 2.2484 | 14100 | 0.0698 | - |
483
+ | 2.2644 | 14200 | 0.0655 | - |
484
+ | 2.2803 | 14300 | 0.0654 | - |
485
+ | 2.2963 | 14400 | 0.0656 | - |
486
+ | 2.3122 | 14500 | 0.0631 | - |
487
+ | 2.3282 | 14600 | 0.0628 | - |
488
+ | 2.3441 | 14700 | 0.0671 | - |
489
+ | 2.3601 | 14800 | 0.0659 | - |
490
+ | 2.3760 | 14900 | 0.0619 | - |
491
+ | 2.3920 | 15000 | 0.0618 | - |
492
+ | 2.4079 | 15100 | 0.0624 | - |
493
+ | 2.4239 | 15200 | 0.0616 | - |
494
+ | 2.4398 | 15300 | 0.0631 | - |
495
+ | 2.4557 | 15400 | 0.0639 | - |
496
+ | 2.4717 | 15500 | 0.0585 | - |
497
+ | 2.4876 | 15600 | 0.0607 | - |
498
+ | 2.5036 | 15700 | 0.0615 | - |
499
+ | 2.5195 | 15800 | 0.062 | - |
500
+ | 2.5355 | 15900 | 0.0621 | - |
501
+ | 2.5514 | 16000 | 0.0608 | - |
502
+ | 2.5674 | 16100 | 0.0594 | - |
503
+ | 2.5833 | 16200 | 0.0631 | - |
504
+ | 2.5993 | 16300 | 0.0635 | - |
505
+ | 2.6152 | 16400 | 0.06 | - |
506
+ | 2.6312 | 16500 | 0.0581 | - |
507
+ | 2.6471 | 16600 | 0.0607 | - |
508
+ | 2.6631 | 16700 | 0.0577 | - |
509
+ | 2.6790 | 16800 | 0.0592 | - |
510
+ | 2.6949 | 16900 | 0.0625 | - |
511
+ | 2.7109 | 17000 | 0.0622 | - |
512
+ | 2.7268 | 17100 | 0.0573 | - |
513
+ | 2.7428 | 17200 | 0.0613 | - |
514
+ | 2.7587 | 17300 | 0.0587 | - |
515
+ | 2.7747 | 17400 | 0.0587 | - |
516
+ | 2.7906 | 17500 | 0.0588 | - |
517
+ | 2.8066 | 17600 | 0.0568 | - |
518
+ | 2.8225 | 17700 | 0.0573 | - |
519
+ | 2.8385 | 17800 | 0.0575 | - |
520
+ | 2.8544 | 17900 | 0.0575 | - |
521
+ | 2.8704 | 18000 | 0.0582 | - |
522
+ | 2.8863 | 18100 | 0.0577 | - |
523
+ | 2.9022 | 18200 | 0.057 | - |
524
+ | 2.9182 | 18300 | 0.0572 | - |
525
+ | 2.9341 | 18400 | 0.0558 | - |
526
+ | 2.9501 | 18500 | 0.0578 | - |
527
+ | 2.9660 | 18600 | 0.0567 | - |
528
+ | 2.9820 | 18700 | 0.0569 | - |
529
+ | 2.9979 | 18800 | 0.0547 | - |
530
+ | 3.0139 | 18900 | 0.0542 | - |
531
+ | 3.0298 | 19000 | 0.0563 | - |
532
+ | 3.0458 | 19100 | 0.0549 | - |
533
+ | 3.0617 | 19200 | 0.0531 | - |
534
+ | 3.0777 | 19300 | 0.053 | - |
535
+ | 3.0936 | 19400 | 0.0557 | - |
536
+ | 3.1096 | 19500 | 0.0546 | - |
537
+ | 3.1255 | 19600 | 0.0518 | - |
538
+ | 3.1414 | 19700 | 0.0517 | - |
539
+ | 3.1574 | 19800 | 0.0528 | - |
540
+ | 3.1733 | 19900 | 0.0551 | - |
541
+ | 3.1893 | 20000 | 0.0544 | - |
542
+ | 3.2052 | 20100 | 0.0526 | - |
543
+ | 3.2212 | 20200 | 0.0494 | - |
544
+ | 3.2371 | 20300 | 0.0537 | - |
545
+ | 3.2531 | 20400 | 0.0568 | - |
546
+ | 3.2690 | 20500 | 0.0525 | - |
547
+ | 3.2850 | 20600 | 0.0566 | - |
548
+ | 3.3009 | 20700 | 0.0539 | - |
549
+ | 3.3169 | 20800 | 0.0531 | - |
550
+ | 3.3328 | 20900 | 0.0524 | - |
551
+ | 3.3487 | 21000 | 0.0543 | - |
552
+ | 3.3647 | 21100 | 0.0537 | - |
553
+ | 3.3806 | 21200 | 0.0524 | - |
554
+ | 3.3966 | 21300 | 0.0516 | - |
555
+ | 3.4125 | 21400 | 0.0537 | - |
556
+ | 3.4285 | 21500 | 0.0515 | - |
557
+ | 3.4444 | 21600 | 0.0537 | - |
558
+ | 3.4604 | 21700 | 0.0526 | - |
559
+ | 3.4763 | 21800 | 0.0508 | - |
560
+ | 3.4923 | 21900 | 0.0526 | - |
561
+ | 3.5082 | 22000 | 0.0521 | - |
562
+ | 3.5242 | 22100 | 0.054 | - |
563
+ | 3.5401 | 22200 | 0.053 | - |
564
+ | 3.5561 | 22300 | 0.0509 | - |
565
+ | 3.5720 | 22400 | 0.0526 | - |
566
+ | 3.5879 | 22500 | 0.0551 | - |
567
+ | 3.6039 | 22600 | 0.0556 | - |
568
+ | 3.6198 | 22700 | 0.0497 | - |
569
+ | 3.6358 | 22800 | 0.0515 | - |
570
+ | 3.6517 | 22900 | 0.0514 | - |
571
+ | 3.6677 | 23000 | 0.0503 | - |
572
+ | 3.6836 | 23100 | 0.0515 | - |
573
+ | 3.6996 | 23200 | 0.0553 | - |
574
+ | 3.7155 | 23300 | 0.0519 | - |
575
+ | 3.7315 | 23400 | 0.0549 | - |
576
+ | 3.7474 | 23500 | 0.0522 | - |
577
+ | 3.7634 | 23600 | 0.0526 | - |
578
+ | 3.7793 | 23700 | 0.0525 | - |
579
+ | 3.7952 | 23800 | 0.051 | - |
580
+ | 3.8112 | 23900 | 0.0509 | - |
581
+ | 3.8271 | 24000 | 0.0503 | - |
582
+ | 3.8431 | 24100 | 0.0524 | - |
583
+ | 3.8590 | 24200 | 0.0526 | - |
584
+ | 3.8750 | 24300 | 0.0512 | - |
585
+ | 3.8909 | 24400 | 0.0518 | - |
586
+ | 3.9069 | 24500 | 0.0521 | - |
587
+ | 3.9228 | 24600 | 0.0524 | - |
588
+ | 3.9388 | 24700 | 0.051 | - |
589
+ | 3.9547 | 24800 | 0.0535 | - |
590
+ | 3.9707 | 24900 | 0.0508 | - |
591
+ | 3.9866 | 25000 | 0.0514 | - |
592
+ | 4.0 | 25084 | - | nan |
593
+
594
+ </details>
595
+
596
+ ### Framework Versions
597
+ - Python: 3.10.9
598
+ - Sentence Transformers: 3.0.1
599
+ - Transformers: 4.41.2
600
+ - PyTorch: 2.4.1+cu124
601
+ - Accelerate: 0.33.0
602
+ - Datasets: 2.18.0
603
+ - Tokenizers: 0.19.1
604
+
605
+ ## Citation
606
+
607
+ ### BibTeX
608
+
609
+ #### Sentence Transformers
610
+ ```bibtex
611
+ @inproceedings{reimers-2019-sentence-bert,
612
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
613
+ author = "Reimers, Nils and Gurevych, Iryna",
614
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
615
+ month = "11",
616
+ year = "2019",
617
+ publisher = "Association for Computational Linguistics",
618
+ url = "https://arxiv.org/abs/1908.10084",
619
+ }
620
+ ```
621
+
622
+ #### CachedMultipleNegativesRankingLoss
623
+ ```bibtex
624
+ @misc{gao2021scaling,
625
+ title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
626
+ author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
627
+ year={2021},
628
+ eprint={2101.06983},
629
+ archivePrefix={arXiv},
630
+ primaryClass={cs.LG}
631
+ }
632
+ ```
633
+
634
+ <!--
635
+ ## Glossary
636
+
637
+ *Clearly define terms in order to be accessible across audiences.*
638
+ -->
639
+
640
+ <!--
641
+ ## Model Card Authors
642
+
643
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
644
+ -->
645
+
646
+ <!--
647
+ ## Model Card Contact
648
+
649
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
650
+ -->
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TaylorAI/bge-micro",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 1536,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 3,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.41.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 30522
31
+ }
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": "2.4.1+cu124"
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:a541ec23496186c0156be8884fc68df90fc7f4a0a2c777fbf0a6229dc2985d5f
3
+ size 69565312
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[PAD]",
4
+ "[UNK]",
5
+ "[CLS]",
6
+ "[SEP]",
7
+ "[MASK]"
8
+ ],
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "[MASK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "[SEP]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "[UNK]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
45
+ "[PAD]",
46
+ "[UNK]",
47
+ "[CLS]",
48
+ "[SEP]",
49
+ "[MASK]"
50
+ ],
51
+ "clean_up_tokenization_spaces": true,
52
+ "cls_token": "[CLS]",
53
+ "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "max_length": 512,
57
+ "model_max_length": 512,
58
+ "never_split": null,
59
+ "pad_to_multiple_of": null,
60
+ "pad_token": "[PAD]",
61
+ "pad_token_type_id": 0,
62
+ "padding_side": "right",
63
+ "sep_token": "[SEP]",
64
+ "stride": 0,
65
+ "strip_accents": null,
66
+ "tokenize_chinese_chars": true,
67
+ "tokenizer_class": "BertTokenizer",
68
+ "truncation_side": "right",
69
+ "truncation_strategy": "longest_first",
70
+ "unk_token": "[UNK]"
71
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff