tomaarsen HF staff commited on
Commit
7a89e71
1 Parent(s): b1db00e

Add new SentenceTransformer model.

Browse files
1_CNN/cnn_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "in_word_embedding_dimension": 768,
3
+ "out_channels": 256,
4
+ "kernel_sizes": [
5
+ 1,
6
+ 3,
7
+ 5
8
+ ]
9
+ }
1_CNN/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db620327ef0bd41f8bce6e851cb90e3eb412293b278e86bd79106502a023c079
3
+ size 7083780
2_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,518 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: sentence-transformers
5
+ tags:
6
+ - sentence-transformers
7
+ - sentence-similarity
8
+ - feature-extraction
9
+ - loss:CosineSimilarityLoss
10
+ base_model: google-bert/bert-base-uncased
11
+ metrics:
12
+ - pearson_cosine
13
+ - spearman_cosine
14
+ - pearson_manhattan
15
+ - spearman_manhattan
16
+ - pearson_euclidean
17
+ - spearman_euclidean
18
+ - pearson_dot
19
+ - spearman_dot
20
+ - pearson_max
21
+ - spearman_max
22
+ widget:
23
+ - source_sentence: A man is speaking.
24
+ sentences:
25
+ - A man is talking on a phone.
26
+ - The boy is jumping into a lake.
27
+ - A cat is pouncing on a trampoline.
28
+ - source_sentence: A woman is reading.
29
+ sentences:
30
+ - A woman is writing something.
31
+ - A woman is applying eye shadow.
32
+ - A tiger is walking around his cage.
33
+ - source_sentence: A baby is laughing.
34
+ sentences:
35
+ - The baby laughed in his car seat.
36
+ - A green bus drives down a road.
37
+ - A woman is applying eye shadow.
38
+ - source_sentence: A man jumping rope
39
+ sentences:
40
+ - A man is climbing a rope.
41
+ - The boy is jumping into a lake.
42
+ - Two women sitting in lawn chairs.
43
+ - source_sentence: A person makes fire.
44
+ sentences:
45
+ - The person is starting a fire.
46
+ - Blast on Indian train kills one
47
+ - An animal is chewing on something.
48
+ pipeline_tag: sentence-similarity
49
+ co2_eq_emissions:
50
+ emissions: 1.1600350080390396
51
+ energy_consumed: 0.002984381371948278
52
+ source: codecarbon
53
+ training_type: fine-tuning
54
+ on_cloud: false
55
+ cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
56
+ ram_total_size: 31.777088165283203
57
+ hours_used: 0.014
58
+ hardware_used: 1 x NVIDIA GeForce RTX 3090
59
+ model-index:
60
+ - name: SentenceTransformer based on google-bert/bert-base-uncased
61
+ results:
62
+ - task:
63
+ type: semantic-similarity
64
+ name: Semantic Similarity
65
+ dataset:
66
+ name: sts dev
67
+ type: sts-dev
68
+ metrics:
69
+ - type: pearson_cosine
70
+ value: 0.8517529845876077
71
+ name: Pearson Cosine
72
+ - type: spearman_cosine
73
+ value: 0.8524623532914918
74
+ name: Spearman Cosine
75
+ - type: pearson_manhattan
76
+ value: 0.800899823827701
77
+ name: Pearson Manhattan
78
+ - type: spearman_manhattan
79
+ value: 0.8051568979113306
80
+ name: Spearman Manhattan
81
+ - type: pearson_euclidean
82
+ value: 0.8006826117948451
83
+ name: Pearson Euclidean
84
+ - type: spearman_euclidean
85
+ value: 0.8053116182840467
86
+ name: Spearman Euclidean
87
+ - type: pearson_dot
88
+ value: 0.7449289216960278
89
+ name: Pearson Dot
90
+ - type: spearman_dot
91
+ value: 0.7558824436512839
92
+ name: Spearman Dot
93
+ - type: pearson_max
94
+ value: 0.8517529845876077
95
+ name: Pearson Max
96
+ - type: spearman_max
97
+ value: 0.8524623532914918
98
+ name: Spearman Max
99
+ - task:
100
+ type: semantic-similarity
101
+ name: Semantic Similarity
102
+ dataset:
103
+ name: sts test
104
+ type: sts-test
105
+ metrics:
106
+ - type: pearson_cosine
107
+ value: 0.83020870287088
108
+ name: Pearson Cosine
109
+ - type: spearman_cosine
110
+ value: 0.823188318981985
111
+ name: Spearman Cosine
112
+ - type: pearson_manhattan
113
+ value: 0.8082481232573683
114
+ name: Pearson Manhattan
115
+ - type: spearman_manhattan
116
+ value: 0.8009567692854708
117
+ name: Spearman Manhattan
118
+ - type: pearson_euclidean
119
+ value: 0.8074730784388158
120
+ name: Pearson Euclidean
121
+ - type: spearman_euclidean
122
+ value: 0.8001358594920889
123
+ name: Spearman Euclidean
124
+ - type: pearson_dot
125
+ value: 0.7172194732542608
126
+ name: Pearson Dot
127
+ - type: spearman_dot
128
+ value: 0.7095712222240558
129
+ name: Spearman Dot
130
+ - type: pearson_max
131
+ value: 0.83020870287088
132
+ name: Pearson Max
133
+ - type: spearman_max
134
+ value: 0.823188318981985
135
+ name: Spearman Max
136
+ ---
137
+
138
+ # SentenceTransformer based on google-bert/bert-base-uncased
139
+
140
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) 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.
141
+
142
+ ## Model Details
143
+
144
+ ### Model Description
145
+ - **Model Type:** Sentence Transformer
146
+ - **Base model:** [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) <!-- at revision 86b5e0934494bd15c9632b12f734a8a67f723594 -->
147
+ - **Maximum Sequence Length:** 512 tokens
148
+ - **Output Dimensionality:** 768 tokens
149
+ - **Similarity Function:** Cosine Similarity
150
+ - **Training Dataset:**
151
+ - [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb)
152
+ - **Language:** en
153
+ <!-- - **License:** Unknown -->
154
+
155
+ ### Model Sources
156
+
157
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
158
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
159
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
160
+
161
+ ### Full Model Architecture
162
+
163
+ ```
164
+ SentenceTransformer(
165
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
166
+ (1): CNN(
167
+ (convs): ModuleList(
168
+ (0): Conv1d(768, 256, kernel_size=(1,), stride=(1,))
169
+ (1): Conv1d(768, 256, kernel_size=(3,), stride=(1,), padding=(1,))
170
+ (2): Conv1d(768, 256, kernel_size=(5,), stride=(1,), padding=(2,))
171
+ )
172
+ )
173
+ (2): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
174
+ )
175
+ ```
176
+
177
+ ## Usage
178
+
179
+ ### Direct Usage (Sentence Transformers)
180
+
181
+ First install the Sentence Transformers library:
182
+
183
+ ```bash
184
+ pip install -U sentence-transformers
185
+ ```
186
+
187
+ Then you can load this model and run inference.
188
+ ```python
189
+ from sentence_transformers import SentenceTransformer
190
+
191
+ # Download from the 🤗 Hub
192
+ model = SentenceTransformer("tomaarsen/bert-base-uncased-cnn")
193
+ # Run inference
194
+ sentences = [
195
+ 'A person makes fire.',
196
+ 'The person is starting a fire.',
197
+ 'Blast on Indian train kills one',
198
+ ]
199
+ embeddings = model.encode(sentences)
200
+ print(embeddings.shape)
201
+ # [3, 768]
202
+
203
+ # Get the similarity scores for the embeddings
204
+ similarities = model.similarity(embeddings)
205
+ print(similarities.shape)
206
+ # [3, 3]
207
+ ```
208
+
209
+ <!--
210
+ ### Direct Usage (Transformers)
211
+
212
+ <details><summary>Click to see the direct usage in Transformers</summary>
213
+
214
+ </details>
215
+ -->
216
+
217
+ <!--
218
+ ### Downstream Usage (Sentence Transformers)
219
+
220
+ You can finetune this model on your own dataset.
221
+
222
+ <details><summary>Click to expand</summary>
223
+
224
+ </details>
225
+ -->
226
+
227
+ <!--
228
+ ### Out-of-Scope Use
229
+
230
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
231
+ -->
232
+
233
+ ## Evaluation
234
+
235
+ ### Metrics
236
+
237
+ #### Semantic Similarity
238
+ * Dataset: `sts-dev`
239
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
240
+
241
+ | Metric | Value |
242
+ |:--------------------|:-----------|
243
+ | pearson_cosine | 0.8518 |
244
+ | **spearman_cosine** | **0.8525** |
245
+ | pearson_manhattan | 0.8009 |
246
+ | spearman_manhattan | 0.8052 |
247
+ | pearson_euclidean | 0.8007 |
248
+ | spearman_euclidean | 0.8053 |
249
+ | pearson_dot | 0.7449 |
250
+ | spearman_dot | 0.7559 |
251
+ | pearson_max | 0.8518 |
252
+ | spearman_max | 0.8525 |
253
+
254
+ #### Semantic Similarity
255
+ * Dataset: `sts-test`
256
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
257
+
258
+ | Metric | Value |
259
+ |:--------------------|:-----------|
260
+ | pearson_cosine | 0.8302 |
261
+ | **spearman_cosine** | **0.8232** |
262
+ | pearson_manhattan | 0.8082 |
263
+ | spearman_manhattan | 0.801 |
264
+ | pearson_euclidean | 0.8075 |
265
+ | spearman_euclidean | 0.8001 |
266
+ | pearson_dot | 0.7172 |
267
+ | spearman_dot | 0.7096 |
268
+ | pearson_max | 0.8302 |
269
+ | spearman_max | 0.8232 |
270
+
271
+ <!--
272
+ ## Bias, Risks and Limitations
273
+
274
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
275
+ -->
276
+
277
+ <!--
278
+ ### Recommendations
279
+
280
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
281
+ -->
282
+
283
+ ## Training Details
284
+
285
+ ### Training Dataset
286
+
287
+ #### sentence-transformers/stsb
288
+
289
+ * Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [d999f12](https://huggingface.co/datasets/sentence-transformers/stsb/tree/d999f12281623b0925506817d9bd85e88289218a)
290
+ * Size: 5,749 training samples
291
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
292
+ * Approximate statistics based on the first 1000 samples:
293
+ | | sentence1 | sentence2 | score |
294
+ |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
295
+ | type | string | string | float |
296
+ | details | <ul><li>min: 6 tokens</li><li>mean: 10.0 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 9.95 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
297
+ * Samples:
298
+ | sentence1 | sentence2 | score |
299
+ |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------|
300
+ | <code>A plane is taking off.</code> | <code>An air plane is taking off.</code> | <code>1.0</code> |
301
+ | <code>A man is playing a large flute.</code> | <code>A man is playing a flute.</code> | <code>0.76</code> |
302
+ | <code>A man is spreading shreded cheese on a pizza.</code> | <code>A man is spreading shredded cheese on an uncooked pizza.</code> | <code>0.76</code> |
303
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/losses.html#cosinesimilarityloss) with these parameters:
304
+ ```json
305
+ {
306
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
307
+ }
308
+ ```
309
+
310
+ ### Evaluation Dataset
311
+
312
+ #### sentence-transformers/stsb
313
+
314
+ * Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [d999f12](https://huggingface.co/datasets/sentence-transformers/stsb/tree/d999f12281623b0925506817d9bd85e88289218a)
315
+ * Size: 1,500 evaluation samples
316
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
317
+ * Approximate statistics based on the first 1000 samples:
318
+ | | sentence1 | sentence2 | score |
319
+ |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
320
+ | type | string | string | float |
321
+ | details | <ul><li>min: 5 tokens</li><li>mean: 15.1 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.11 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> |
322
+ * Samples:
323
+ | sentence1 | sentence2 | score |
324
+ |:--------------------------------------------------|:------------------------------------------------------|:------------------|
325
+ | <code>A man with a hard hat is dancing.</code> | <code>A man wearing a hard hat is dancing.</code> | <code>1.0</code> |
326
+ | <code>A young child is riding a horse.</code> | <code>A child is riding a horse.</code> | <code>0.95</code> |
327
+ | <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code> |
328
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/losses.html#cosinesimilarityloss) with these parameters:
329
+ ```json
330
+ {
331
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
332
+ }
333
+ ```
334
+
335
+ ### Training Hyperparameters
336
+ #### Non-Default Hyperparameters
337
+
338
+ - `eval_strategy`: steps
339
+ - `per_device_train_batch_size`: 32
340
+ - `per_device_eval_batch_size`: 32
341
+ - `num_train_epochs`: 1
342
+ - `warmup_ratio`: 0.1
343
+ - `fp16`: True
344
+
345
+ #### All Hyperparameters
346
+ <details><summary>Click to expand</summary>
347
+
348
+ - `overwrite_output_dir`: False
349
+ - `do_predict`: False
350
+ - `eval_strategy`: steps
351
+ - `prediction_loss_only`: False
352
+ - `per_device_train_batch_size`: 32
353
+ - `per_device_eval_batch_size`: 32
354
+ - `per_gpu_train_batch_size`: None
355
+ - `per_gpu_eval_batch_size`: None
356
+ - `gradient_accumulation_steps`: 1
357
+ - `eval_accumulation_steps`: None
358
+ - `learning_rate`: 5e-05
359
+ - `weight_decay`: 0.0
360
+ - `adam_beta1`: 0.9
361
+ - `adam_beta2`: 0.999
362
+ - `adam_epsilon`: 1e-08
363
+ - `max_grad_norm`: 1.0
364
+ - `num_train_epochs`: 1
365
+ - `max_steps`: -1
366
+ - `lr_scheduler_type`: linear
367
+ - `lr_scheduler_kwargs`: {}
368
+ - `warmup_ratio`: 0.1
369
+ - `warmup_steps`: 0
370
+ - `log_level`: passive
371
+ - `log_level_replica`: warning
372
+ - `log_on_each_node`: True
373
+ - `logging_nan_inf_filter`: True
374
+ - `save_safetensors`: True
375
+ - `save_on_each_node`: False
376
+ - `save_only_model`: False
377
+ - `no_cuda`: False
378
+ - `use_cpu`: False
379
+ - `use_mps_device`: False
380
+ - `seed`: 42
381
+ - `data_seed`: None
382
+ - `jit_mode_eval`: False
383
+ - `use_ipex`: False
384
+ - `bf16`: False
385
+ - `fp16`: True
386
+ - `fp16_opt_level`: O1
387
+ - `half_precision_backend`: auto
388
+ - `bf16_full_eval`: False
389
+ - `fp16_full_eval`: False
390
+ - `tf32`: None
391
+ - `local_rank`: 0
392
+ - `ddp_backend`: None
393
+ - `tpu_num_cores`: None
394
+ - `tpu_metrics_debug`: False
395
+ - `debug`: []
396
+ - `dataloader_drop_last`: False
397
+ - `dataloader_num_workers`: 0
398
+ - `dataloader_prefetch_factor`: None
399
+ - `past_index`: -1
400
+ - `disable_tqdm`: False
401
+ - `remove_unused_columns`: True
402
+ - `label_names`: None
403
+ - `load_best_model_at_end`: False
404
+ - `ignore_data_skip`: False
405
+ - `fsdp`: []
406
+ - `fsdp_min_num_params`: 0
407
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
408
+ - `fsdp_transformer_layer_cls_to_wrap`: None
409
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
410
+ - `deepspeed`: None
411
+ - `label_smoothing_factor`: 0.0
412
+ - `optim`: adamw_torch
413
+ - `optim_args`: None
414
+ - `adafactor`: False
415
+ - `group_by_length`: False
416
+ - `length_column_name`: length
417
+ - `ddp_find_unused_parameters`: None
418
+ - `ddp_bucket_cap_mb`: None
419
+ - `ddp_broadcast_buffers`: None
420
+ - `dataloader_pin_memory`: True
421
+ - `dataloader_persistent_workers`: False
422
+ - `skip_memory_metrics`: True
423
+ - `use_legacy_prediction_loop`: False
424
+ - `push_to_hub`: False
425
+ - `resume_from_checkpoint`: None
426
+ - `hub_model_id`: None
427
+ - `hub_strategy`: every_save
428
+ - `hub_private_repo`: False
429
+ - `hub_always_push`: False
430
+ - `gradient_checkpointing`: False
431
+ - `gradient_checkpointing_kwargs`: None
432
+ - `include_inputs_for_metrics`: False
433
+ - `eval_do_concat_batches`: True
434
+ - `fp16_backend`: auto
435
+ - `push_to_hub_model_id`: None
436
+ - `push_to_hub_organization`: None
437
+ - `mp_parameters`:
438
+ - `auto_find_batch_size`: False
439
+ - `full_determinism`: False
440
+ - `torchdynamo`: None
441
+ - `ray_scope`: last
442
+ - `ddp_timeout`: 1800
443
+ - `torch_compile`: False
444
+ - `torch_compile_backend`: None
445
+ - `torch_compile_mode`: None
446
+ - `dispatch_batches`: None
447
+ - `split_batches`: None
448
+ - `include_tokens_per_second`: False
449
+ - `include_num_input_tokens_seen`: False
450
+ - `neftune_noise_alpha`: None
451
+ - `optim_target_modules`: None
452
+ - `batch_sampler`: batch_sampler
453
+ - `multi_dataset_batch_sampler`: proportional
454
+
455
+ </details>
456
+
457
+ ### Training Logs
458
+ | Epoch | Step | Training Loss | loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
459
+ |:------:|:----:|:-------------:|:------:|:-----------------------:|:------------------------:|
460
+ | 0.5556 | 100 | 0.0417 | 0.0304 | 0.8525 | - |
461
+ | 1.0 | 180 | - | - | - | 0.8232 |
462
+
463
+
464
+ ### Environmental Impact
465
+ Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
466
+ - **Energy Consumed**: 0.003 kWh
467
+ - **Carbon Emitted**: 0.001 kg of CO2
468
+ - **Hours Used**: 0.014 hours
469
+
470
+ ### Training Hardware
471
+ - **On Cloud**: No
472
+ - **GPU Model**: 1 x NVIDIA GeForce RTX 3090
473
+ - **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
474
+ - **RAM Size**: 31.78 GB
475
+
476
+ ### Framework Versions
477
+ - Python: 3.11.6
478
+ - Sentence Transformers: 3.0.0.dev0
479
+ - Transformers: 4.41.0.dev0
480
+ - PyTorch: 2.3.0+cu121
481
+ - Accelerate: 0.26.1
482
+ - Datasets: 2.18.0
483
+ - Tokenizers: 0.19.1
484
+
485
+ ## Citation
486
+
487
+ ### BibTeX
488
+
489
+ #### Sentence Transformers
490
+ ```bibtex
491
+ @inproceedings{reimers-2019-sentence-bert,
492
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
493
+ author = "Reimers, Nils and Gurevych, Iryna",
494
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
495
+ month = "11",
496
+ year = "2019",
497
+ publisher = "Association for Computational Linguistics",
498
+ url = "https://arxiv.org/abs/1908.10084",
499
+ }
500
+ ```
501
+
502
+ <!--
503
+ ## Glossary
504
+
505
+ *Clearly define terms in order to be accessible across audiences.*
506
+ -->
507
+
508
+ <!--
509
+ ## Model Card Authors
510
+
511
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
512
+ -->
513
+
514
+ <!--
515
+ ## Model Card Contact
516
+
517
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
518
+ -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.41.0.dev0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.0.dev0",
4
+ "transformers": "4.41.0.dev0",
5
+ "pytorch": "2.3.0+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77332904b7838c23c1037523137f3000339fec96df7a56be2a75916724b64ca9
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_CNN",
12
+ "type": "sentence_transformers.models.CNN"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Pooling",
18
+ "type": "sentence_transformers.models.Pooling"
19
+ }
20
+ ]
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 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff