tomaarsen HF staff commited on
Commit
e9ee5d2
1 Parent(s): 215255a

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": 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 +1,556 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: sentence-transformers
5
+ tags:
6
+ - sentence-transformers
7
+ - sentence-similarity
8
+ - feature-extraction
9
+ - loss:SoftmaxLoss
10
+ - loss:CosineSimilarityLoss
11
+ base_model: google-bert/bert-base-uncased
12
+ metrics:
13
+ - pearson_cosine
14
+ - spearman_cosine
15
+ - pearson_manhattan
16
+ - spearman_manhattan
17
+ - pearson_euclidean
18
+ - spearman_euclidean
19
+ - pearson_dot
20
+ - spearman_dot
21
+ - pearson_max
22
+ - spearman_max
23
+ widget:
24
+ - source_sentence: the guy is dead
25
+ sentences:
26
+ - The dog is dead.
27
+ - Men are sitting in the park.
28
+ - People are outside.
29
+ - source_sentence: Women are running.
30
+ sentences:
31
+ - Two women are running.
32
+ - A animated airplane is landing.
33
+ - The man sang and played his guitar.
34
+ - source_sentence: The gate is yellow.
35
+ sentences:
36
+ - The gate is blue.
37
+ - The cook is kneading the flour.
38
+ - A woman puts flour on a piece of meat.
39
+ - source_sentence: A parrot is talking.
40
+ sentences:
41
+ - A man is singing.
42
+ - Two men are standing in a room.
43
+ - Three dogs playing in the snow.
44
+ - source_sentence: the guy is paid
45
+ sentences:
46
+ - A man is receiving a contract.
47
+ - A man is racing on his bike.
48
+ - a dog chases a cat
49
+ pipeline_tag: sentence-similarity
50
+ co2_eq_emissions:
51
+ emissions: 6.489379533908795
52
+ energy_consumed: 0.01669499908389665
53
+ source: codecarbon
54
+ training_type: fine-tuning
55
+ on_cloud: false
56
+ cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
57
+ ram_total_size: 31.777088165283203
58
+ hours_used: 0.097
59
+ hardware_used: 1 x NVIDIA GeForce RTX 3090
60
+ model-index:
61
+ - name: SentenceTransformer based on google-bert/bert-base-uncased
62
+ results:
63
+ - task:
64
+ type: semantic-similarity
65
+ name: Semantic Similarity
66
+ dataset:
67
+ name: sts dev
68
+ type: sts-dev
69
+ metrics:
70
+ - type: pearson_cosine
71
+ value: 0.8287682657838144
72
+ name: Pearson Cosine
73
+ - type: spearman_cosine
74
+ value: 0.8350670289838767
75
+ name: Spearman Cosine
76
+ - type: pearson_manhattan
77
+ value: 0.796834648877542
78
+ name: Pearson Manhattan
79
+ - type: spearman_manhattan
80
+ value: 0.8041000103101458
81
+ name: Spearman Manhattan
82
+ - type: pearson_euclidean
83
+ value: 0.7968015917572032
84
+ name: Pearson Euclidean
85
+ - type: spearman_euclidean
86
+ value: 0.803879972820206
87
+ name: Spearman Euclidean
88
+ - type: pearson_dot
89
+ value: 0.7572392072098838
90
+ name: Pearson Dot
91
+ - type: spearman_dot
92
+ value: 0.7696731029709327
93
+ name: Spearman Dot
94
+ - type: pearson_max
95
+ value: 0.8287682657838144
96
+ name: Pearson Max
97
+ - type: spearman_max
98
+ value: 0.8350670289838767
99
+ name: Spearman Max
100
+ - task:
101
+ type: semantic-similarity
102
+ name: Semantic Similarity
103
+ dataset:
104
+ name: sts test
105
+ type: sts-test
106
+ metrics:
107
+ - type: pearson_cosine
108
+ value: 0.8014245911006761
109
+ name: Pearson Cosine
110
+ - type: spearman_cosine
111
+ value: 0.8049359058371248
112
+ name: Spearman Cosine
113
+ - type: pearson_manhattan
114
+ value: 0.7934883900951029
115
+ name: Pearson Manhattan
116
+ - type: spearman_manhattan
117
+ value: 0.793480619733962
118
+ name: Spearman Manhattan
119
+ - type: pearson_euclidean
120
+ value: 0.7940198430253176
121
+ name: Pearson Euclidean
122
+ - type: spearman_euclidean
123
+ value: 0.7942686805824551
124
+ name: Spearman Euclidean
125
+ - type: pearson_dot
126
+ value: 0.698878713916111
127
+ name: Pearson Dot
128
+ - type: spearman_dot
129
+ value: 0.6967434595564439
130
+ name: Spearman Dot
131
+ - type: pearson_max
132
+ value: 0.8014245911006761
133
+ name: Pearson Max
134
+ - type: spearman_max
135
+ value: 0.8049359058371248
136
+ name: Spearman Max
137
+ ---
138
+
139
+ # SentenceTransformer based on google-bert/bert-base-uncased
140
+
141
+ 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 [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) and [sts](https://huggingface.co/datasets/sentence-transformers/stsb) datasets. 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.
142
+
143
+ ## Model Details
144
+
145
+ ### Model Description
146
+ - **Model Type:** Sentence Transformer
147
+ - **Base model:** [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) <!-- at revision 86b5e0934494bd15c9632b12f734a8a67f723594 -->
148
+ - **Maximum Sequence Length:** 512 tokens
149
+ - **Output Dimensionality:** 768 tokens
150
+ - **Similarity Function:** Cosine Similarity
151
+ - **Training Datasets:**
152
+ - [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
153
+ - [sts](https://huggingface.co/datasets/sentence-transformers/stsb)
154
+ - **Language:** en
155
+ <!-- - **License:** Unknown -->
156
+
157
+ ### Model Sources
158
+
159
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
160
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
161
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
162
+
163
+ ### Full Model Architecture
164
+
165
+ ```
166
+ SentenceTransformer(
167
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
168
+ (1): 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})
169
+ )
170
+ ```
171
+
172
+ ## Usage
173
+
174
+ ### Direct Usage (Sentence Transformers)
175
+
176
+ First install the Sentence Transformers library:
177
+
178
+ ```bash
179
+ pip install -U sentence-transformers
180
+ ```
181
+
182
+ Then you can load this model and run inference.
183
+ ```python
184
+ from sentence_transformers import SentenceTransformer
185
+
186
+ # Download from the 🤗 Hub
187
+ model = SentenceTransformer("tomaarsen/bert-base-uncased-multi-task")
188
+ # Run inference
189
+ sentences = [
190
+ 'the guy is paid',
191
+ 'A man is receiving a contract.',
192
+ 'A man is racing on his bike.',
193
+ ]
194
+ embeddings = model.encode(sentences)
195
+ print(embeddings.shape)
196
+ # [3, 768]
197
+
198
+ # Get the similarity scores for the embeddings
199
+ similarities = model.similarity(embeddings)
200
+ print(similarities.shape)
201
+ # [3, 3]
202
+ ```
203
+
204
+ <!--
205
+ ### Direct Usage (Transformers)
206
+
207
+ <details><summary>Click to see the direct usage in Transformers</summary>
208
+
209
+ </details>
210
+ -->
211
+
212
+ <!--
213
+ ### Downstream Usage (Sentence Transformers)
214
+
215
+ You can finetune this model on your own dataset.
216
+
217
+ <details><summary>Click to expand</summary>
218
+
219
+ </details>
220
+ -->
221
+
222
+ <!--
223
+ ### Out-of-Scope Use
224
+
225
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
226
+ -->
227
+
228
+ ## Evaluation
229
+
230
+ ### Metrics
231
+
232
+ #### Semantic Similarity
233
+ * Dataset: `sts-dev`
234
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
235
+
236
+ | Metric | Value |
237
+ |:--------------------|:-----------|
238
+ | pearson_cosine | 0.8288 |
239
+ | **spearman_cosine** | **0.8351** |
240
+ | pearson_manhattan | 0.7968 |
241
+ | spearman_manhattan | 0.8041 |
242
+ | pearson_euclidean | 0.7968 |
243
+ | spearman_euclidean | 0.8039 |
244
+ | pearson_dot | 0.7572 |
245
+ | spearman_dot | 0.7697 |
246
+ | pearson_max | 0.8288 |
247
+ | spearman_max | 0.8351 |
248
+
249
+ #### Semantic Similarity
250
+ * Dataset: `sts-test`
251
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
252
+
253
+ | Metric | Value |
254
+ |:--------------------|:-----------|
255
+ | pearson_cosine | 0.8014 |
256
+ | **spearman_cosine** | **0.8049** |
257
+ | pearson_manhattan | 0.7935 |
258
+ | spearman_manhattan | 0.7935 |
259
+ | pearson_euclidean | 0.794 |
260
+ | spearman_euclidean | 0.7943 |
261
+ | pearson_dot | 0.6989 |
262
+ | spearman_dot | 0.6967 |
263
+ | pearson_max | 0.8014 |
264
+ | spearman_max | 0.8049 |
265
+
266
+ <!--
267
+ ## Bias, Risks and Limitations
268
+
269
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
270
+ -->
271
+
272
+ <!--
273
+ ### Recommendations
274
+
275
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
276
+ -->
277
+
278
+ ## Training Details
279
+
280
+ ### Training Datasets
281
+
282
+ #### all-nli
283
+
284
+ * Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [cc6c526](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/cc6c526380e29912b5c6fa03682da4daf773c013)
285
+ * Size: 942,069 training samples
286
+ * Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
287
+ * Approximate statistics based on the first 1000 samples:
288
+ | | premise | hypothesis | label |
289
+ |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-------------------------------------------------------------------|
290
+ | type | string | string | int |
291
+ | details | <ul><li>min: 6 tokens</li><li>mean: 17.38 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.7 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>0: ~33.40%</li><li>1: ~33.30%</li><li>2: ~33.30%</li></ul> |
292
+ * Samples:
293
+ | premise | hypothesis | label |
294
+ |:--------------------------------------------------------------------|:---------------------------------------------------------------|:---------------|
295
+ | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is training his horse for a competition.</code> | <code>1</code> |
296
+ | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is at a diner, ordering an omelette.</code> | <code>2</code> |
297
+ | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>0</code> |
298
+ * Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/losses.html#softmaxloss)
299
+
300
+ #### sts
301
+
302
+ * Dataset: [sts](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
303
+ * Size: 5,749 training samples
304
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
305
+ * Approximate statistics based on the first 1000 samples:
306
+ | | sentence1 | sentence2 | score |
307
+ |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
308
+ | type | string | string | float |
309
+ | 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> |
310
+ * Samples:
311
+ | sentence1 | sentence2 | score |
312
+ |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------|
313
+ | <code>A plane is taking off.</code> | <code>An air plane is taking off.</code> | <code>1.0</code> |
314
+ | <code>A man is playing a large flute.</code> | <code>A man is playing a flute.</code> | <code>0.76</code> |
315
+ | <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> |
316
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/losses.html#cosinesimilarityloss) with these parameters:
317
+ ```json
318
+ {
319
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
320
+ }
321
+ ```
322
+
323
+ ### Evaluation Datasets
324
+
325
+ #### all-nli
326
+
327
+ * Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [cc6c526](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/cc6c526380e29912b5c6fa03682da4daf773c013)
328
+ * Size: 1,000 evaluation samples
329
+ * Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
330
+ * Approximate statistics based on the first 1000 samples:
331
+ | | premise | hypothesis | label |
332
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|
333
+ | type | string | string | int |
334
+ | details | <ul><li>min: 6 tokens</li><li>mean: 18.44 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.57 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>0: ~33.10%</li><li>1: ~33.30%</li><li>2: ~33.60%</li></ul> |
335
+ * Samples:
336
+ | premise | hypothesis | label |
337
+ |:-------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|:---------------|
338
+ | <code>Two women are embracing while holding to go packages.</code> | <code>The sisters are hugging goodbye while holding to go packages after just eating lunch.</code> | <code>1</code> |
339
+ | <code>Two women are embracing while holding to go packages.</code> | <code>Two woman are holding packages.</code> | <code>0</code> |
340
+ | <code>Two women are embracing while holding to go packages.</code> | <code>The men are fighting outside a deli.</code> | <code>2</code> |
341
+ * Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/losses.html#softmaxloss)
342
+
343
+ #### sts
344
+
345
+ * Dataset: [sts](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
346
+ * Size: 1,500 evaluation samples
347
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
348
+ * Approximate statistics based on the first 1000 samples:
349
+ | | sentence1 | sentence2 | score |
350
+ |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
351
+ | type | string | string | float |
352
+ | 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> |
353
+ * Samples:
354
+ | sentence1 | sentence2 | score |
355
+ |:--------------------------------------------------|:------------------------------------------------------|:------------------|
356
+ | <code>A man with a hard hat is dancing.</code> | <code>A man wearing a hard hat is dancing.</code> | <code>1.0</code> |
357
+ | <code>A young child is riding a horse.</code> | <code>A child is riding a horse.</code> | <code>0.95</code> |
358
+ | <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> |
359
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/losses.html#cosinesimilarityloss) with these parameters:
360
+ ```json
361
+ {
362
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
363
+ }
364
+ ```
365
+
366
+ ### Training Hyperparameters
367
+ #### Non-Default Hyperparameters
368
+
369
+ - `eval_strategy`: steps
370
+ - `per_device_train_batch_size`: 16
371
+ - `per_device_eval_batch_size`: 16
372
+ - `num_train_epochs`: 1
373
+ - `warmup_ratio`: 0.1
374
+ - `fp16`: True
375
+ - `multi_dataset_batch_sampler`: round_robin
376
+
377
+ #### All Hyperparameters
378
+ <details><summary>Click to expand</summary>
379
+
380
+ - `overwrite_output_dir`: False
381
+ - `do_predict`: False
382
+ - `eval_strategy`: steps
383
+ - `prediction_loss_only`: False
384
+ - `per_device_train_batch_size`: 16
385
+ - `per_device_eval_batch_size`: 16
386
+ - `per_gpu_train_batch_size`: None
387
+ - `per_gpu_eval_batch_size`: None
388
+ - `gradient_accumulation_steps`: 1
389
+ - `eval_accumulation_steps`: None
390
+ - `learning_rate`: 5e-05
391
+ - `weight_decay`: 0.0
392
+ - `adam_beta1`: 0.9
393
+ - `adam_beta2`: 0.999
394
+ - `adam_epsilon`: 1e-08
395
+ - `max_grad_norm`: 1.0
396
+ - `num_train_epochs`: 1
397
+ - `max_steps`: -1
398
+ - `lr_scheduler_type`: linear
399
+ - `lr_scheduler_kwargs`: {}
400
+ - `warmup_ratio`: 0.1
401
+ - `warmup_steps`: 0
402
+ - `log_level`: passive
403
+ - `log_level_replica`: warning
404
+ - `log_on_each_node`: True
405
+ - `logging_nan_inf_filter`: True
406
+ - `save_safetensors`: True
407
+ - `save_on_each_node`: False
408
+ - `save_only_model`: False
409
+ - `no_cuda`: False
410
+ - `use_cpu`: False
411
+ - `use_mps_device`: False
412
+ - `seed`: 42
413
+ - `data_seed`: None
414
+ - `jit_mode_eval`: False
415
+ - `use_ipex`: False
416
+ - `bf16`: False
417
+ - `fp16`: True
418
+ - `fp16_opt_level`: O1
419
+ - `half_precision_backend`: auto
420
+ - `bf16_full_eval`: False
421
+ - `fp16_full_eval`: False
422
+ - `tf32`: None
423
+ - `local_rank`: 0
424
+ - `ddp_backend`: None
425
+ - `tpu_num_cores`: None
426
+ - `tpu_metrics_debug`: False
427
+ - `debug`: []
428
+ - `dataloader_drop_last`: False
429
+ - `dataloader_num_workers`: 0
430
+ - `dataloader_prefetch_factor`: None
431
+ - `past_index`: -1
432
+ - `disable_tqdm`: False
433
+ - `remove_unused_columns`: True
434
+ - `label_names`: None
435
+ - `load_best_model_at_end`: False
436
+ - `ignore_data_skip`: False
437
+ - `fsdp`: []
438
+ - `fsdp_min_num_params`: 0
439
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
440
+ - `fsdp_transformer_layer_cls_to_wrap`: None
441
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
442
+ - `deepspeed`: None
443
+ - `label_smoothing_factor`: 0.0
444
+ - `optim`: adamw_torch
445
+ - `optim_args`: None
446
+ - `adafactor`: False
447
+ - `group_by_length`: False
448
+ - `length_column_name`: length
449
+ - `ddp_find_unused_parameters`: None
450
+ - `ddp_bucket_cap_mb`: None
451
+ - `ddp_broadcast_buffers`: None
452
+ - `dataloader_pin_memory`: True
453
+ - `dataloader_persistent_workers`: False
454
+ - `skip_memory_metrics`: True
455
+ - `use_legacy_prediction_loop`: False
456
+ - `push_to_hub`: False
457
+ - `resume_from_checkpoint`: None
458
+ - `hub_model_id`: None
459
+ - `hub_strategy`: every_save
460
+ - `hub_private_repo`: False
461
+ - `hub_always_push`: False
462
+ - `gradient_checkpointing`: False
463
+ - `gradient_checkpointing_kwargs`: None
464
+ - `include_inputs_for_metrics`: False
465
+ - `eval_do_concat_batches`: True
466
+ - `fp16_backend`: auto
467
+ - `push_to_hub_model_id`: None
468
+ - `push_to_hub_organization`: None
469
+ - `mp_parameters`:
470
+ - `auto_find_batch_size`: False
471
+ - `full_determinism`: False
472
+ - `torchdynamo`: None
473
+ - `ray_scope`: last
474
+ - `ddp_timeout`: 1800
475
+ - `torch_compile`: False
476
+ - `torch_compile_backend`: None
477
+ - `torch_compile_mode`: None
478
+ - `dispatch_batches`: None
479
+ - `split_batches`: None
480
+ - `include_tokens_per_second`: False
481
+ - `include_num_input_tokens_seen`: False
482
+ - `neftune_noise_alpha`: None
483
+ - `optim_target_modules`: None
484
+ - `batch_sampler`: batch_sampler
485
+ - `multi_dataset_batch_sampler`: round_robin
486
+
487
+ </details>
488
+
489
+ ### Training Logs
490
+ | Epoch | Step | Training Loss | sts loss | all-nli loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
491
+ |:------:|:----:|:-------------:|:--------:|:------------:|:-----------------------:|:------------------------:|
492
+ | 0.1389 | 100 | 0.5961 | 0.0470 | 1.1005 | 0.8096 | - |
493
+ | 0.2778 | 200 | 0.5408 | 0.0354 | 0.9687 | 0.8229 | - |
494
+ | 0.4167 | 300 | 0.5185 | 0.0373 | 0.9398 | 0.8265 | - |
495
+ | 0.5556 | 400 | 0.4978 | 0.0368 | 0.9304 | 0.8200 | - |
496
+ | 0.6944 | 500 | 0.5026 | 0.0347 | 0.9044 | 0.8234 | - |
497
+ | 0.8333 | 600 | 0.4702 | 0.0326 | 0.8727 | 0.8300 | - |
498
+ | 0.9722 | 700 | 0.4649 | 0.0328 | 0.8723 | 0.8351 | - |
499
+ | 1.0 | 720 | - | - | - | - | 0.8049 |
500
+
501
+
502
+ ### Environmental Impact
503
+ Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
504
+ - **Energy Consumed**: 0.017 kWh
505
+ - **Carbon Emitted**: 0.006 kg of CO2
506
+ - **Hours Used**: 0.097 hours
507
+
508
+ ### Training Hardware
509
+ - **On Cloud**: No
510
+ - **GPU Model**: 1 x NVIDIA GeForce RTX 3090
511
+ - **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
512
+ - **RAM Size**: 31.78 GB
513
+
514
+ ### Framework Versions
515
+ - Python: 3.11.6
516
+ - Sentence Transformers: 3.0.0.dev0
517
+ - Transformers: 4.41.0.dev0
518
+ - PyTorch: 2.3.0+cu121
519
+ - Accelerate: 0.26.1
520
+ - Datasets: 2.18.0
521
+ - Tokenizers: 0.19.1
522
+
523
+ ## Citation
524
+
525
+ ### BibTeX
526
+
527
+ #### Sentence Transformers and SoftmaxLoss
528
+ ```bibtex
529
+ @inproceedings{reimers-2019-sentence-bert,
530
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
531
+ author = "Reimers, Nils and Gurevych, Iryna",
532
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
533
+ month = "11",
534
+ year = "2019",
535
+ publisher = "Association for Computational Linguistics",
536
+ url = "https://arxiv.org/abs/1908.10084",
537
+ }
538
+ ```
539
+
540
+ <!--
541
+ ## Glossary
542
+
543
+ *Clearly define terms in order to be accessible across audiences.*
544
+ -->
545
+
546
+ <!--
547
+ ## Model Card Authors
548
+
549
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
550
+ -->
551
+
552
+ <!--
553
+ ## Model Card Contact
554
+
555
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
556
+ -->
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:f7ec19651449c9899fdc6651afbfc35651f9aedaef7918c6d12b8ef0a3210961
3
+ size 437951328
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 +1,7 @@
 
 
 
 
 
 
 
 
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