pierreinalco commited on
Commit
5c3e1e8
1 Parent(s): 7f71f97

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 +1,504 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: sentence-transformers
5
+ tags:
6
+ - sentence-transformers
7
+ - sentence-similarity
8
+ - feature-extraction
9
+ - dataset_size:1K<n<10K
10
+ - loss:CosineSimilarityLoss
11
+ base_model: distilbert/distilbert-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: A man shoots a man.
25
+ sentences:
26
+ - The target was being shot with bullets.
27
+ - Two women compete in a contest.
28
+ - Kittens are eating from dishes.
29
+ - source_sentence: A man is spitting.
30
+ sentences:
31
+ - A man is crying.
32
+ - The cougar is chasing the bear.
33
+ - A slow loris hanging on a cord.
34
+ - source_sentence: A man jumping rope
35
+ sentences:
36
+ - The man without a shirt is jumping.
37
+ - Suicide bomber strikes in Syria
38
+ - Two women sitting in lawn chairs.
39
+ - source_sentence: A woman is reading.
40
+ sentences:
41
+ - The woman is pencilling on eye shadow.
42
+ - Bombings kill 19 people in Iraq
43
+ - A man with his dog on the beach.
44
+ - source_sentence: A cat is on a robot.
45
+ sentences:
46
+ - A cat is pouncing on a trampoline.
47
+ - Two men are standing in a room.
48
+ - The two men are wearing jeans.
49
+ pipeline_tag: sentence-similarity
50
+ model-index:
51
+ - name: SentenceTransformer based on distilbert/distilbert-base-uncased
52
+ results:
53
+ - task:
54
+ type: semantic-similarity
55
+ name: Semantic Similarity
56
+ dataset:
57
+ name: sts dev
58
+ type: sts-dev
59
+ metrics:
60
+ - type: pearson_cosine
61
+ value: 0.8697331501677178
62
+ name: Pearson Cosine
63
+ - type: spearman_cosine
64
+ value: 0.8685180246535534
65
+ name: Spearman Cosine
66
+ - type: pearson_manhattan
67
+ value: 0.8437823469562609
68
+ name: Pearson Manhattan
69
+ - type: spearman_manhattan
70
+ value: 0.8453821992823211
71
+ name: Spearman Manhattan
72
+ - type: pearson_euclidean
73
+ value: 0.8437006142247849
74
+ name: Pearson Euclidean
75
+ - type: spearman_euclidean
76
+ value: 0.8452387041309848
77
+ name: Spearman Euclidean
78
+ - type: pearson_dot
79
+ value: 0.8131236162716029
80
+ name: Pearson Dot
81
+ - type: spearman_dot
82
+ value: 0.8170086888260258
83
+ name: Spearman Dot
84
+ - type: pearson_max
85
+ value: 0.8697331501677178
86
+ name: Pearson Max
87
+ - type: spearman_max
88
+ value: 0.8685180246535534
89
+ name: Spearman Max
90
+ - task:
91
+ type: semantic-similarity
92
+ name: Semantic Similarity
93
+ dataset:
94
+ name: sts test
95
+ type: sts-test
96
+ metrics:
97
+ - type: pearson_cosine
98
+ value: 0.8385072210953088
99
+ name: Pearson Cosine
100
+ - type: spearman_cosine
101
+ value: 0.8381420978910276
102
+ name: Spearman Cosine
103
+ - type: pearson_manhattan
104
+ value: 0.8314551294633353
105
+ name: Pearson Manhattan
106
+ - type: spearman_manhattan
107
+ value: 0.8311067092857745
108
+ name: Spearman Manhattan
109
+ - type: pearson_euclidean
110
+ value: 0.8321704746684249
111
+ name: Pearson Euclidean
112
+ - type: spearman_euclidean
113
+ value: 0.831638857612135
114
+ name: Spearman Euclidean
115
+ - type: pearson_dot
116
+ value: 0.7504803996099798
117
+ name: Pearson Dot
118
+ - type: spearman_dot
119
+ value: 0.7471600293342772
120
+ name: Spearman Dot
121
+ - type: pearson_max
122
+ value: 0.8385072210953088
123
+ name: Pearson Max
124
+ - type: spearman_max
125
+ value: 0.8381420978910276
126
+ name: Spearman Max
127
+ ---
128
+
129
+ # SentenceTransformer based on distilbert/distilbert-base-uncased
130
+
131
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-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.
132
+
133
+ ## Model Details
134
+
135
+ ### Model Description
136
+ - **Model Type:** Sentence Transformer
137
+ - **Base model:** [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) <!-- at revision 12040accade4e8a0f71eabdb258fecc2e7e948be -->
138
+ - **Maximum Sequence Length:** 512 tokens
139
+ - **Output Dimensionality:** 768 tokens
140
+ - **Similarity Function:** Cosine Similarity
141
+ - **Training Dataset:**
142
+ - [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb)
143
+ - **Language:** en
144
+ <!-- - **License:** Unknown -->
145
+
146
+ ### Model Sources
147
+
148
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
149
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
150
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
151
+
152
+ ### Full Model Architecture
153
+
154
+ ```
155
+ SentenceTransformer(
156
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel
157
+ (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})
158
+ )
159
+ ```
160
+
161
+ ## Usage
162
+
163
+ ### Direct Usage (Sentence Transformers)
164
+
165
+ First install the Sentence Transformers library:
166
+
167
+ ```bash
168
+ pip install -U sentence-transformers
169
+ ```
170
+
171
+ Then you can load this model and run inference.
172
+ ```python
173
+ from sentence_transformers import SentenceTransformer
174
+
175
+ # Download from the 🤗 Hub
176
+ model = SentenceTransformer("pierreinalco/distilbert-base-uncased-sts")
177
+ # Run inference
178
+ sentences = [
179
+ 'A cat is on a robot.',
180
+ 'A cat is pouncing on a trampoline.',
181
+ 'Two men are standing in a room.',
182
+ ]
183
+ embeddings = model.encode(sentences)
184
+ print(embeddings.shape)
185
+ # [3, 768]
186
+
187
+ # Get the similarity scores for the embeddings
188
+ similarities = model.similarity(embeddings, embeddings)
189
+ print(similarities.shape)
190
+ # [3, 3]
191
+ ```
192
+
193
+ <!--
194
+ ### Direct Usage (Transformers)
195
+
196
+ <details><summary>Click to see the direct usage in Transformers</summary>
197
+
198
+ </details>
199
+ -->
200
+
201
+ <!--
202
+ ### Downstream Usage (Sentence Transformers)
203
+
204
+ You can finetune this model on your own dataset.
205
+
206
+ <details><summary>Click to expand</summary>
207
+
208
+ </details>
209
+ -->
210
+
211
+ <!--
212
+ ### Out-of-Scope Use
213
+
214
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
215
+ -->
216
+
217
+ ## Evaluation
218
+
219
+ ### Metrics
220
+
221
+ #### Semantic Similarity
222
+ * Dataset: `sts-dev`
223
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
224
+
225
+ | Metric | Value |
226
+ |:--------------------|:-----------|
227
+ | pearson_cosine | 0.8697 |
228
+ | **spearman_cosine** | **0.8685** |
229
+ | pearson_manhattan | 0.8438 |
230
+ | spearman_manhattan | 0.8454 |
231
+ | pearson_euclidean | 0.8437 |
232
+ | spearman_euclidean | 0.8452 |
233
+ | pearson_dot | 0.8131 |
234
+ | spearman_dot | 0.817 |
235
+ | pearson_max | 0.8697 |
236
+ | spearman_max | 0.8685 |
237
+
238
+ #### Semantic Similarity
239
+ * Dataset: `sts-test`
240
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
241
+
242
+ | Metric | Value |
243
+ |:--------------------|:-----------|
244
+ | pearson_cosine | 0.8385 |
245
+ | **spearman_cosine** | **0.8381** |
246
+ | pearson_manhattan | 0.8315 |
247
+ | spearman_manhattan | 0.8311 |
248
+ | pearson_euclidean | 0.8322 |
249
+ | spearman_euclidean | 0.8316 |
250
+ | pearson_dot | 0.7505 |
251
+ | spearman_dot | 0.7472 |
252
+ | pearson_max | 0.8385 |
253
+ | spearman_max | 0.8381 |
254
+
255
+ <!--
256
+ ## Bias, Risks and Limitations
257
+
258
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
259
+ -->
260
+
261
+ <!--
262
+ ### Recommendations
263
+
264
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
265
+ -->
266
+
267
+ ## Training Details
268
+
269
+ ### Training Dataset
270
+
271
+ #### sentence-transformers/stsb
272
+
273
+ * Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
274
+ * Size: 5,749 training samples
275
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
276
+ * Approximate statistics based on the first 1000 samples:
277
+ | | sentence1 | sentence2 | score |
278
+ |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
279
+ | type | string | string | float |
280
+ | 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> |
281
+ * Samples:
282
+ | sentence1 | sentence2 | score |
283
+ |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------|
284
+ | <code>A plane is taking off.</code> | <code>An air plane is taking off.</code> | <code>1.0</code> |
285
+ | <code>A man is playing a large flute.</code> | <code>A man is playing a flute.</code> | <code>0.76</code> |
286
+ | <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> |
287
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
288
+ ```json
289
+ {
290
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
291
+ }
292
+ ```
293
+
294
+ ### Evaluation Dataset
295
+
296
+ #### sentence-transformers/stsb
297
+
298
+ * Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
299
+ * Size: 1,500 evaluation samples
300
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
301
+ * Approximate statistics based on the first 1000 samples:
302
+ | | sentence1 | sentence2 | score |
303
+ |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
304
+ | type | string | string | float |
305
+ | 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> |
306
+ * Samples:
307
+ | sentence1 | sentence2 | score |
308
+ |:--------------------------------------------------|:------------------------------------------------------|:------------------|
309
+ | <code>A man with a hard hat is dancing.</code> | <code>A man wearing a hard hat is dancing.</code> | <code>1.0</code> |
310
+ | <code>A young child is riding a horse.</code> | <code>A child is riding a horse.</code> | <code>0.95</code> |
311
+ | <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> |
312
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
313
+ ```json
314
+ {
315
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
316
+ }
317
+ ```
318
+
319
+ ### Training Hyperparameters
320
+ #### Non-Default Hyperparameters
321
+
322
+ - `eval_strategy`: steps
323
+ - `per_device_train_batch_size`: 16
324
+ - `per_device_eval_batch_size`: 16
325
+ - `num_train_epochs`: 4
326
+ - `warmup_ratio`: 0.1
327
+
328
+ #### All Hyperparameters
329
+ <details><summary>Click to expand</summary>
330
+
331
+ - `overwrite_output_dir`: False
332
+ - `do_predict`: False
333
+ - `eval_strategy`: steps
334
+ - `prediction_loss_only`: True
335
+ - `per_device_train_batch_size`: 16
336
+ - `per_device_eval_batch_size`: 16
337
+ - `per_gpu_train_batch_size`: None
338
+ - `per_gpu_eval_batch_size`: None
339
+ - `gradient_accumulation_steps`: 1
340
+ - `eval_accumulation_steps`: None
341
+ - `learning_rate`: 5e-05
342
+ - `weight_decay`: 0.0
343
+ - `adam_beta1`: 0.9
344
+ - `adam_beta2`: 0.999
345
+ - `adam_epsilon`: 1e-08
346
+ - `max_grad_norm`: 1.0
347
+ - `num_train_epochs`: 4
348
+ - `max_steps`: -1
349
+ - `lr_scheduler_type`: linear
350
+ - `lr_scheduler_kwargs`: {}
351
+ - `warmup_ratio`: 0.1
352
+ - `warmup_steps`: 0
353
+ - `log_level`: passive
354
+ - `log_level_replica`: warning
355
+ - `log_on_each_node`: True
356
+ - `logging_nan_inf_filter`: True
357
+ - `save_safetensors`: True
358
+ - `save_on_each_node`: False
359
+ - `save_only_model`: False
360
+ - `restore_callback_states_from_checkpoint`: False
361
+ - `no_cuda`: False
362
+ - `use_cpu`: False
363
+ - `use_mps_device`: False
364
+ - `seed`: 42
365
+ - `data_seed`: None
366
+ - `jit_mode_eval`: False
367
+ - `use_ipex`: False
368
+ - `bf16`: False
369
+ - `fp16`: False
370
+ - `fp16_opt_level`: O1
371
+ - `half_precision_backend`: auto
372
+ - `bf16_full_eval`: False
373
+ - `fp16_full_eval`: False
374
+ - `tf32`: None
375
+ - `local_rank`: 0
376
+ - `ddp_backend`: None
377
+ - `tpu_num_cores`: None
378
+ - `tpu_metrics_debug`: False
379
+ - `debug`: []
380
+ - `dataloader_drop_last`: False
381
+ - `dataloader_num_workers`: 0
382
+ - `dataloader_prefetch_factor`: None
383
+ - `past_index`: -1
384
+ - `disable_tqdm`: False
385
+ - `remove_unused_columns`: True
386
+ - `label_names`: None
387
+ - `load_best_model_at_end`: False
388
+ - `ignore_data_skip`: False
389
+ - `fsdp`: []
390
+ - `fsdp_min_num_params`: 0
391
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
392
+ - `fsdp_transformer_layer_cls_to_wrap`: None
393
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
394
+ - `deepspeed`: None
395
+ - `label_smoothing_factor`: 0.0
396
+ - `optim`: adamw_torch
397
+ - `optim_args`: None
398
+ - `adafactor`: False
399
+ - `group_by_length`: False
400
+ - `length_column_name`: length
401
+ - `ddp_find_unused_parameters`: None
402
+ - `ddp_bucket_cap_mb`: None
403
+ - `ddp_broadcast_buffers`: False
404
+ - `dataloader_pin_memory`: True
405
+ - `dataloader_persistent_workers`: False
406
+ - `skip_memory_metrics`: True
407
+ - `use_legacy_prediction_loop`: False
408
+ - `push_to_hub`: False
409
+ - `resume_from_checkpoint`: None
410
+ - `hub_model_id`: None
411
+ - `hub_strategy`: every_save
412
+ - `hub_private_repo`: False
413
+ - `hub_always_push`: False
414
+ - `gradient_checkpointing`: False
415
+ - `gradient_checkpointing_kwargs`: None
416
+ - `include_inputs_for_metrics`: False
417
+ - `eval_do_concat_batches`: True
418
+ - `fp16_backend`: auto
419
+ - `push_to_hub_model_id`: None
420
+ - `push_to_hub_organization`: None
421
+ - `mp_parameters`:
422
+ - `auto_find_batch_size`: False
423
+ - `full_determinism`: False
424
+ - `torchdynamo`: None
425
+ - `ray_scope`: last
426
+ - `ddp_timeout`: 1800
427
+ - `torch_compile`: False
428
+ - `torch_compile_backend`: None
429
+ - `torch_compile_mode`: None
430
+ - `dispatch_batches`: None
431
+ - `split_batches`: None
432
+ - `include_tokens_per_second`: False
433
+ - `include_num_input_tokens_seen`: False
434
+ - `neftune_noise_alpha`: None
435
+ - `optim_target_modules`: None
436
+ - `batch_eval_metrics`: False
437
+ - `batch_sampler`: batch_sampler
438
+ - `multi_dataset_batch_sampler`: proportional
439
+
440
+ </details>
441
+
442
+ ### Training Logs
443
+ | Epoch | Step | Training Loss | loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
444
+ |:------:|:----:|:-------------:|:------:|:-----------------------:|:------------------------:|
445
+ | 0.2778 | 100 | 0.0836 | 0.0399 | 0.8029 | - |
446
+ | 0.5556 | 200 | 0.0334 | 0.0301 | 0.8481 | - |
447
+ | 0.8333 | 300 | 0.0282 | 0.0262 | 0.8578 | - |
448
+ | 1.1111 | 400 | 0.0204 | 0.0273 | 0.8593 | - |
449
+ | 1.3889 | 500 | 0.0138 | 0.0281 | 0.8589 | - |
450
+ | 1.6667 | 600 | 0.0118 | 0.0276 | 0.8566 | - |
451
+ | 1.9444 | 700 | 0.0128 | 0.0263 | 0.8614 | - |
452
+ | 2.2222 | 800 | 0.0077 | 0.0259 | 0.8685 | - |
453
+ | 2.5 | 900 | 0.0057 | 0.0254 | 0.8661 | - |
454
+ | 2.7778 | 1000 | 0.0059 | 0.0261 | 0.8677 | - |
455
+ | 3.0556 | 1100 | 0.0054 | 0.0258 | 0.8682 | - |
456
+ | 3.3333 | 1200 | 0.0039 | 0.0261 | 0.8668 | - |
457
+ | 3.6111 | 1300 | 0.0039 | 0.0261 | 0.8678 | - |
458
+ | 3.8889 | 1400 | 0.0037 | 0.0259 | 0.8685 | - |
459
+ | 4.0 | 1440 | - | - | - | 0.8381 |
460
+
461
+
462
+ ### Framework Versions
463
+ - Python: 3.11.9
464
+ - Sentence Transformers: 3.0.0
465
+ - Transformers: 4.41.1
466
+ - PyTorch: 2.3.0
467
+ - Accelerate: 0.30.1
468
+ - Datasets: 2.19.1
469
+ - Tokenizers: 0.19.1
470
+
471
+ ## Citation
472
+
473
+ ### BibTeX
474
+
475
+ #### Sentence Transformers
476
+ ```bibtex
477
+ @inproceedings{reimers-2019-sentence-bert,
478
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
479
+ author = "Reimers, Nils and Gurevych, Iryna",
480
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
481
+ month = "11",
482
+ year = "2019",
483
+ publisher = "Association for Computational Linguistics",
484
+ url = "https://arxiv.org/abs/1908.10084",
485
+ }
486
+ ```
487
+
488
+ <!--
489
+ ## Glossary
490
+
491
+ *Clearly define terms in order to be accessible across audiences.*
492
+ -->
493
+
494
+ <!--
495
+ ## Model Card Authors
496
+
497
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
498
+ -->
499
+
500
+ <!--
501
+ ## Model Card Contact
502
+
503
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
504
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.41.1",
23
+ "vocab_size": 30522
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.0",
4
+ "transformers": "4.41.1",
5
+ "pytorch": "2.3.0"
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 sha256:1a5fd4c267f6db4cf50326ef33393f477659de6271e4085ff68adf8bef7ea721
3
+ size 265462608
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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff