rajistics commited on
Commit
6f04aed
1 Parent(s): ace9720

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 +1,495 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ library_name: sentence-transformers
6
+ tags:
7
+ - sentence-transformers
8
+ - sentence-similarity
9
+ - feature-extraction
10
+ - dataset_size:100K<n<1M
11
+ - loss:MultipleNegativesRankingLoss
12
+ base_model: microsoft/mpnet-base
13
+ metrics:
14
+ - cosine_accuracy
15
+ - dot_accuracy
16
+ - manhattan_accuracy
17
+ - euclidean_accuracy
18
+ - max_accuracy
19
+ widget:
20
+ - source_sentence: No animals.
21
+ sentences:
22
+ - It doesn't get it.
23
+ - The person is sleeping.
24
+ - the man is at home sleeping
25
+ - source_sentence: Three boys.
26
+ sentences:
27
+ - All of them
28
+ - Oh, what a fool I feel!
29
+ - The lady is taking a nap.
30
+ - source_sentence: Suggesetions
31
+ sentences:
32
+ - said San'doro.
33
+ - He wears contact lens.
34
+ - a cat sleeps on a pillow
35
+ - source_sentence: It's true.
36
+ sentences:
37
+ - It is true
38
+ - A whale eats the fish.
39
+ - a cat sleeps on a pillow
40
+ - source_sentence: Yes it did.
41
+ sentences:
42
+ - oh does it sure
43
+ - The puppets eat human.
44
+ - the woman is asleep at home
45
+ pipeline_tag: sentence-similarity
46
+ model-index:
47
+ - name: MPNet base trained on AllNLI triplets
48
+ results:
49
+ - task:
50
+ type: triplet
51
+ name: Triplet
52
+ dataset:
53
+ name: all nli dev
54
+ type: all-nli-dev
55
+ metrics:
56
+ - type: cosine_accuracy
57
+ value: 0.8452308626974484
58
+ name: Cosine Accuracy
59
+ - type: dot_accuracy
60
+ value: 0.15264277035236937
61
+ name: Dot Accuracy
62
+ - type: manhattan_accuracy
63
+ value: 0.8420413122721749
64
+ name: Manhattan Accuracy
65
+ - type: euclidean_accuracy
66
+ value: 0.8399149453219927
67
+ name: Euclidean Accuracy
68
+ - type: max_accuracy
69
+ value: 0.8452308626974484
70
+ name: Max Accuracy
71
+ - task:
72
+ type: triplet
73
+ name: Triplet
74
+ dataset:
75
+ name: all nli test
76
+ type: all-nli-test
77
+ metrics:
78
+ - type: cosine_accuracy
79
+ value: 0.8662430019670146
80
+ name: Cosine Accuracy
81
+ - type: dot_accuracy
82
+ value: 0.13269783628385534
83
+ name: Dot Accuracy
84
+ - type: manhattan_accuracy
85
+ value: 0.8607958844000605
86
+ name: Manhattan Accuracy
87
+ - type: euclidean_accuracy
88
+ value: 0.8635194431835376
89
+ name: Euclidean Accuracy
90
+ - type: max_accuracy
91
+ value: 0.8662430019670146
92
+ name: Max Accuracy
93
+ ---
94
+
95
+ # MPNet base trained on AllNLI triplets
96
+
97
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) 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.
98
+
99
+ ## Model Details
100
+
101
+ ### Model Description
102
+ - **Model Type:** Sentence Transformer
103
+ - **Base model:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
104
+ - **Maximum Sequence Length:** 512 tokens
105
+ - **Output Dimensionality:** 768 tokens
106
+ - **Similarity Function:** Cosine Similarity
107
+ - **Training Dataset:**
108
+ - [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
109
+ - **Language:** en
110
+ - **License:** apache-2.0
111
+
112
+ ### Model Sources
113
+
114
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
115
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
116
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
117
+
118
+ ### Full Model Architecture
119
+
120
+ ```
121
+ SentenceTransformer(
122
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
123
+ (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})
124
+ )
125
+ ```
126
+
127
+ ## Usage
128
+
129
+ ### Direct Usage (Sentence Transformers)
130
+
131
+ First install the Sentence Transformers library:
132
+
133
+ ```bash
134
+ pip install -U sentence-transformers
135
+ ```
136
+
137
+ Then you can load this model and run inference.
138
+ ```python
139
+ from sentence_transformers import SentenceTransformer
140
+
141
+ # Download from the 🤗 Hub
142
+ model = SentenceTransformer("rajistics/mpnet-base-all-nli-triplet")
143
+ # Run inference
144
+ sentences = [
145
+ 'Yes it did.',
146
+ 'oh does it sure',
147
+ 'The puppets eat human.',
148
+ ]
149
+ embeddings = model.encode(sentences)
150
+ print(embeddings.shape)
151
+ # [3, 768]
152
+
153
+ # Get the similarity scores for the embeddings
154
+ similarities = model.similarity(embeddings, embeddings)
155
+ print(similarities.shape)
156
+ # [3, 3]
157
+ ```
158
+
159
+ <!--
160
+ ### Direct Usage (Transformers)
161
+
162
+ <details><summary>Click to see the direct usage in Transformers</summary>
163
+
164
+ </details>
165
+ -->
166
+
167
+ <!--
168
+ ### Downstream Usage (Sentence Transformers)
169
+
170
+ You can finetune this model on your own dataset.
171
+
172
+ <details><summary>Click to expand</summary>
173
+
174
+ </details>
175
+ -->
176
+
177
+ <!--
178
+ ### Out-of-Scope Use
179
+
180
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
181
+ -->
182
+
183
+ ## Evaluation
184
+
185
+ ### Metrics
186
+
187
+ #### Triplet
188
+ * Dataset: `all-nli-dev`
189
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
190
+
191
+ | Metric | Value |
192
+ |:-------------------|:-----------|
193
+ | cosine_accuracy | 0.8452 |
194
+ | dot_accuracy | 0.1526 |
195
+ | manhattan_accuracy | 0.842 |
196
+ | euclidean_accuracy | 0.8399 |
197
+ | **max_accuracy** | **0.8452** |
198
+
199
+ #### Triplet
200
+ * Dataset: `all-nli-test`
201
+ * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
202
+
203
+ | Metric | Value |
204
+ |:-------------------|:-----------|
205
+ | cosine_accuracy | 0.8662 |
206
+ | dot_accuracy | 0.1327 |
207
+ | manhattan_accuracy | 0.8608 |
208
+ | euclidean_accuracy | 0.8635 |
209
+ | **max_accuracy** | **0.8662** |
210
+
211
+ <!--
212
+ ## Bias, Risks and Limitations
213
+
214
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
215
+ -->
216
+
217
+ <!--
218
+ ### Recommendations
219
+
220
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
221
+ -->
222
+
223
+ ## Training Details
224
+
225
+ ### Training Dataset
226
+
227
+ #### sentence-transformers/all-nli
228
+
229
+ * Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
230
+ * Size: 100,000 training samples
231
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
232
+ * Approximate statistics based on the first 1000 samples:
233
+ | | anchor | positive | negative |
234
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
235
+ | type | string | string | string |
236
+ | details | <ul><li>min: 7 tokens</li><li>mean: 10.46 tokens</li><li>max: 46 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.81 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.4 tokens</li><li>max: 50 tokens</li></ul> |
237
+ * Samples:
238
+ | anchor | positive | negative |
239
+ |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
240
+ | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>A person is at a diner, ordering an omelette.</code> |
241
+ | <code>Children smiling and waving at camera</code> | <code>There are children present</code> | <code>The kids are frowning</code> |
242
+ | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code> |
243
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
244
+ ```json
245
+ {
246
+ "scale": 20.0,
247
+ "similarity_fct": "cos_sim"
248
+ }
249
+ ```
250
+
251
+ ### Evaluation Dataset
252
+
253
+ #### sentence-transformers/all-nli
254
+
255
+ * Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
256
+ * Size: 6,584 evaluation samples
257
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
258
+ * Approximate statistics based on the first 1000 samples:
259
+ | | anchor | positive | negative |
260
+ |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
261
+ | type | string | string | string |
262
+ | details | <ul><li>min: 6 tokens</li><li>mean: 17.95 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.78 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.35 tokens</li><li>max: 29 tokens</li></ul> |
263
+ * Samples:
264
+ | anchor | positive | negative |
265
+ |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:--------------------------------------------------------|
266
+ | <code>Two women are embracing while holding to go packages.</code> | <code>Two woman are holding packages.</code> | <code>The men are fighting outside a deli.</code> |
267
+ | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code> |
268
+ | <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code> | <code>A man selling donuts to a customer.</code> | <code>A woman drinks her coffee in a small cafe.</code> |
269
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
270
+ ```json
271
+ {
272
+ "scale": 20.0,
273
+ "similarity_fct": "cos_sim"
274
+ }
275
+ ```
276
+
277
+ ### Training Hyperparameters
278
+ #### Non-Default Hyperparameters
279
+
280
+ - `eval_strategy`: steps
281
+ - `per_device_train_batch_size`: 16
282
+ - `per_device_eval_batch_size`: 16
283
+ - `num_train_epochs`: 1
284
+ - `warmup_ratio`: 0.1
285
+ - `fp16`: True
286
+ - `batch_sampler`: no_duplicates
287
+
288
+ #### All Hyperparameters
289
+ <details><summary>Click to expand</summary>
290
+
291
+ - `overwrite_output_dir`: False
292
+ - `do_predict`: False
293
+ - `eval_strategy`: steps
294
+ - `prediction_loss_only`: True
295
+ - `per_device_train_batch_size`: 16
296
+ - `per_device_eval_batch_size`: 16
297
+ - `per_gpu_train_batch_size`: None
298
+ - `per_gpu_eval_batch_size`: None
299
+ - `gradient_accumulation_steps`: 1
300
+ - `eval_accumulation_steps`: None
301
+ - `learning_rate`: 5e-05
302
+ - `weight_decay`: 0.0
303
+ - `adam_beta1`: 0.9
304
+ - `adam_beta2`: 0.999
305
+ - `adam_epsilon`: 1e-08
306
+ - `max_grad_norm`: 1.0
307
+ - `num_train_epochs`: 1
308
+ - `max_steps`: -1
309
+ - `lr_scheduler_type`: linear
310
+ - `lr_scheduler_kwargs`: {}
311
+ - `warmup_ratio`: 0.1
312
+ - `warmup_steps`: 0
313
+ - `log_level`: passive
314
+ - `log_level_replica`: warning
315
+ - `log_on_each_node`: True
316
+ - `logging_nan_inf_filter`: True
317
+ - `save_safetensors`: True
318
+ - `save_on_each_node`: False
319
+ - `save_only_model`: False
320
+ - `restore_callback_states_from_checkpoint`: False
321
+ - `no_cuda`: False
322
+ - `use_cpu`: False
323
+ - `use_mps_device`: False
324
+ - `seed`: 42
325
+ - `data_seed`: None
326
+ - `jit_mode_eval`: False
327
+ - `use_ipex`: False
328
+ - `bf16`: False
329
+ - `fp16`: True
330
+ - `fp16_opt_level`: O1
331
+ - `half_precision_backend`: auto
332
+ - `bf16_full_eval`: False
333
+ - `fp16_full_eval`: False
334
+ - `tf32`: None
335
+ - `local_rank`: 0
336
+ - `ddp_backend`: None
337
+ - `tpu_num_cores`: None
338
+ - `tpu_metrics_debug`: False
339
+ - `debug`: []
340
+ - `dataloader_drop_last`: False
341
+ - `dataloader_num_workers`: 0
342
+ - `dataloader_prefetch_factor`: None
343
+ - `past_index`: -1
344
+ - `disable_tqdm`: False
345
+ - `remove_unused_columns`: True
346
+ - `label_names`: None
347
+ - `load_best_model_at_end`: False
348
+ - `ignore_data_skip`: False
349
+ - `fsdp`: []
350
+ - `fsdp_min_num_params`: 0
351
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
352
+ - `fsdp_transformer_layer_cls_to_wrap`: None
353
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
354
+ - `deepspeed`: None
355
+ - `label_smoothing_factor`: 0.0
356
+ - `optim`: adamw_torch
357
+ - `optim_args`: None
358
+ - `adafactor`: False
359
+ - `group_by_length`: False
360
+ - `length_column_name`: length
361
+ - `ddp_find_unused_parameters`: None
362
+ - `ddp_bucket_cap_mb`: None
363
+ - `ddp_broadcast_buffers`: False
364
+ - `dataloader_pin_memory`: True
365
+ - `dataloader_persistent_workers`: False
366
+ - `skip_memory_metrics`: True
367
+ - `use_legacy_prediction_loop`: False
368
+ - `push_to_hub`: False
369
+ - `resume_from_checkpoint`: None
370
+ - `hub_model_id`: None
371
+ - `hub_strategy`: every_save
372
+ - `hub_private_repo`: False
373
+ - `hub_always_push`: False
374
+ - `gradient_checkpointing`: False
375
+ - `gradient_checkpointing_kwargs`: None
376
+ - `include_inputs_for_metrics`: False
377
+ - `eval_do_concat_batches`: True
378
+ - `fp16_backend`: auto
379
+ - `push_to_hub_model_id`: None
380
+ - `push_to_hub_organization`: None
381
+ - `mp_parameters`:
382
+ - `auto_find_batch_size`: False
383
+ - `full_determinism`: False
384
+ - `torchdynamo`: None
385
+ - `ray_scope`: last
386
+ - `ddp_timeout`: 1800
387
+ - `torch_compile`: False
388
+ - `torch_compile_backend`: None
389
+ - `torch_compile_mode`: None
390
+ - `dispatch_batches`: None
391
+ - `split_batches`: None
392
+ - `include_tokens_per_second`: False
393
+ - `include_num_input_tokens_seen`: False
394
+ - `neftune_noise_alpha`: None
395
+ - `optim_target_modules`: None
396
+ - `batch_eval_metrics`: False
397
+ - `batch_sampler`: no_duplicates
398
+ - `multi_dataset_batch_sampler`: proportional
399
+
400
+ </details>
401
+
402
+ ### Training Logs
403
+ | Epoch | Step | Training Loss | loss | all-nli-dev_max_accuracy | all-nli-test_max_accuracy |
404
+ |:------:|:----:|:-------------:|:------:|:------------------------:|:-------------------------:|
405
+ | 0 | 0 | - | - | 0.6832 | - |
406
+ | 0.016 | 100 | 2.6596 | 1.0454 | 0.7942 | - |
407
+ | 0.032 | 200 | 0.9172 | 0.8283 | 0.8071 | - |
408
+ | 0.048 | 300 | 1.3038 | 0.8209 | 0.8048 | - |
409
+ | 0.064 | 400 | 0.8026 | 0.8679 | 0.8009 | - |
410
+ | 0.08 | 500 | 0.8252 | 0.9687 | 0.7906 | - |
411
+ | 0.096 | 600 | 0.9903 | 1.0263 | 0.7893 | - |
412
+ | 0.112 | 700 | 0.8719 | 1.3540 | 0.7708 | - |
413
+ | 0.128 | 800 | 0.9602 | 1.4494 | 0.7622 | - |
414
+ | 0.144 | 900 | 1.0746 | 1.3507 | 0.7646 | - |
415
+ | 0.16 | 1000 | 1.0095 | 1.4260 | 0.7672 | - |
416
+ | 0.176 | 1100 | 1.1258 | 1.2828 | 0.7661 | - |
417
+ | 0.192 | 1200 | 0.9865 | 1.4121 | 0.7418 | - |
418
+ | 0.208 | 1300 | 0.8064 | 1.4133 | 0.7471 | - |
419
+ | 0.224 | 1400 | 0.8036 | 1.2877 | 0.7631 | - |
420
+ | 0.24 | 1500 | 0.899 | 1.0845 | 0.7764 | - |
421
+ | 0.256 | 1600 | 0.7128 | 1.0439 | 0.7679 | - |
422
+ | 0.272 | 1700 | 0.8902 | 1.2055 | 0.7638 | - |
423
+ | 0.288 | 1800 | 0.8587 | 1.1773 | 0.7641 | - |
424
+ | 0.304 | 1900 | 0.797 | 1.0642 | 0.7898 | - |
425
+ | 0.32 | 2000 | 0.7618 | 1.0628 | 0.8232 | - |
426
+ | 0.336 | 2100 | 0.6756 | 1.1256 | 0.8155 | - |
427
+ | 0.352 | 2200 | 0.6782 | 1.0629 | 0.8382 | - |
428
+ | 0.368 | 2300 | 0.7761 | 1.1455 | 0.8071 | - |
429
+ | 0.384 | 2400 | 0.8032 | 1.0287 | 0.7884 | - |
430
+ | 0.4 | 2500 | 0.7219 | 1.0806 | 0.8323 | - |
431
+ | 0.416 | 2600 | 0.5967 | 0.9803 | 0.8180 | - |
432
+ | 0.432 | 2700 | 0.8474 | 1.3061 | 0.8223 | - |
433
+ | 0.448 | 2800 | 0.9129 | 0.9933 | 0.8136 | - |
434
+ | 0.464 | 2900 | 0.8005 | 0.8897 | 0.8235 | - |
435
+ | 0.48 | 3000 | 0.73 | 0.9185 | 0.8349 | - |
436
+ | 0.496 | 3100 | 0.7637 | 0.9318 | 0.8367 | - |
437
+ | 0.512 | 3200 | 0.5791 | 0.8514 | 0.8452 | - |
438
+ | 0.5123 | 3202 | - | - | - | 0.8662 |
439
+
440
+
441
+ ### Framework Versions
442
+ - Python: 3.10.12
443
+ - Sentence Transformers: 3.0.0
444
+ - Transformers: 4.41.1
445
+ - PyTorch: 2.3.0+cu121
446
+ - Accelerate: 0.30.1
447
+ - Datasets: 2.19.2
448
+ - Tokenizers: 0.19.1
449
+
450
+ ## Citation
451
+
452
+ ### BibTeX
453
+
454
+ #### Sentence Transformers
455
+ ```bibtex
456
+ @inproceedings{reimers-2019-sentence-bert,
457
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
458
+ author = "Reimers, Nils and Gurevych, Iryna",
459
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
460
+ month = "11",
461
+ year = "2019",
462
+ publisher = "Association for Computational Linguistics",
463
+ url = "https://arxiv.org/abs/1908.10084",
464
+ }
465
+ ```
466
+
467
+ #### MultipleNegativesRankingLoss
468
+ ```bibtex
469
+ @misc{henderson2017efficient,
470
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
471
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
472
+ year={2017},
473
+ eprint={1705.00652},
474
+ archivePrefix={arXiv},
475
+ primaryClass={cs.CL}
476
+ }
477
+ ```
478
+
479
+ <!--
480
+ ## Glossary
481
+
482
+ *Clearly define terms in order to be accessible across audiences.*
483
+ -->
484
+
485
+ <!--
486
+ ## Model Card Authors
487
+
488
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
489
+ -->
490
+
491
+ <!--
492
+ ## Model Card Contact
493
+
494
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
495
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mpnet-base",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
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-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.41.1",
23
+ "vocab_size": 30527
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+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:f13977c6bbb9b30de38bcc6b18e3d4f9c2c9252253ec63f3cf9a27720ac5c284
3
+ size 437967672
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": true,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "mask_token": "<mask>",
58
+ "model_max_length": 512,
59
+ "pad_token": "<pad>",
60
+ "sep_token": "</s>",
61
+ "strip_accents": null,
62
+ "tokenize_chinese_chars": true,
63
+ "tokenizer_class": "MPNetTokenizer",
64
+ "unk_token": "[UNK]"
65
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff