Hugging Face's logo

wwydmanski
/
arctic-pubmed-v0.1

Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:10053
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
wwydmanski commited on
Commit
75be210
·
verified ·
1 Parent(s): 4f00544

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +137 -391
  2. config.json +1 -1
  3. config_sentence_transformers.json +4 -4
  4. model.safetensors +1 -1
  5. tokenizer_config.json +1 -0
README.md CHANGED
@@ -8,44 +8,42 @@ tags:
8
  - loss:MultipleNegativesRankingLoss
9
  base_model: Snowflake/snowflake-arctic-embed-l-v2.0
10
  widget:
11
- - source_sentence: Fluorescence quenching of tryptophan residues
12
  sentences:
13
- - 'Fluorescence of buried tyrosine residues in proteins. '
14
- - 'A fluorescence quenching study of tryptophanyl residues of (Ca2+ + Mg2+)-ATPase
15
- from sarcoplasmic reticulum. '
16
- - 'Some hormonal influences on the acetylation of sulfanilamide in vivo. '
17
- - source_sentence: Human migration to the Americas
 
18
  sentences:
19
- - 'Homo sapiens in the Americas. Overview of the earliest human expansion in the
20
- New World. '
21
- - 'Profiles of College Drinkers Defined by Alcohol Behaviors at the Week Level:
22
- Replication Across Semesters and Prospective Associations With Hazardous Drinking
23
- and Dependence-Related Symptoms. '
24
- - 'Human migration. '
25
- - source_sentence: Human Mobility Prediction
26
  sentences:
27
- - 'Human mobility prediction from region functions with taxi trajectories. '
28
- - 'Understanding Human Mobility from Twitter. '
29
- - 'Ovarian cancer gene therapy using HPV-16 pseudovirion carrying the HSV-tk gene. '
30
- - source_sentence: Nevirapine Resistance
 
31
  sentences:
32
- - 'Nevirapine toxicity. '
33
- - 'Recognizing rhenium. '
34
- - 'Update on nevirapine: quest for a niche. '
35
- - source_sentence: EHL tendon reconstruction
 
 
36
  sentences:
37
- - 'A Combined Surgical Approach for Extensor Hallucis Longus Reconstruction: Two
38
- Case Reports. '
39
- - 'Flexor tendon reconstruction. '
40
- - 'Noble gases and neuroprotection: summary of current evidence. '
 
41
  pipeline_tag: sentence-similarity
42
  library_name: sentence-transformers
43
  metrics:
44
  - cosine_accuracy
45
- - dot_accuracy
46
- - manhattan_accuracy
47
- - euclidean_accuracy
48
- - max_accuracy
49
  model-index:
50
  - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l-v2.0
51
  results:
@@ -57,20 +55,8 @@ model-index:
57
  type: triplet-dev
58
  metrics:
59
  - type: cosine_accuracy
60
- value: 0.932
61
  name: Cosine Accuracy
62
- - type: dot_accuracy
63
- value: 0.066
64
- name: Dot Accuracy
65
- - type: manhattan_accuracy
66
- value: 0.933
67
- name: Manhattan Accuracy
68
- - type: euclidean_accuracy
69
- value: 0.932
70
- name: Euclidean Accuracy
71
- - type: max_accuracy
72
- value: 0.933
73
- name: Max Accuracy
74
  ---
75
 
76
  # SentenceTransformer based on Snowflake/snowflake-arctic-embed-l-v2.0
@@ -83,7 +69,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [S
83
  - **Model Type:** Sentence Transformer
84
  - **Base model:** [Snowflake/snowflake-arctic-embed-l-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) <!-- at revision 7f311bb640ad3babc0a4e3a8873240dcba44c9d2 -->
85
  - **Maximum Sequence Length:** 8192 tokens
86
- - **Output Dimensionality:** 1024 tokens
87
  - **Similarity Function:** Cosine Similarity
88
  - **Training Dataset:**
89
  - json
@@ -124,9 +110,9 @@ from sentence_transformers import SentenceTransformer
124
  model = SentenceTransformer("sentence_transformers_model_id")
125
  # Run inference
126
  sentences = [
127
- 'EHL tendon reconstruction',
128
- 'A Combined Surgical Approach for Extensor Hallucis Longus Reconstruction: Two Case Reports. ',
129
- 'Flexor tendon reconstruction. ',
130
  ]
131
  embeddings = model.encode(sentences)
132
  print(embeddings.shape)
@@ -167,16 +153,13 @@ You can finetune this model on your own dataset.
167
  ### Metrics
168
 
169
  #### Triplet
 
170
  * Dataset: `triplet-dev`
171
  * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
172
 
173
  | Metric | Value |
174
  |:--------------------|:----------|
175
- | **cosine_accuracy** | **0.932** |
176
- | dot_accuracy | 0.066 |
177
- | manhattan_accuracy | 0.933 |
178
- | euclidean_accuracy | 0.932 |
179
- | max_accuracy | 0.933 |
180
 
181
  <!--
182
  ## Bias, Risks and Limitations
@@ -200,16 +183,16 @@ You can finetune this model on your own dataset.
200
  * Size: 10,053 training samples
201
  * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
202
  * Approximate statistics based on the first 1000 samples:
203
- | | anchor | positive | negative |
204
- |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
205
- | type | string | string | string |
206
- | details | <ul><li>min: 4 tokens</li><li>mean: 10.55 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.45 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 16.1 tokens</li><li>max: 55 tokens</li></ul> |
207
  * Samples:
208
- | anchor | positive | negative |
209
- |:-------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------|
210
- | <code>COM-induced secretome changes in U937 monocytes</code> | <code>Characterization of calcium oxalate crystal-induced changes in the secretome of U937 human monocytes. </code> | <code>Monocytes. </code> |
211
- | <code>Metamaterials</code> | <code>Sound attenuation optimization using metaporous materials tuned on exceptional points. </code> | <code>Metamaterials: A cat's eye for all directions. </code> |
212
- | <code>Pediatric Parasitology</code> | <code>Parasitic infections among school age children 6 to 11-years-of-age in the Eastern province. </code> | <code>[DIALOGUE ON PEDIATRIC PARASITOLOGY]. </code> |
213
  * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
214
  ```json
215
  {
@@ -222,9 +205,8 @@ You can finetune this model on your own dataset.
222
  #### Non-Default Hyperparameters
223
 
224
  - `eval_strategy`: steps
225
- - `per_device_train_batch_size`: 32
226
- - `per_device_eval_batch_size`: 32
227
- - `learning_rate`: 0.001
228
  - `num_train_epochs`: 1
229
  - `lr_scheduler_type`: cosine_with_restarts
230
  - `warmup_ratio`: 0.1
@@ -238,14 +220,14 @@ You can finetune this model on your own dataset.
238
  - `do_predict`: False
239
  - `eval_strategy`: steps
240
  - `prediction_loss_only`: True
241
- - `per_device_train_batch_size`: 32
242
- - `per_device_eval_batch_size`: 32
243
  - `per_gpu_train_batch_size`: None
244
  - `per_gpu_eval_batch_size`: None
245
  - `gradient_accumulation_steps`: 1
246
  - `eval_accumulation_steps`: None
247
  - `torch_empty_cache_steps`: None
248
- - `learning_rate`: 0.001
249
  - `weight_decay`: 0.0
250
  - `adam_beta1`: 0.9
251
  - `adam_beta2`: 0.999
@@ -316,11 +298,12 @@ You can finetune this model on your own dataset.
316
  - `resume_from_checkpoint`: None
317
  - `hub_model_id`: None
318
  - `hub_strategy`: every_save
319
- - `hub_private_repo`: False
320
  - `hub_always_push`: False
321
  - `gradient_checkpointing`: False
322
  - `gradient_checkpointing_kwargs`: None
323
  - `include_inputs_for_metrics`: False
 
324
  - `eval_do_concat_batches`: True
325
  - `fp16_backend`: auto
326
  - `push_to_hub_model_id`: None
@@ -344,343 +327,106 @@ You can finetune this model on your own dataset.
344
  - `eval_on_start`: False
345
  - `use_liger_kernel`: False
346
  - `eval_use_gather_object`: False
 
 
347
  - `batch_sampler`: no_duplicates
348
  - `multi_dataset_batch_sampler`: proportional
349
 
350
  </details>
351
 
352
  ### Training Logs
353
- <details><summary>Click to expand</summary>
354
-
355
  | Epoch | Step | Training Loss | triplet-dev_cosine_accuracy |
356
  |:------:|:----:|:-------------:|:---------------------------:|
357
  | 0 | 0 | - | 0.58 |
358
- | 0.0032 | 1 | 1.3744 | - |
359
- | 0.0063 | 2 | 1.2294 | - |
360
- | 0.0095 | 3 | 1.2058 | - |
361
- | 0.0127 | 4 | 1.2122 | - |
362
- | 0.0159 | 5 | 1.5614 | - |
363
- | 0.0190 | 6 | 1.2478 | - |
364
- | 0.0222 | 7 | 0.7569 | - |
365
- | 0.0254 | 8 | 0.734 | - |
366
- | 0.0286 | 9 | 1.16 | - |
367
- | 0.0317 | 10 | 0.5651 | 0.711 |
368
- | 0.0349 | 11 | 1.1555 | - |
369
- | 0.0381 | 12 | 0.7146 | - |
370
- | 0.0413 | 13 | 0.5214 | - |
371
- | 0.0444 | 14 | 0.6155 | - |
372
- | 0.0476 | 15 | 0.6998 | - |
373
- | 0.0508 | 16 | 1.3517 | - |
374
- | 0.0540 | 17 | 0.6028 | - |
375
- | 0.0571 | 18 | 0.7165 | - |
376
- | 0.0603 | 19 | 0.712 | - |
377
- | 0.0635 | 20 | 0.6988 | 0.86 |
378
- | 0.0667 | 21 | 0.6056 | - |
379
- | 0.0698 | 22 | 0.6244 | - |
380
- | 0.0730 | 23 | 0.8347 | - |
381
- | 0.0762 | 24 | 0.5033 | - |
382
- | 0.0794 | 25 | 0.9254 | - |
383
- | 0.0825 | 26 | 0.3873 | - |
384
- | 0.0857 | 27 | 0.5664 | - |
385
- | 0.0889 | 28 | 0.6109 | - |
386
- | 0.0921 | 29 | 0.4903 | - |
387
- | 0.0952 | 30 | 0.696 | 0.874 |
388
- | 0.0984 | 31 | 1.1626 | - |
389
- | 0.1016 | 32 | 0.3114 | - |
390
- | 0.1048 | 33 | 0.8082 | - |
391
- | 0.1079 | 34 | 0.9072 | - |
392
- | 0.1111 | 35 | 0.3157 | - |
393
- | 0.1143 | 36 | 0.8342 | - |
394
- | 0.1175 | 37 | 0.3941 | - |
395
- | 0.1206 | 38 | 0.4069 | - |
396
- | 0.1238 | 39 | 0.4186 | - |
397
- | 0.1270 | 40 | 0.4617 | 0.902 |
398
- | 0.1302 | 41 | 0.5417 | - |
399
- | 0.1333 | 42 | 0.4168 | - |
400
- | 0.1365 | 43 | 0.702 | - |
401
- | 0.1397 | 44 | 0.7394 | - |
402
- | 0.1429 | 45 | 0.4674 | - |
403
- | 0.1460 | 46 | 0.6938 | - |
404
- | 0.1492 | 47 | 0.5182 | - |
405
- | 0.1524 | 48 | 0.3144 | - |
406
- | 0.1556 | 49 | 0.3902 | - |
407
- | 0.1587 | 50 | 0.4609 | 0.906 |
408
- | 0.1619 | 51 | 0.5452 | - |
409
- | 0.1651 | 52 | 0.2095 | - |
410
- | 0.1683 | 53 | 0.4914 | - |
411
- | 0.1714 | 54 | 0.2427 | - |
412
- | 0.1746 | 55 | 0.5135 | - |
413
- | 0.1778 | 56 | 0.3787 | - |
414
- | 0.1810 | 57 | 0.5147 | - |
415
- | 0.1841 | 58 | 0.7125 | - |
416
- | 0.1873 | 59 | 0.4769 | - |
417
- | 0.1905 | 60 | 0.7483 | 0.893 |
418
- | 0.1937 | 61 | 0.1751 | - |
419
- | 0.1968 | 62 | 0.2693 | - |
420
- | 0.2 | 63 | 0.3711 | - |
421
- | 0.2032 | 64 | 0.2972 | - |
422
- | 0.2063 | 65 | 0.2336 | - |
423
- | 0.2095 | 66 | 0.2769 | - |
424
- | 0.2127 | 67 | 0.3912 | - |
425
- | 0.2159 | 68 | 0.8191 | - |
426
- | 0.2190 | 69 | 0.6568 | - |
427
- | 0.2222 | 70 | 0.3074 | 0.923 |
428
- | 0.2254 | 71 | 0.3406 | - |
429
- | 0.2286 | 72 | 0.4384 | - |
430
- | 0.2317 | 73 | 0.3491 | - |
431
- | 0.2349 | 74 | 0.3305 | - |
432
- | 0.2381 | 75 | 0.599 | - |
433
- | 0.2413 | 76 | 0.2404 | - |
434
- | 0.2444 | 77 | 0.3085 | - |
435
- | 0.2476 | 78 | 0.3822 | - |
436
- | 0.2508 | 79 | 0.2815 | - |
437
- | 0.2540 | 80 | 0.6003 | 0.909 |
438
- | 0.2571 | 81 | 0.4779 | - |
439
- | 0.2603 | 82 | 0.8126 | - |
440
- | 0.2635 | 83 | 0.381 | - |
441
- | 0.2667 | 84 | 0.2567 | - |
442
- | 0.2698 | 85 | 0.4422 | - |
443
- | 0.2730 | 86 | 0.592 | - |
444
- | 0.2762 | 87 | 0.5947 | - |
445
- | 0.2794 | 88 | 0.3042 | - |
446
- | 0.2825 | 89 | 0.5894 | - |
447
- | 0.2857 | 90 | 0.3807 | 0.904 |
448
- | 0.2889 | 91 | 0.4121 | - |
449
- | 0.2921 | 92 | 0.4026 | - |
450
- | 0.2952 | 93 | 0.5424 | - |
451
- | 0.2984 | 94 | 0.359 | - |
452
- | 0.3016 | 95 | 0.3766 | - |
453
- | 0.3048 | 96 | 0.9112 | - |
454
- | 0.3079 | 97 | 0.5143 | - |
455
- | 0.3111 | 98 | 0.2945 | - |
456
- | 0.3143 | 99 | 0.7727 | - |
457
- | 0.3175 | 100 | 0.375 | 0.91 |
458
- | 0.3206 | 101 | 0.6702 | - |
459
- | 0.3238 | 102 | 0.8303 | - |
460
- | 0.3270 | 103 | 0.4229 | - |
461
- | 0.3302 | 104 | 0.4837 | - |
462
- | 0.3333 | 105 | 0.4012 | - |
463
- | 0.3365 | 106 | 0.4679 | - |
464
- | 0.3397 | 107 | 0.2605 | - |
465
- | 0.3429 | 108 | 0.292 | - |
466
- | 0.3460 | 109 | 0.2689 | - |
467
- | 0.3492 | 110 | 0.5062 | 0.899 |
468
- | 0.3524 | 111 | 0.9799 | - |
469
- | 0.3556 | 112 | 0.2778 | - |
470
- | 0.3587 | 113 | 0.6223 | - |
471
- | 0.3619 | 114 | 0.4111 | - |
472
- | 0.3651 | 115 | 0.4589 | - |
473
- | 0.3683 | 116 | 0.4762 | - |
474
- | 0.3714 | 117 | 0.5911 | - |
475
- | 0.3746 | 118 | 0.4893 | - |
476
- | 0.3778 | 119 | 0.2245 | - |
477
- | 0.3810 | 120 | 0.5912 | 0.923 |
478
- | 0.3841 | 121 | 0.4241 | - |
479
- | 0.3873 | 122 | 0.7066 | - |
480
- | 0.3905 | 123 | 0.4916 | - |
481
- | 0.3937 | 124 | 0.5478 | - |
482
- | 0.3968 | 125 | 0.401 | - |
483
- | 0.4 | 126 | 0.3737 | - |
484
- | 0.4032 | 127 | 0.4901 | - |
485
- | 0.4063 | 128 | 0.7427 | - |
486
- | 0.4095 | 129 | 0.6794 | - |
487
- | 0.4127 | 130 | 0.3169 | 0.921 |
488
- | 0.4159 | 131 | 0.3946 | - |
489
- | 0.4190 | 132 | 0.2456 | - |
490
- | 0.4222 | 133 | 0.5542 | - |
491
- | 0.4254 | 134 | 0.2707 | - |
492
- | 0.4286 | 135 | 0.6747 | - |
493
- | 0.4317 | 136 | 0.336 | - |
494
- | 0.4349 | 137 | 0.5647 | - |
495
- | 0.4381 | 138 | 0.2744 | - |
496
- | 0.4413 | 139 | 0.4579 | - |
497
- | 0.4444 | 140 | 0.2718 | 0.899 |
498
- | 0.4476 | 141 | 0.7238 | - |
499
- | 0.4508 | 142 | 0.2833 | - |
500
- | 0.4540 | 143 | 0.6608 | - |
501
- | 0.4571 | 144 | 0.4052 | - |
502
- | 0.4603 | 145 | 0.3781 | - |
503
- | 0.4635 | 146 | 0.2905 | - |
504
- | 0.4667 | 147 | 0.4854 | - |
505
- | 0.4698 | 148 | 0.3493 | - |
506
- | 0.4730 | 149 | 0.4885 | - |
507
- | 0.4762 | 150 | 0.3831 | 0.921 |
508
- | 0.4794 | 151 | 0.4424 | - |
509
- | 0.4825 | 152 | 0.4305 | - |
510
- | 0.4857 | 153 | 0.5456 | - |
511
- | 0.4889 | 154 | 0.4577 | - |
512
- | 0.4921 | 155 | 0.2772 | - |
513
- | 0.4952 | 156 | 0.5053 | - |
514
- | 0.4984 | 157 | 0.2823 | - |
515
- | 0.5016 | 158 | 0.4512 | - |
516
- | 0.5048 | 159 | 0.3884 | - |
517
- | 0.5079 | 160 | 0.6302 | 0.922 |
518
- | 0.5111 | 161 | 0.5108 | - |
519
- | 0.5143 | 162 | 0.3148 | - |
520
- | 0.5175 | 163 | 0.3471 | - |
521
- | 0.5206 | 164 | 0.3473 | - |
522
- | 0.5238 | 165 | 0.8119 | - |
523
- | 0.5270 | 166 | 0.5589 | - |
524
- | 0.5302 | 167 | 0.6691 | - |
525
- | 0.5333 | 168 | 0.5297 | - |
526
- | 0.5365 | 169 | 0.4171 | - |
527
- | 0.5397 | 170 | 0.3299 | 0.92 |
528
- | 0.5429 | 171 | 0.3409 | - |
529
- | 0.5460 | 172 | 0.4409 | - |
530
- | 0.5492 | 173 | 0.2566 | - |
531
- | 0.5524 | 174 | 0.2815 | - |
532
- | 0.5556 | 175 | 0.401 | - |
533
- | 0.5587 | 176 | 0.346 | - |
534
- | 0.5619 | 177 | 0.285 | - |
535
- | 0.5651 | 178 | 0.3536 | - |
536
- | 0.5683 | 179 | 0.3927 | - |
537
- | 0.5714 | 180 | 0.5802 | 0.92 |
538
- | 0.5746 | 181 | 0.17 | - |
539
- | 0.5778 | 182 | 0.679 | - |
540
- | 0.5810 | 183 | 0.3586 | - |
541
- | 0.5841 | 184 | 0.4641 | - |
542
- | 0.5873 | 185 | 0.7828 | - |
543
- | 0.5905 | 186 | 0.6755 | - |
544
- | 0.5937 | 187 | 0.1829 | - |
545
- | 0.5968 | 188 | 0.4509 | - |
546
- | 0.6 | 189 | 0.5535 | - |
547
- | 0.6032 | 190 | 0.28 | 0.93 |
548
- | 0.6063 | 191 | 0.5103 | - |
549
- | 0.6095 | 192 | 0.5829 | - |
550
- | 0.6127 | 193 | 0.6395 | - |
551
- | 0.6159 | 194 | 0.3645 | - |
552
- | 0.6190 | 195 | 0.6134 | - |
553
- | 0.6222 | 196 | 0.3655 | - |
554
- | 0.6254 | 197 | 0.3102 | - |
555
- | 0.6286 | 198 | 0.6075 | - |
556
- | 0.6317 | 199 | 0.2264 | - |
557
- | 0.6349 | 200 | 0.5285 | 0.92 |
558
- | 0.6381 | 201 | 0.5746 | - |
559
- | 0.6413 | 202 | 0.5452 | - |
560
- | 0.6444 | 203 | 0.3349 | - |
561
- | 0.6476 | 204 | 0.3771 | - |
562
- | 0.6508 | 205 | 0.5956 | - |
563
- | 0.6540 | 206 | 0.3077 | - |
564
- | 0.6571 | 207 | 0.5275 | - |
565
- | 0.6603 | 208 | 0.3552 | - |
566
- | 0.6635 | 209 | 0.385 | - |
567
- | 0.6667 | 210 | 0.2846 | 0.933 |
568
- | 0.6698 | 211 | 0.3865 | - |
569
- | 0.6730 | 212 | 0.4522 | - |
570
- | 0.6762 | 213 | 0.0635 | - |
571
- | 0.6794 | 214 | 0.5131 | - |
572
- | 0.6825 | 215 | 0.6883 | - |
573
- | 0.6857 | 216 | 0.464 | - |
574
- | 0.6889 | 217 | 0.666 | - |
575
- | 0.6921 | 218 | 0.7519 | - |
576
- | 0.6952 | 219 | 0.5231 | - |
577
- | 0.6984 | 220 | 0.1605 | 0.927 |
578
- | 0.7016 | 221 | 0.2982 | - |
579
- | 0.7048 | 222 | 0.47 | - |
580
- | 0.7079 | 223 | 0.3701 | - |
581
- | 0.7111 | 224 | 0.4694 | - |
582
- | 0.7143 | 225 | 0.1195 | - |
583
- | 0.7175 | 226 | 0.3682 | - |
584
- | 0.7206 | 227 | 0.311 | - |
585
- | 0.7238 | 228 | 0.5959 | - |
586
- | 0.7270 | 229 | 0.4565 | - |
587
- | 0.7302 | 230 | 0.1803 | 0.926 |
588
- | 0.7333 | 231 | 0.4599 | - |
589
- | 0.7365 | 232 | 0.2979 | - |
590
- | 0.7397 | 233 | 0.433 | - |
591
- | 0.7429 | 234 | 0.3443 | - |
592
- | 0.7460 | 235 | 0.524 | - |
593
- | 0.7492 | 236 | 0.4083 | - |
594
- | 0.7524 | 237 | 0.3159 | - |
595
- | 0.7556 | 238 | 0.4017 | - |
596
- | 0.7587 | 239 | 0.3955 | - |
597
- | 0.7619 | 240 | 0.2405 | 0.928 |
598
- | 0.7651 | 241 | 0.3249 | - |
599
- | 0.7683 | 242 | 0.2882 | - |
600
- | 0.7714 | 243 | 0.6232 | - |
601
- | 0.7746 | 244 | 0.5724 | - |
602
- | 0.7778 | 245 | 0.4484 | - |
603
- | 0.7810 | 246 | 0.4394 | - |
604
- | 0.7841 | 247 | 0.4487 | - |
605
- | 0.7873 | 248 | 0.1622 | - |
606
- | 0.7905 | 249 | 0.2732 | - |
607
- | 0.7937 | 250 | 0.4144 | 0.93 |
608
- | 0.7968 | 251 | 0.3666 | - |
609
- | 0.8 | 252 | 0.8073 | - |
610
- | 0.8032 | 253 | 0.1864 | - |
611
- | 0.8063 | 254 | 0.7214 | - |
612
- | 0.8095 | 255 | 0.3487 | - |
613
- | 0.8127 | 256 | 0.1865 | - |
614
- | 0.8159 | 257 | 0.4027 | - |
615
- | 0.8190 | 258 | 0.8281 | - |
616
- | 0.8222 | 259 | 0.5036 | - |
617
- | 0.8254 | 260 | 0.2968 | 0.922 |
618
- | 0.8286 | 261 | 0.4473 | - |
619
- | 0.8317 | 262 | 0.2062 | - |
620
- | 0.8349 | 263 | 0.4047 | - |
621
- | 0.8381 | 264 | 0.1914 | - |
622
- | 0.8413 | 265 | 0.3805 | - |
623
- | 0.8444 | 266 | 0.1199 | - |
624
- | 0.8476 | 267 | 0.2759 | - |
625
- | 0.8508 | 268 | 0.2259 | - |
626
- | 0.8540 | 269 | 0.2683 | - |
627
- | 0.8571 | 270 | 0.6274 | 0.935 |
628
- | 0.8603 | 271 | 0.4319 | - |
629
- | 0.8635 | 272 | 0.5258 | - |
630
- | 0.8667 | 273 | 0.2761 | - |
631
- | 0.8698 | 274 | 0.5513 | - |
632
- | 0.8730 | 275 | 0.1808 | - |
633
- | 0.8762 | 276 | 0.495 | - |
634
- | 0.8794 | 277 | 0.2988 | - |
635
- | 0.8825 | 278 | 0.5273 | - |
636
- | 0.8857 | 279 | 0.7676 | - |
637
- | 0.8889 | 280 | 0.5209 | 0.933 |
638
- | 0.8921 | 281 | 0.4381 | - |
639
- | 0.8952 | 282 | 0.5668 | - |
640
- | 0.8984 | 283 | 0.5858 | - |
641
- | 0.9016 | 284 | 0.7875 | - |
642
- | 0.9048 | 285 | 0.2061 | - |
643
- | 0.9079 | 286 | 0.268 | - |
644
- | 0.9111 | 287 | 0.2322 | - |
645
- | 0.9143 | 288 | 0.233 | - |
646
- | 0.9175 | 289 | 0.3316 | - |
647
- | 0.9206 | 290 | 0.5176 | 0.932 |
648
- | 0.9238 | 291 | 0.3647 | - |
649
- | 0.9270 | 292 | 0.5906 | - |
650
- | 0.9302 | 293 | 0.5098 | - |
651
- | 0.9333 | 294 | 0.3505 | - |
652
- | 0.9365 | 295 | 0.379 | - |
653
- | 0.9397 | 296 | 0.5529 | - |
654
- | 0.9429 | 297 | 0.4044 | - |
655
- | 0.9460 | 298 | 0.4637 | - |
656
- | 0.9492 | 299 | 0.4014 | - |
657
- | 0.9524 | 300 | 0.692 | 0.932 |
658
- | 0.9556 | 301 | 0.6072 | - |
659
- | 0.9587 | 302 | 0.2852 | - |
660
- | 0.9619 | 303 | 0.3548 | - |
661
- | 0.9651 | 304 | 0.7898 | - |
662
- | 0.9683 | 305 | 0.4211 | - |
663
- | 0.9714 | 306 | 0.2773 | - |
664
- | 0.9746 | 307 | 0.4182 | - |
665
- | 0.9778 | 308 | 0.2633 | - |
666
- | 0.9810 | 309 | 0.6833 | - |
667
- | 0.9841 | 310 | 0.2619 | 0.932 |
668
- | 0.9873 | 311 | 0.3085 | - |
669
- | 0.9905 | 312 | 0.3142 | - |
670
- | 0.9937 | 313 | 0.221 | - |
671
- | 0.9968 | 314 | 0.348 | - |
672
- | 1.0 | 315 | 0.0322 | 0.932 |
673
 
674
- </details>
675
 
676
  ### Framework Versions
677
- - Python: 3.9.19
678
- - Sentence Transformers: 3.1.1
679
- - Transformers: 4.45.2
680
- - PyTorch: 2.5.0
681
- - Accelerate: 1.0.1
682
  - Datasets: 2.19.0
683
- - Tokenizers: 0.20.3
684
 
685
  ## Citation
686
 
 
8
  - loss:MultipleNegativesRankingLoss
9
  base_model: Snowflake/snowflake-arctic-embed-l-v2.0
10
  widget:
11
+ - source_sentence: Nursing Reform
12
  sentences:
13
+ - 'Staff nurses speak out on reform. '
14
+ - 'Synthesis of graphene with different layers on paper-like sintered stainless
15
+ steel fibers and its application as a metal-free catalyst for catalytic wet peroxide
16
+ oxidation of phenol. '
17
+ - 'Nursing reformation. '
18
+ - source_sentence: NiTiO3 composite
19
  sentences:
20
+ - 'Fabrication and electromagnetic performance of talc/NiTiO 3 composite. '
21
+ - 'Nickel-titanium usage and breakage: an update. '
22
+ - 'Innervational plasticity of the oculomotor system. '
23
+ - source_sentence: Single-Session Competency Framework
 
 
 
24
  sentences:
25
+ - 'Competency assessment: one step at the time. '
26
+ - 'Optothermal molecule trapping by opposing fluid flow with thermophoretic drift. '
27
+ - 'Describing a Clinical Group Coding Method for Identifying Competencies in an
28
+ Allied Health Single Session. '
29
+ - source_sentence: Streptococcal myositis treatment outcomes
30
  sentences:
31
+ - 'Evaluation of penicillin and hyperbaric oxygen in the treatment of streptococcal
32
+ myositis. '
33
+ - 'Polymicrobial myositis. '
34
+ - 'Parse''s criteria for evaluation of theory with a comparison of Fawcett''s and
35
+ Parse''s approaches. '
36
+ - source_sentence: Risk-based water quality monitoring framework
37
  sentences:
38
+ - 'Development of a new risk-based framework to guide investment in water quality
39
+ monitoring. '
40
+ - 'NADPH oxidase 1 supports proliferation of colon cancer cells by modulating reactive
41
+ oxygen species-dependent signal transduction. '
42
+ - 'Water quality monitoring strategies - A review and future perspectives. '
43
  pipeline_tag: sentence-similarity
44
  library_name: sentence-transformers
45
  metrics:
46
  - cosine_accuracy
 
 
 
 
47
  model-index:
48
  - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l-v2.0
49
  results:
 
55
  type: triplet-dev
56
  metrics:
57
  - type: cosine_accuracy
58
+ value: 0.802
59
  name: Cosine Accuracy
 
 
 
 
 
 
 
 
 
 
 
 
60
  ---
61
 
62
  # SentenceTransformer based on Snowflake/snowflake-arctic-embed-l-v2.0
 
69
  - **Model Type:** Sentence Transformer
70
  - **Base model:** [Snowflake/snowflake-arctic-embed-l-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) <!-- at revision 7f311bb640ad3babc0a4e3a8873240dcba44c9d2 -->
71
  - **Maximum Sequence Length:** 8192 tokens
72
+ - **Output Dimensionality:** 1024 dimensions
73
  - **Similarity Function:** Cosine Similarity
74
  - **Training Dataset:**
75
  - json
 
110
  model = SentenceTransformer("sentence_transformers_model_id")
111
  # Run inference
112
  sentences = [
113
+ 'Risk-based water quality monitoring framework',
114
+ 'Development of a new risk-based framework to guide investment in water quality monitoring. ',
115
+ 'Water quality monitoring strategies - A review and future perspectives. ',
116
  ]
117
  embeddings = model.encode(sentences)
118
  print(embeddings.shape)
 
153
  ### Metrics
154
 
155
  #### Triplet
156
+
157
  * Dataset: `triplet-dev`
158
  * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
159
 
160
  | Metric | Value |
161
  |:--------------------|:----------|
162
+ | **cosine_accuracy** | **0.802** |
 
 
 
 
163
 
164
  <!--
165
  ## Bias, Risks and Limitations
 
183
  * Size: 10,053 training samples
184
  * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
185
  * Approximate statistics based on the first 1000 samples:
186
+ | | anchor | positive | negative |
187
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
188
+ | type | string | string | string |
189
+ | details | <ul><li>min: 4 tokens</li><li>mean: 10.58 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 26.91 tokens</li><li>max: 79 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.99 tokens</li><li>max: 61 tokens</li></ul> |
190
  * Samples:
191
+ | anchor | positive | negative |
192
+ |:--------------------------------------------------|:--------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------|
193
+ | <code>Pediatric Infectious Disease Control</code> | <code>[Urgent tasks in scientific studies concerning the control of infectious diseases in children]. </code> | <code>Pediatric workforce: a look at pediatric infectious diseases data from the American Board of Pediatrics. </code> |
194
+ | <code>Thermal coefficient of phase shift</code> | <code>Thermal characteristics of phase shift in jacketed optical fibers. </code> | <code>Thermal effects. </code> |
195
+ | <code>Renal biomarkers in heart failure</code> | <code>Current and novel renal biomarkers in heart failure. </code> | <code>Cardiac biomarkers of heart failure in chronic kidney disease. </code> |
196
  * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
197
  ```json
198
  {
 
205
  #### Non-Default Hyperparameters
206
 
207
  - `eval_strategy`: steps
208
+ - `per_device_train_batch_size`: 128
209
+ - `per_device_eval_batch_size`: 128
 
210
  - `num_train_epochs`: 1
211
  - `lr_scheduler_type`: cosine_with_restarts
212
  - `warmup_ratio`: 0.1
 
220
  - `do_predict`: False
221
  - `eval_strategy`: steps
222
  - `prediction_loss_only`: True
223
+ - `per_device_train_batch_size`: 128
224
+ - `per_device_eval_batch_size`: 128
225
  - `per_gpu_train_batch_size`: None
226
  - `per_gpu_eval_batch_size`: None
227
  - `gradient_accumulation_steps`: 1
228
  - `eval_accumulation_steps`: None
229
  - `torch_empty_cache_steps`: None
230
+ - `learning_rate`: 5e-05
231
  - `weight_decay`: 0.0
232
  - `adam_beta1`: 0.9
233
  - `adam_beta2`: 0.999
 
298
  - `resume_from_checkpoint`: None
299
  - `hub_model_id`: None
300
  - `hub_strategy`: every_save
301
+ - `hub_private_repo`: None
302
  - `hub_always_push`: False
303
  - `gradient_checkpointing`: False
304
  - `gradient_checkpointing_kwargs`: None
305
  - `include_inputs_for_metrics`: False
306
+ - `include_for_metrics`: []
307
  - `eval_do_concat_batches`: True
308
  - `fp16_backend`: auto
309
  - `push_to_hub_model_id`: None
 
327
  - `eval_on_start`: False
328
  - `use_liger_kernel`: False
329
  - `eval_use_gather_object`: False
330
+ - `average_tokens_across_devices`: False
331
+ - `prompts`: None
332
  - `batch_sampler`: no_duplicates
333
  - `multi_dataset_batch_sampler`: proportional
334
 
335
  </details>
336
 
337
  ### Training Logs
 
 
338
  | Epoch | Step | Training Loss | triplet-dev_cosine_accuracy |
339
  |:------:|:----:|:-------------:|:---------------------------:|
340
  | 0 | 0 | - | 0.58 |
341
+ | 0.0127 | 1 | 1.677 | - |
342
+ | 0.0253 | 2 | 1.7295 | - |
343
+ | 0.0380 | 3 | 1.6713 | - |
344
+ | 0.0506 | 4 | 1.4761 | - |
345
+ | 0.0633 | 5 | 1.3731 | - |
346
+ | 0.0759 | 6 | 1.8333 | - |
347
+ | 0.0886 | 7 | 1.3218 | - |
348
+ | 0.1013 | 8 | 1.1539 | - |
349
+ | 0.1139 | 9 | 1.4003 | - |
350
+ | 0.1266 | 10 | 1.4514 | - |
351
+ | 0.1392 | 11 | 1.0803 | - |
352
+ | 0.1519 | 12 | 1.183 | - |
353
+ | 0.1646 | 13 | 0.9984 | - |
354
+ | 0.1772 | 14 | 1.2043 | - |
355
+ | 0.1899 | 15 | 1.1367 | - |
356
+ | 0.2025 | 16 | 1.1863 | - |
357
+ | 0.2152 | 17 | 1.0185 | - |
358
+ | 0.2278 | 18 | 0.9038 | - |
359
+ | 0.2405 | 19 | 0.8942 | - |
360
+ | 0.2532 | 20 | 1.0396 | - |
361
+ | 0.2658 | 21 | 1.1067 | - |
362
+ | 0.2785 | 22 | 1.0281 | - |
363
+ | 0.2911 | 23 | 1.1479 | - |
364
+ | 0.3038 | 24 | 1.2893 | - |
365
+ | 0.3165 | 25 | 1.0388 | - |
366
+ | 0.3291 | 26 | 1.1925 | - |
367
+ | 0.3418 | 27 | 0.9564 | - |
368
+ | 0.3544 | 28 | 0.8533 | - |
369
+ | 0.3671 | 29 | 0.9999 | - |
370
+ | 0.3797 | 30 | 1.126 | - |
371
+ | 0.3924 | 31 | 0.9898 | - |
372
+ | 0.4051 | 32 | 0.8786 | - |
373
+ | 0.4177 | 33 | 0.9878 | - |
374
+ | 0.4304 | 34 | 1.0988 | - |
375
+ | 0.4430 | 35 | 0.9721 | - |
376
+ | 0.4557 | 36 | 0.838 | - |
377
+ | 0.4684 | 37 | 0.9935 | - |
378
+ | 0.4810 | 38 | 1.1439 | - |
379
+ | 0.4937 | 39 | 0.7076 | - |
380
+ | 0.5063 | 40 | 1.0033 | - |
381
+ | 0.5190 | 41 | 1.0411 | - |
382
+ | 0.5316 | 42 | 0.8646 | - |
383
+ | 0.5443 | 43 | 0.8991 | - |
384
+ | 0.5570 | 44 | 0.6337 | - |
385
+ | 0.5696 | 45 | 1.0695 | - |
386
+ | 0.5823 | 46 | 0.9144 | - |
387
+ | 0.5949 | 47 | 0.9248 | - |
388
+ | 0.6076 | 48 | 0.7711 | - |
389
+ | 0.6203 | 49 | 1.0001 | - |
390
+ | 0.6329 | 50 | 1.0151 | - |
391
+ | 0.6456 | 51 | 1.06 | - |
392
+ | 0.6582 | 52 | 0.8105 | - |
393
+ | 0.6709 | 53 | 0.6892 | - |
394
+ | 0.6835 | 54 | 1.1341 | - |
395
+ | 0.6962 | 55 | 0.9726 | - |
396
+ | 0.7089 | 56 | 0.8783 | - |
397
+ | 0.7215 | 57 | 0.8084 | - |
398
+ | 0.7342 | 58 | 1.089 | - |
399
+ | 0.7468 | 59 | 0.8486 | - |
400
+ | 0.7595 | 60 | 0.8507 | - |
401
+ | 0.7722 | 61 | 0.9502 | - |
402
+ | 0.7848 | 62 | 0.8178 | - |
403
+ | 0.7975 | 63 | 1.0142 | - |
404
+ | 0.8101 | 64 | 0.9516 | - |
405
+ | 0.8228 | 65 | 0.9399 | - |
406
+ | 0.8354 | 66 | 0.7602 | - |
407
+ | 0.8481 | 67 | 0.8389 | - |
408
+ | 0.8608 | 68 | 0.9234 | - |
409
+ | 0.8734 | 69 | 0.9747 | - |
410
+ | 0.8861 | 70 | 1.1591 | - |
411
+ | 0.8987 | 71 | 1.0074 | - |
412
+ | 0.9114 | 72 | 0.8169 | - |
413
+ | 0.9241 | 73 | 0.9561 | - |
414
+ | 0.9367 | 74 | 0.9406 | - |
415
+ | 0.9494 | 75 | 0.9603 | - |
416
+ | 0.9620 | 76 | 0.8758 | - |
417
+ | 0.9747 | 77 | 0.8546 | - |
418
+ | 0.9873 | 78 | 0.7313 | - |
419
+ | 1.0 | 79 | 0.6568 | 0.802 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
420
 
 
421
 
422
  ### Framework Versions
423
+ - Python: 3.12.3
424
+ - Sentence Transformers: 3.3.1
425
+ - Transformers: 4.48.0.dev0
426
+ - PyTorch: 2.5.1
427
+ - Accelerate: 1.2.1
428
  - Datasets: 2.19.0
429
+ - Tokenizers: 0.21.0
430
 
431
  ## Citation
432
 
config.json CHANGED
@@ -21,7 +21,7 @@
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
  "torch_dtype": "float32",
24
- "transformers_version": "4.45.2",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 250002
 
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.48.0.dev0",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 250002
config_sentence_transformers.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "__version__": {
3
- "sentence_transformers": "3.1.1",
4
- "transformers": "4.45.2",
5
- "pytorch": "2.5.0"
6
  },
7
  "prompts": {
8
  "query": "query: "
9
  },
10
  "default_prompt_name": null,
11
- "similarity_fn_name": null
12
  }
 
1
  {
2
  "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.48.0.dev0",
5
+ "pytorch": "2.5.1"
6
  },
7
  "prompts": {
8
  "query": "query: "
9
  },
10
  "default_prompt_name": null,
11
+ "similarity_fn_name": "cosine"
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53b2f2fdb09b12ee82a6a0e90ab7d94e1f9f91e39d9f1522566d89548e46da80
3
  size 2271064456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c2654e18c5b8eae32ae1f04ad1ad6d8be0be94000f327c1fb8bd9c89763dfd9
3
  size 2271064456
tokenizer_config.json CHANGED
@@ -45,6 +45,7 @@
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
 
48
  "mask_token": "<mask>",
49
  "max_length": 512,
50
  "model_max_length": 8192,
 
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
  "mask_token": "<mask>",
50
  "max_length": 512,
51
  "model_max_length": 8192,