sileod commited on
Commit
d4f93e5
·
verified ·
1 Parent(s): ee7fda4

Add new SentenceTransformer model

Browse files
README.md CHANGED
@@ -131,7 +131,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [j
131
  ### Model Description
132
  - **Model Type:** Sentence Transformer
133
  - **Base model:** [jhu-clsp/ettin-encoder-17m](https://huggingface.co/jhu-clsp/ettin-encoder-17m) <!-- at revision 987607455c61e7a5bbc85f7758e0512ea6d0ae4c -->
134
- - **Maximum Sequence Length:** 128 tokens
135
  - **Output Dimensionality:** 256 dimensions
136
  - **Similarity Function:** Cosine Similarity
137
  - **Training Datasets:**
@@ -166,7 +166,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [j
166
 
167
  ```
168
  SentenceTransformer(
169
- (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
170
  (1): Pooling({'word_embedding_dimension': 256, '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})
171
  )
172
  ```
@@ -204,7 +204,7 @@ print(query_embeddings.shape, document_embeddings.shape)
204
  # Get the similarity scores for the embeddings
205
  similarities = model.similarity(query_embeddings, document_embeddings)
206
  print(similarities)
207
- # tensor([[ 0.6162, 0.7105, -0.1445]])
208
  ```
209
 
210
  <!--
@@ -257,7 +257,7 @@ You can finetune this model on your own dataset.
257
  | | sentence1 | sentence2 |
258
  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
259
  | type | string | string |
260
- | details | <ul><li>min: 6 tokens</li><li>mean: 48.84 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 15.66 tokens</li><li>max: 122 tokens</li></ul> |
261
  * Samples:
262
  | sentence1 | sentence2 |
263
  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------|
@@ -269,7 +269,7 @@ You can finetune this model on your own dataset.
269
  {
270
  "scale": 20.0,
271
  "similarity_fct": "cos_sim",
272
- "mini_batch_size": 32,
273
  "gather_across_devices": false
274
  }
275
  ```
@@ -285,7 +285,7 @@ You can finetune this model on your own dataset.
285
  | | sentence1 | sentence2 |
286
  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
287
  | type | string | string |
288
- | details | <ul><li>min: 3 tokens</li><li>mean: 42.59 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 27.27 tokens</li><li>max: 128 tokens</li></ul> |
289
  * Samples:
290
  | sentence1 | sentence2 |
291
  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|
@@ -297,7 +297,7 @@ You can finetune this model on your own dataset.
297
  {
298
  "scale": 20.0,
299
  "similarity_fct": "cos_sim",
300
- "mini_batch_size": 32,
301
  "gather_across_devices": false
302
  }
303
  ```
@@ -313,7 +313,7 @@ You can finetune this model on your own dataset.
313
  | | sentence1 | sentence2 |
314
  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
315
  | type | string | string |
316
- | details | <ul><li>min: 3 tokens</li><li>mean: 43.41 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 12.15 tokens</li><li>max: 20 tokens</li></ul> |
317
  * Samples:
318
  | sentence1 | sentence2 |
319
  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------|
@@ -325,7 +325,7 @@ You can finetune this model on your own dataset.
325
  {
326
  "scale": 20.0,
327
  "similarity_fct": "cos_sim",
328
- "mini_batch_size": 32,
329
  "gather_across_devices": false
330
  }
331
  ```
@@ -341,7 +341,7 @@ You can finetune this model on your own dataset.
341
  | | sentence1 | sentence2 |
342
  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
343
  | type | string | string |
344
- | details | <ul><li>min: 4 tokens</li><li>mean: 63.81 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 17.99 tokens</li><li>max: 42 tokens</li></ul> |
345
  * Samples:
346
  | sentence1 | sentence2 |
347
  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------|
@@ -353,7 +353,7 @@ You can finetune this model on your own dataset.
353
  {
354
  "scale": 20.0,
355
  "similarity_fct": "cos_sim",
356
- "mini_batch_size": 32,
357
  "gather_across_devices": false
358
  }
359
  ```
@@ -381,7 +381,7 @@ You can finetune this model on your own dataset.
381
  {
382
  "scale": 20.0,
383
  "similarity_fct": "cos_sim",
384
- "mini_batch_size": 32,
385
  "gather_across_devices": false
386
  }
387
  ```
@@ -409,7 +409,7 @@ You can finetune this model on your own dataset.
409
  {
410
  "scale": 20.0,
411
  "similarity_fct": "cos_sim",
412
- "mini_batch_size": 32,
413
  "gather_across_devices": false
414
  }
415
  ```
@@ -437,7 +437,7 @@ You can finetune this model on your own dataset.
437
  {
438
  "scale": 20.0,
439
  "similarity_fct": "cos_sim",
440
- "mini_batch_size": 32,
441
  "gather_across_devices": false
442
  }
443
  ```
@@ -453,7 +453,7 @@ You can finetune this model on your own dataset.
453
  | | sentence1 | sentence2 |
454
  |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
455
  | type | string | string |
456
- | details | <ul><li>min: 6 tokens</li><li>mean: 13.69 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 35 tokens</li><li>mean: 106.26 tokens</li><li>max: 128 tokens</li></ul> |
457
  * Samples:
458
  | sentence1 | sentence2 |
459
  |:---------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -465,7 +465,7 @@ You can finetune this model on your own dataset.
465
  {
466
  "scale": 20.0,
467
  "similarity_fct": "cos_sim",
468
- "mini_batch_size": 32,
469
  "gather_across_devices": false
470
  }
471
  ```
@@ -559,7 +559,7 @@ You can finetune this model on your own dataset.
559
  | | query | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
560
  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
561
  | type | string | string | string | string | string | string | string |
562
- | details | <ul><li>min: 10 tokens</li><li>mean: 12.52 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 106.67 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 23 tokens</li><li>mean: 107.39 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 109.24 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 108.44 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 109.21 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 107.55 tokens</li><li>max: 128 tokens</li></ul> |
563
  * Samples:
564
  | query | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
565
  |:----------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -587,7 +587,7 @@ You can finetune this model on your own dataset.
587
  | | question | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
588
  |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
589
  | type | string | string | string | string | string | string | string |
590
- | details | <ul><li>min: 8 tokens</li><li>mean: 11.99 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 57.81 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 57.42 tokens</li><li>max: 125 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 56.84 tokens</li><li>max: 120 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 57.05 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 57.54 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 58.11 tokens</li><li>max: 128 tokens</li></ul> |
591
  * Samples:
592
  | question | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
593
  |:---------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -615,7 +615,7 @@ You can finetune this model on your own dataset.
615
  | | query | positive | negative |
616
  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
617
  | type | string | string | string |
618
- | details | <ul><li>min: 4 tokens</li><li>mean: 9.31 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 79.83 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 77.31 tokens</li><li>max: 128 tokens</li></ul> |
619
  * Samples:
620
  | query | positive | negative |
621
  |:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -671,7 +671,7 @@ You can finetune this model on your own dataset.
671
  | | query | positive | negative |
672
  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
673
  | type | string | string | string |
674
- | details | <ul><li>min: 5 tokens</li><li>mean: 9.87 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 44 tokens</li><li>mean: 81.57 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 79.18 tokens</li><li>max: 128 tokens</li></ul> |
675
  * Samples:
676
  | query | positive | negative |
677
  |:----------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -727,7 +727,7 @@ You can finetune this model on your own dataset.
727
  | | query | answer |
728
  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
729
  | type | string | string |
730
- | details | <ul><li>min: 10 tokens</li><li>mean: 12.47 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 106.87 tokens</li><li>max: 128 tokens</li></ul> |
731
  * Samples:
732
  | query | answer |
733
  |:----------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -881,8 +881,13 @@ You can finetune this model on your own dataset.
881
  ### Training Logs
882
  | Epoch | Step | Training Loss |
883
  |:------:|:----:|:-------------:|
884
- | 0.2626 | 500 | 4.2908 |
885
- | 0.5252 | 1000 | 2.4668 |
 
 
 
 
 
886
 
887
 
888
  ### Framework Versions
 
131
  ### Model Description
132
  - **Model Type:** Sentence Transformer
133
  - **Base model:** [jhu-clsp/ettin-encoder-17m](https://huggingface.co/jhu-clsp/ettin-encoder-17m) <!-- at revision 987607455c61e7a5bbc85f7758e0512ea6d0ae4c -->
134
+ - **Maximum Sequence Length:** 512 tokens
135
  - **Output Dimensionality:** 256 dimensions
136
  - **Similarity Function:** Cosine Similarity
137
  - **Training Datasets:**
 
166
 
167
  ```
168
  SentenceTransformer(
169
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
170
  (1): Pooling({'word_embedding_dimension': 256, '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})
171
  )
172
  ```
 
204
  # Get the similarity scores for the embeddings
205
  similarities = model.similarity(query_embeddings, document_embeddings)
206
  print(similarities)
207
+ # tensor([[ 0.6392, 0.7162, -0.1267]])
208
  ```
209
 
210
  <!--
 
257
  | | sentence1 | sentence2 |
258
  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
259
  | type | string | string |
260
+ | details | <ul><li>min: 6 tokens</li><li>mean: 66.07 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 15.66 tokens</li><li>max: 122 tokens</li></ul> |
261
  * Samples:
262
  | sentence1 | sentence2 |
263
  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------|
 
269
  {
270
  "scale": 20.0,
271
  "similarity_fct": "cos_sim",
272
+ "mini_batch_size": 48,
273
  "gather_across_devices": false
274
  }
275
  ```
 
285
  | | sentence1 | sentence2 |
286
  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
287
  | type | string | string |
288
+ | details | <ul><li>min: 3 tokens</li><li>mean: 66.24 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 34.01 tokens</li><li>max: 512 tokens</li></ul> |
289
  * Samples:
290
  | sentence1 | sentence2 |
291
  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|
 
297
  {
298
  "scale": 20.0,
299
  "similarity_fct": "cos_sim",
300
+ "mini_batch_size": 48,
301
  "gather_across_devices": false
302
  }
303
  ```
 
313
  | | sentence1 | sentence2 |
314
  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
315
  | type | string | string |
316
+ | details | <ul><li>min: 3 tokens</li><li>mean: 63.96 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 12.15 tokens</li><li>max: 20 tokens</li></ul> |
317
  * Samples:
318
  | sentence1 | sentence2 |
319
  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------|
 
325
  {
326
  "scale": 20.0,
327
  "similarity_fct": "cos_sim",
328
+ "mini_batch_size": 48,
329
  "gather_across_devices": false
330
  }
331
  ```
 
341
  | | sentence1 | sentence2 |
342
  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
343
  | type | string | string |
344
+ | details | <ul><li>min: 4 tokens</li><li>mean: 93.99 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 17.99 tokens</li><li>max: 42 tokens</li></ul> |
345
  * Samples:
346
  | sentence1 | sentence2 |
347
  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------|
 
353
  {
354
  "scale": 20.0,
355
  "similarity_fct": "cos_sim",
356
+ "mini_batch_size": 48,
357
  "gather_across_devices": false
358
  }
359
  ```
 
381
  {
382
  "scale": 20.0,
383
  "similarity_fct": "cos_sim",
384
+ "mini_batch_size": 48,
385
  "gather_across_devices": false
386
  }
387
  ```
 
409
  {
410
  "scale": 20.0,
411
  "similarity_fct": "cos_sim",
412
+ "mini_batch_size": 48,
413
  "gather_across_devices": false
414
  }
415
  ```
 
437
  {
438
  "scale": 20.0,
439
  "similarity_fct": "cos_sim",
440
+ "mini_batch_size": 48,
441
  "gather_across_devices": false
442
  }
443
  ```
 
453
  | | sentence1 | sentence2 |
454
  |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
455
  | type | string | string |
456
+ | details | <ul><li>min: 6 tokens</li><li>mean: 13.69 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 35 tokens</li><li>mean: 187.03 tokens</li><li>max: 512 tokens</li></ul> |
457
  * Samples:
458
  | sentence1 | sentence2 |
459
  |:---------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 
465
  {
466
  "scale": 20.0,
467
  "similarity_fct": "cos_sim",
468
+ "mini_batch_size": 48,
469
  "gather_across_devices": false
470
  }
471
  ```
 
559
  | | query | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
560
  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
561
  | type | string | string | string | string | string | string | string |
562
+ | details | <ul><li>min: 10 tokens</li><li>mean: 12.52 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 137.81 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 23 tokens</li><li>mean: 143.36 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 142.38 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 145.93 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 145.76 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 141.95 tokens</li><li>max: 512 tokens</li></ul> |
563
  * Samples:
564
  | query | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
565
  |:----------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 
587
  | | question | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
588
  |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
589
  | type | string | string | string | string | string | string | string |
590
+ | details | <ul><li>min: 8 tokens</li><li>mean: 11.99 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 57.82 tokens</li><li>max: 138 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 57.42 tokens</li><li>max: 125 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 56.84 tokens</li><li>max: 120 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 57.08 tokens</li><li>max: 155 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 57.54 tokens</li><li>max: 129 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 58.23 tokens</li><li>max: 195 tokens</li></ul> |
591
  * Samples:
592
  | question | answer | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 |
593
  |:---------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 
615
  | | query | positive | negative |
616
  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
617
  | type | string | string | string |
618
+ | details | <ul><li>min: 4 tokens</li><li>mean: 9.31 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 82.19 tokens</li><li>max: 216 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 78.99 tokens</li><li>max: 209 tokens</li></ul> |
619
  * Samples:
620
  | query | positive | negative |
621
  |:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 
671
  | | query | positive | negative |
672
  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
673
  | type | string | string | string |
674
+ | details | <ul><li>min: 5 tokens</li><li>mean: 9.87 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 44 tokens</li><li>mean: 85.25 tokens</li><li>max: 211 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 81.18 tokens</li><li>max: 227 tokens</li></ul> |
675
  * Samples:
676
  | query | positive | negative |
677
  |:----------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 
727
  | | query | answer |
728
  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
729
  | type | string | string |
730
+ | details | <ul><li>min: 10 tokens</li><li>mean: 12.47 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 138.28 tokens</li><li>max: 512 tokens</li></ul> |
731
  * Samples:
732
  | query | answer |
733
  |:----------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 
881
  ### Training Logs
882
  | Epoch | Step | Training Loss |
883
  |:------:|:----:|:-------------:|
884
+ | 0.2626 | 500 | 4.2889 |
885
+ | 0.5252 | 1000 | 2.4545 |
886
+ | 0.7878 | 1500 | 2.0409 |
887
+ | 1.0504 | 2000 | 1.992 |
888
+ | 1.3130 | 2500 | 1.9145 |
889
+ | 1.5756 | 3000 | 1.6902 |
890
+ | 1.8382 | 3500 | 1.745 |
891
 
892
 
893
  ### Framework Versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de0a448512e40e3a7b2560f1082de3aebc8ee85d3428d7116e94670d4fd68e7c
3
  size 67193928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76ca6d6f3afd8da3965ef03746c7041eb86d55637fdc2383401efc890dead09
3
  size 67193928
sentence_bert_config.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "max_seq_length": 128,
3
  "do_lower_case": false
4
  }
 
1
  {
2
+ "max_seq_length": 512,
3
  "do_lower_case": false
4
  }
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 128,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
tokenizer_config.json CHANGED
@@ -937,7 +937,7 @@
937
  "input_ids",
938
  "attention_mask"
939
  ],
940
- "model_max_length": 128,
941
  "pad_token": "[PAD]",
942
  "sep_token": "[SEP]",
943
  "tokenizer_class": "PreTrainedTokenizerFast",
 
937
  "input_ids",
938
  "attention_mask"
939
  ],
940
+ "model_max_length": 512,
941
  "pad_token": "[PAD]",
942
  "sep_token": "[SEP]",
943
  "tokenizer_class": "PreTrainedTokenizerFast",