diff --git "a/last-checkpoint/README.md" "b/last-checkpoint/README.md"
--- "a/last-checkpoint/README.md"
+++ "b/last-checkpoint/README.md"
@@ -7,12 +7,12 @@ tags:
 - sentence-similarity
 - feature-extraction
 - generated_from_trainer
-- dataset_size:131566
-- loss:MultipleNegativesRankingLoss
-- loss:CoSENTLoss
+- dataset_size:526885
 - loss:GISTEmbedLoss
+- loss:CoSENTLoss
 - loss:OnlineContrastiveLoss
 - loss:MultipleNegativesSymmetricRankingLoss
+- loss:MarginMSELoss
 base_model: microsoft/deberta-v3-small
 datasets:
 - sentence-transformers/all-nli
@@ -25,46 +25,137 @@ datasets:
 - allenai/sciq
 - allenai/qasc
 - allenai/openbookqa
-- sentence-transformers/msmarco-msmarco-distilbert-base-v3
 - sentence-transformers/natural-questions
 - sentence-transformers/trivia-qa
 - sentence-transformers/quora-duplicates
 - sentence-transformers/gooaq
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
 widget:
-- source_sentence: Centrosome-independent mitotic spindle formation in  vertebrates.
+- source_sentence: A man in a Santa Claus costume is sitting on a wooden chair holding
+    a microphone and a stringed instrument.
   sentences:
-  - Birds pair up with the same bird in mating season.
-  - We use voltage to keep track of electric potential energy.
-  - A mitotic spindle forms from the centrosomes.
-- source_sentence: A dog carrying a stick in its mouth runs through a snow-covered
-    field.
+  - The man is is near the ball.
+  - The man is wearing a costume.
+  - People are having a picnic.
+- source_sentence: A street vendor selling his art.
   sentences:
-  - The children played on the floor.
-  - A pair of people play video games together on a couch.
-  - A animal carried a stick through a snow covered field.
-- source_sentence: A guy on a skateboard, jumping off some steps.
+  - A man is selling things on the street.
+  - A woman is walking outside.
+  - A clown is talking into a microphone.
+- source_sentence: A boy looks surly as his father looks at the camera.
   sentences:
-  - A woman is making music.
-  - a guy with a skateboard making a jump
-  - A dog holds an object in the water.
-- source_sentence: A photographer with bushy dark hair takes a photo of a skateboarder
-    at an indoor park.
+  - a boy looks at his farther
+  - A dark-haired girl in a spotted shirt is pointing at the picture while sitting
+    next to a boy wearing a purple shirt and jeans.
+  - Man and woman stop and chat with each other.
+- source_sentence: Which company provided streetcar connections between downtown and
+    the hospital?
   sentences:
-  - The person with the camera photographs the person skating.
-  - A man starring at a piece of paper.
-  - The man is riding a bike in sand.
-- source_sentence: Why did oil start getting priced in terms of gold?
+  - In 1914 developers Billings & Meyering acquired the tract, completed street development,
+    provided the last of the necessary municipal improvements including water service,
+    and began marketing the property with fervor.
+  - The war was fought primarily along the frontiers between New France and the British
+    colonies, from Virginia in the South to Nova Scotia in the North.
+  - 'On the basis of CST, Burnet developed a theory of how an immune response is triggered
+    according to the self/nonself distinction: "self" constituents (constituents of
+    the body) do not trigger destructive immune responses, while "nonself" entities
+    (pathogens, an allograft) trigger a destructive immune response.'
+- source_sentence: What language did Tesla study while in school?
   sentences:
-  - Because oil was priced in dollars, oil producers' real income decreased.
-  - This allows all set top boxes in a household to share recordings and other media.
-  - Only the series from 2009 onwards are available on Blu-ray, except for the 1970
-    story Spearhead from Space, released in July 2013.
+  - Because of the complexity of medications including specific indications, effectiveness
+    of treatment regimens, safety of medications (i.e., drug interactions) and patient
+    compliance issues (in the hospital and at home) many pharmacists practicing in
+    hospitals gain more education and training after pharmacy school through a pharmacy
+    practice residency and sometimes followed by another residency in a specific area.
+  - Rev. Jimmy Creech was defrocked after a highly publicized church trial in 1999
+    on account of his participation in same-sex union ceremonies.
+  - Tesla was the fourth of five children.
 pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on microsoft/deberta-v3-small
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.2520910673470529
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.2588662067006675
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.30439718484055006
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.3013780326567434
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.25977707672353506
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.26078444276128726
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.08121075567918108
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.0753891417253212
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.30439718484055006
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.3013780326567434
+      name: Spearman Max
+    - type: pearson_cosine
+      value: 0.2520910673470529
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.2588662067006675
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.30439718484055006
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.3013780326567434
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.25977707672353506
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.26078444276128726
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.08121075567918108
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.0753891417253212
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.30439718484055006
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.3013780326567434
+      name: Spearman Max
 ---
 
 # SentenceTransformer based on microsoft/deberta-v3-small
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-v3-small](https://huggingface.co./microsoft/deberta-v3-small) on the [nli-pairs](https://huggingface.co./datasets/sentence-transformers/all-nli), [sts-label](https://huggingface.co./datasets/sentence-transformers/stsb), [vitaminc-pairs](https://huggingface.co./datasets/tals/vitaminc), [qnli-contrastive](https://huggingface.co./datasets/nyu-mll/glue), [scitail-pairs-qa](https://huggingface.co./datasets/allenai/scitail), [scitail-pairs-pos](https://huggingface.co./datasets/allenai/scitail), [xsum-pairs](https://huggingface.co./datasets/sentence-transformers/xsum), [compression-pairs](https://huggingface.co./datasets/sentence-transformers/sentence-compression), [sciq_pairs](https://huggingface.co./datasets/allenai/sciq), [qasc_pairs](https://huggingface.co./datasets/allenai/qasc), [openbookqa_pairs](https://huggingface.co./datasets/allenai/openbookqa), [msmarco_pairs](https://huggingface.co./datasets/sentence-transformers/msmarco-msmarco-distilbert-base-v3), [nq_pairs](https://huggingface.co./datasets/sentence-transformers/natural-questions), [trivia_pairs](https://huggingface.co./datasets/sentence-transformers/trivia-qa), [quora_pairs](https://huggingface.co./datasets/sentence-transformers/quora-duplicates) and [gooaq_pairs](https://huggingface.co./datasets/sentence-transformers/gooaq) datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-v3-small](https://huggingface.co./microsoft/deberta-v3-small) on the [nli-pairs](https://huggingface.co./datasets/sentence-transformers/all-nli), [sts-label](https://huggingface.co./datasets/sentence-transformers/stsb), [vitaminc-pairs](https://huggingface.co./datasets/tals/vitaminc), [qnli-contrastive](https://huggingface.co./datasets/nyu-mll/glue), [scitail-pairs-qa](https://huggingface.co./datasets/allenai/scitail), [scitail-pairs-pos](https://huggingface.co./datasets/allenai/scitail), [xsum-pairs](https://huggingface.co./datasets/sentence-transformers/xsum), [compression-pairs](https://huggingface.co./datasets/sentence-transformers/sentence-compression), [sciq_pairs](https://huggingface.co./datasets/allenai/sciq), [qasc_pairs](https://huggingface.co./datasets/allenai/qasc), [openbookqa_pairs](https://huggingface.co./datasets/allenai/openbookqa), msmarco_pairs, [nq_pairs](https://huggingface.co./datasets/sentence-transformers/natural-questions), [trivia_pairs](https://huggingface.co./datasets/sentence-transformers/trivia-qa), [quora_pairs](https://huggingface.co./datasets/sentence-transformers/quora-duplicates) and [gooaq_pairs](https://huggingface.co./datasets/sentence-transformers/gooaq) datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
@@ -86,7 +177,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [m
     - [sciq_pairs](https://huggingface.co./datasets/allenai/sciq)
     - [qasc_pairs](https://huggingface.co./datasets/allenai/qasc)
     - [openbookqa_pairs](https://huggingface.co./datasets/allenai/openbookqa)
-    - [msmarco_pairs](https://huggingface.co./datasets/sentence-transformers/msmarco-msmarco-distilbert-base-v3)
+    - msmarco_pairs
     - [nq_pairs](https://huggingface.co./datasets/sentence-transformers/natural-questions)
     - [trivia_pairs](https://huggingface.co./datasets/sentence-transformers/trivia-qa)
     - [quora_pairs](https://huggingface.co./datasets/sentence-transformers/quora-duplicates)
@@ -127,9 +218,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("bobox/DeBERTaV3-small-GeneralSentenceTransformer-v2-checkpoints-tmp")
 # Run inference
 sentences = [
-    'Why did oil start getting priced in terms of gold?',
-    "Because oil was priced in dollars, oil producers' real income decreased.",
-    'This allows all set top boxes in a household to share recordings and other media.',
+    'What language did Tesla study while in school?',
+    'Tesla was the fourth of five children.',
+    'Rev. Jimmy Creech was defrocked after a highly publicized church trial in 1999 on account of his participation in same-sex union ceremonies.',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -165,6 +256,44 @@ You can finetune this model on your own dataset.
 *List how the model may foreseeably be misused and address what users ought not to do with the model.*
 -->
 
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.2521     |
+| **spearman_cosine** | **0.2589** |
+| pearson_manhattan   | 0.3044     |
+| spearman_manhattan  | 0.3014     |
+| pearson_euclidean   | 0.2598     |
+| spearman_euclidean  | 0.2608     |
+| pearson_dot         | 0.0812     |
+| spearman_dot        | 0.0754     |
+| pearson_max         | 0.3044     |
+| spearman_max        | 0.3014     |
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.2521     |
+| **spearman_cosine** | **0.2589** |
+| pearson_manhattan   | 0.3044     |
+| spearman_manhattan  | 0.3014     |
+| pearson_euclidean   | 0.2598     |
+| spearman_euclidean  | 0.2608     |
+| pearson_dot         | 0.0812     |
+| spearman_dot        | 0.0754     |
+| pearson_max         | 0.3044     |
+| spearman_max        | 0.3014     |
+
 <!--
 ## Bias, Risks and Limitations
 
@@ -184,7 +313,7 @@ You can finetune this model on your own dataset.
 #### nli-pairs
 
 * Dataset: [nli-pairs](https://huggingface.co./datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co./datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
-* Size: 10,000 training samples
+* Size: 50,000 training samples
 * Columns: <code>sentence1</code> and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence1                                                                         | sentence2                                                                        |
@@ -197,12 +326,13 @@ You can finetune this model on your own dataset.
   | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   |
   | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          |
   | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 #### sts-label
@@ -232,23 +362,23 @@ You can finetune this model on your own dataset.
 #### vitaminc-pairs
 
 * Dataset: [vitaminc-pairs](https://huggingface.co./datasets/tals/vitaminc) at [be6febb](https://huggingface.co./datasets/tals/vitaminc/tree/be6febb761b0b2807687e61e0b5282e459df2fa0)
-* Size: 4,943 training samples
+* Size: 24,996 training samples
 * Columns: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | label                        | sentence1                                                                         | sentence2                                                                          |
-  |:--------|:-----------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
-  | type    | int                          | string                                                                            | string                                                                             |
-  | details | <ul><li>1: 100.00%</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.56 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 37.97 tokens</li><li>max: 184 tokens</li></ul> |
+  |         | label                        | sentence1                                                                         | sentence2                                                                         |
+  |:--------|:-----------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | int                          | string                                                                            | string                                                                            |
+  | details | <ul><li>1: 100.00%</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.65 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 36.9 tokens</li><li>max: 161 tokens</li></ul> |
 * Samples:
-  | label          | sentence1                                                                  | sentence2                                                                                                                  |
-  |:---------------|:---------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------|
-  | <code>1</code> | <code>The film scored above 85.5 % based on more than 127 reviews .</code> | <code>On Rotten Tomatoes the film has a rating of 86 % , based on 128 reviews , with an average rating of 7.2/10 .</code>  |
-  | <code>1</code> | <code>The film has more than 59 reviews .</code>                           | <code>On Rotten Tomatoes , the film has a rating of 47 % , based on 60 reviews , with an average rating of 5.4/10 .</code> |
-  | <code>1</code> | <code>More than 100 cases of COVID-19 have been reported .</code>          | <code>Tamil Nadu reported more than 190 cases in a day , all who had been to the event.</code>                             |
+  | label          | sentence1                                                                                      | sentence2                                                                                                                                                                                                                             |
+  |:---------------|:-----------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>1</code> | <code>Linkin Park sold more than 30 million singles and 130 million records worldwide .</code> | <code>Linkin Park has sold over 100 million albums and 31 million singles worldwide , making a total of over 131 million records sold worldwide with 32,000,000 albums and 33,000,000 singles sold in the US as of June 2017 .</code> |
+  | <code>1</code> | <code>Anibal Sanchez has played for the Atlanta Braves .</code>                                | <code>He has played in Major League Baseball ( MLB ) for the Florida/Miami Marlins , Detroit Tigers and Atlanta Braves .</code>                                                                                                       |
+  | <code>1</code> | <code>Frankenweenie has under 37 reviews on Metacritic , and a score above 74 .</code>         | <code>Metacritic , which assigns a weighted average score out of 100 to reviews from mainstream critics , gives the film a score of 75 based on 35 reviews .</code>                                                                   |
 * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
   {'guide': SentenceTransformer(
-    (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
     (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
     (2): Normalize()
   ), 'temperature': 0.05}
@@ -257,85 +387,87 @@ You can finetune this model on your own dataset.
 #### qnli-contrastive
 
 * Dataset: [qnli-contrastive](https://huggingface.co./datasets/nyu-mll/glue) at [bcdcba7](https://huggingface.co./datasets/nyu-mll/glue/tree/bcdcba79d07bc864c1c254ccfcedcce55bcc9a8c)
-* Size: 10,000 training samples
+* Size: 50,000 training samples
 * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence1                                                                         | sentence2                                                                          | label                        |
   |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------|
   | type    | string                                                                            | string                                                                             | int                          |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 13.69 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 35.17 tokens</li><li>max: 499 tokens</li></ul> | <ul><li>0: 100.00%</li></ul> |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 13.54 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 35.96 tokens</li><li>max: 136 tokens</li></ul> | <ul><li>0: 100.00%</li></ul> |
 * Samples:
-  | sentence1                                                                                                            | sentence2                                                                                                                                                                                               | label          |
-  |:---------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
-  | <code>What year was the Southampton Docks company created?</code>                                                    | <code>The Southampton Docks company had been formed in 1835.</code>                                                                                                                                     | <code>0</code> |
-  | <code>what happens to the reflected wave which allows the antenna to reach its asympotic feedpoint impedance?</code> | <code>Thus the antenna's impedance, given by the ratio of feedpoint voltage to current, is altered due to the antenna's proximity to the ground.</code>                                                 | <code>0</code> |
-  | <code>West 132nd Street is interrupted by St. Nicholas Park and which college?</code>                                | <code>The main portion of 132nd Street runs eastbound from Frederick Douglass Boulevard to northern end of Park Avenue where there is a southbound exit from/entrance to the Harlem River Drive.</code> | <code>0</code> |
+  | sentence1                                                 | sentence2                                                                                                                                                                                                                                                      | label          |
+  |:----------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>By what means did the British govern Tuvalu?</code> | <code>The Ellice Islands were administered as British protectorate by a Resident Commissioner from 1892 to 1916 as part of the British Western Pacific Territories (BWPT), and then as part of the Gilbert and Ellice Islands colony from 1916 to 1974.</code> | <code>0</code> |
+  | <code>Who is the current head of BBC Television?</code>   | <code>As a division within the BBC, Television was formerly known as BBC Vision for a few years in the early 21st century, until its name reverted to Television in 2013.</code>                                                                               | <code>0</code> |
+  | <code>What was the PLDA formerly known as?</code>         | <code>The Professional Lighting Designers Association (PLDA), formerly known as ELDA is an organisation focusing on the promotion of the profession of Architectural Lighting Design.</code>                                                                   | <code>0</code> |
 * Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
 
 #### scitail-pairs-qa
 
 * Dataset: [scitail-pairs-qa](https://huggingface.co./datasets/allenai/scitail) at [0cc4353](https://huggingface.co./datasets/allenai/scitail/tree/0cc4353235b289165dfde1c7c5d1be983f99ce44)
-* Size: 6,595 training samples
+* Size: 14,987 training samples
 * Columns: <code>sentence2</code> and <code>sentence1</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence2                                                                         | sentence1                                                                         |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 7 tokens</li><li>mean: 16.18 tokens</li><li>max: 41 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 15.15 tokens</li><li>max: 41 tokens</li></ul> |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 15.63 tokens</li><li>max: 41 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.73 tokens</li><li>max: 41 tokens</li></ul> |
 * Samples:
-  | sentence2                                                                                                                 | sentence1                                                                                                                             |
-  |:--------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Nearly five million people die yearly due to air pollution.</code>                                                  | <code>Nearly how many millions of people die yearly due to air pollution?</code>                                                      |
-  | <code>Exercising every day is an example of a good health habit.</code>                                                   | <code>Which activity is an example of a good health habit?</code>                                                                     |
-  | <code>A(n) fungus causes ergot, a disease that impacts crops directly and has more devastating effects on animals.</code> | <code>A type of what organism causes ergot, a disease that impacts crops directly and has more devastating effects on animals?</code> |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  | sentence2                                                                                                 | sentence1                                                                                                      |
+  |:----------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------|
+  | <code>People stopped adding lead to gasoline because of environmental pollution.</code>                   | <code>Why did people stop adding lead to gasoline?</code>                                                      |
+  | <code>The pleura that surrounds the lungs consists of two layers.</code>                                  | <code>The pleura that surrounds the lungs consists of how many layers?</code>                                  |
+  | <code>Thermal energy constitutes the total kinetic energy of all the atoms that make up an object.</code> | <code>What kind of energy constitutes the total kinetic energy of all the atoms that make up an object?</code> |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 #### scitail-pairs-pos
 
 * Dataset: [scitail-pairs-pos](https://huggingface.co./datasets/allenai/scitail) at [0cc4353](https://huggingface.co./datasets/allenai/scitail/tree/0cc4353235b289165dfde1c7c5d1be983f99ce44)
-* Size: 3,405 training samples
+* Size: 8,600 training samples
 * Columns: <code>sentence1</code> and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                         | sentence2                                                                        |
-  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                           |
-  | details | <ul><li>min: 8 tokens</li><li>mean: 23.97 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 15.1 tokens</li><li>max: 39 tokens</li></ul> |
+  |         | sentence1                                                                         | sentence2                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 24.02 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 15.66 tokens</li><li>max: 39 tokens</li></ul> |
 * Samples:
-  | sentence1                                                                                                                              | sentence2                                                                                                |
-  |:---------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------|
-  | <code>Tornadoes Tornadoes are most common during the period of spring and early summer, but can occur in any month of the year.</code> | <code>Tornadoes can occur in any.</code>                                                                 |
-  | <code>A watershed is the land area that drains water into a river system or other body of water.</code>                                | <code>All of the land drained by a river system is called its basin, or the "wet" term  watershed</code> |
-  | <code>Humans have 23 pairs of chromosomes (one set from each parent).</code>                                                           | <code>Humans have 23 pairs pairs of chromosomes.</code>                                                  |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  | sentence1                                                                                                                                                                                                                                                                     | sentence2                                                                  |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------|
+  | <code>TELEPHONE (818) 354-5011 PHOTO CAPTION P-23254 C & BW S-1-62 Dec. 4, 1980 Voyager 1 looked back at Saturn on Nov. 16, 1980, four days after the spacecraft flew past the planet, to observe the appearance of Saturn and its rings from this unique perspective.</code> | <code>The voyager 1 spacecraft visited saturn in 1980.</code>              |
+  | <code>atoms may share one pair of electrons (single bonds), two pairs (double bonds), or three pairs (triple bonds).</code>                                                                                                                                                   | <code>In a carbon triple bond, three pairs of electrons are shared.</code> |
+  | <code>One gram of protein contains four calories.</code>                                                                                                                                                                                                                      | <code>One gram of proteins provides four calories of energy.</code>        |
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 #### xsum-pairs
 
 * Dataset: [xsum-pairs](https://huggingface.co./datasets/sentence-transformers/xsum) at [788ddaf](https://huggingface.co./datasets/sentence-transformers/xsum/tree/788ddafe04e539956d56b567bc32a036ee7b9206)
-* Size: 10,000 training samples
+* Size: 50,000 training samples
 * Columns: <code>sentence1</code> and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                           | sentence2                                                                          |
-  |:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
-  | type    | string                                                                              | string                                                                             |
-  | details | <ul><li>min: 10 tokens</li><li>mean: 355.4 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 27.07 tokens</li><li>max: 70 tokens</li></ul> |
+  |         | sentence1                                                                           | sentence2                                                                        |
+  |:--------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                           |
+  | details | <ul><li>min: 2 tokens</li><li>mean: 351.25 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 26.7 tokens</li><li>max: 59 tokens</li></ul> |
 * Samples:
-  | sentence1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | sentence2                                                                                                                                              |
-  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>Former Royal Marine Stephen Gough, 55, was found guilty by a jury at Winchester Crown Court of breaching an anti-social behaviour order (Asbo).<br>The order bans him from taking off his clothes in public.<br>He had refused to put on clothes as he left Winchester Prison after being imprisoned for a previous Asbo breach.<br>Judge Jane Miller QC suggested moves should be made to find Gough a closed nudist community to live in to prevent the cycle of imprisonment which has seen him jailed for much of the past eight years.<br>Gough earned his nickname when he completed a naked trek from Land's End to John O'Groats in 2003.<br>A BBC documentary team followed his journey.<br>He had previously argued there was nothing intimidating about him appearing "in his natural human state".</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | <code>A man known as the "naked rambler" has been jailed for two-and-a-half years after walking out of prison wearing only his boots and socks.</code> |
-  | <code>Colbert, 49, is host of Comedy Central's acclaimed late-night satire programme The Colbert Report.<br>Letterman, 66, said last week he was retiring after 21 years hosting the CBS show and 11 years on NBC's Late Night.<br>On his show, Colbert plays a satirical version of himself to mock right-wing pundits. He has suggested he will retire the character for the new show.<br>"Stephen Colbert is one of the most inventive and respected forces on television," CBS president Leslie Moonves wrote in a statement following the announcement.<br>"David Letterman's legacy and accomplishments are an incredible source of pride for all of us here, and today's announcement speaks to our commitment of upholding what he established for CBS in late night."<br>On his popular and influential Emmy-winning Comedy Central programme, Colbert's biting brand of satire has drawn critical acclaim as well as provoking ire, often from the Republicans and conservatives he skewers.<br>Recently he was attacked on social media for a joke some viewed as disparaging toward Asian Americans but which he meant as a satirical jab at the owner of the Washington Redskins American football team.<br>Of his hiring to the Late Show top spot, Colbert said, "simply being a guest on David Letterman's show has been a highlight of my career."<br>"I never dreamed that I would follow in his footsteps, though everyone in late night follows Dave's lead."</code> | <code>Stephen Colbert will succeed Late Show host David Letterman upon his retirement next year, CBS has said.</code>                                  |
-  | <code>The pair are both through to the last eight of the Welsh Open at Cardiff, with White beating defending champion John Higgins 4-1.<br>"Michael White is an amazing player. He has absolutely everything," O'Sullivan, 40, told BBC Wales.<br>"Wales is going to have another world champion... maybe a multiple world champion."<br>O'Sullivan added: "John Higgins behind Stephen Hendry is the best player I have seen and he has lost to Michael.<br>"He [White] is fearless, he plays everybody like they are the same. He doesn't care who is sat in that seat against him and that is a gift.<br>"Michael is now a top player. He's definitely knocking on the doo. If he won the world title this year I wouldn't be surprised."<br>Englishman O'Sullivan had little trouble beating China's Yu Delu 4-1 after losing the opening frame.<br>White, 24, described the victory over four-time world champion Higgins as a career highlight.<br>"It is a fantastic win, [it] would have to be up there with the best of my career," White said.<br>"I am feeling very relaxed and laid back and it showed in my performance.<br>"To get that win in my home event makes it more special. It is good for Wales and the tournament.<br>"Who knows, maybe a Welsh player could get to the final."</code>                                                                                                                                                                           | <code>Welshman Michael White can become a world champion, according to five-time winner Ronnie O'Sullivan.</code>                                      |
+  | sentence1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | sentence2                                                                                                                                             |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Bivsi Rana, 15, was born in Germany to Nepalese parents. In May she was deported with the rest of her family.<br>Her classmates protested and lobbied on her behalf against the deportation, drawing hundreds of people to rally under the slogan "Bring Bivsi back".<br>Officials called it a "unique case" and said Bivsi was "de facto German".<br>Mayor of Duisburg Sören Link said: "The fact that we have managed to resolve this difficult situation lifts a burden from my shoulders."<br>Bivsi's parents moved to Germany in 1998, fleeing civil conflict in their native Nepal, but their applications for asylum were denied. Their repeated appeals were rejected. Fearing political repercussions at home Bivsi's father, Mr Rana, initially applied for asylum under a false name and has since called this "the worst mistake" of his life.<br>But Bivsi herself was born and brought up in Germany.<br>On the last Monday in May, Bivsi was in class at school in Duisburg, in north west Germany, when she was told she had to pack her things and leave. That same day she and her family were deported to Nepal, a country Bivsi had never visited before.<br>Class teacher Sascha Thamm told German media afterwards that all the girls in the class cried and Bivsi's best friend broke down to the extent that an emergency doctor had to be called.<br>Mr Thamm said Bivsi was a kind, engaged student who was good at German and science and helped teach swimming lessons.<br>Bivsi has been living in Nepal with her family and, according to reports, has been unable to find a new school there due to language issues.<br>She has now been given a study visa enabling her to return Germany while she finishes her education. Her parents can return with her.<br>North-Rhine Westphalia state's integration minister Joachim Stamp said: "This is a unique case and generalisations cannot be drawn from it.<br>"The right of the child stood in the foreground in this decision.<br>"Bivsi was born in Germany and grew up here - she is de facto a German child."<br>Bivsi is reported to be "totally happy" with the decision, and her parents are reported to be "overjoyed".</code>                                                                                                                                                                                                                                     | <code>A teenager who was removed from her classroom and deported to Nepal has been allowed to return to Germany on a study visa.</code>               |
+  | <code>It was bought by an individual from the Dorset area in a phone bid.<br>A piece of paper found with the hair said "A single hair of Napoleon Bonaparte's head 29th August 1816" and "5th May 1821' - the date Napoleon died.<br>The strand of hair was attached to a piece of paper by red sealing wax.<br>Auctioneer Max Beaumont, of Cottees Auction House, Wareham, said it was found in a drawer by a colleague doing a home valuation.<br>He said they found a small goldsmith's box and expected to find a watch, but instead they found the folded paper.<br>The hair is understood to have been owned by the family for the whole of the 20th Century, but has not been professionally analysed.<br>The initial estimate was £100 to £200.<br>Mr Beaumont, who at 19 claims to be one of the youngest auctioneers in the country, said: "There has been a lot of interest."<br>Napoleon Bonaparte was a French emperor who conquered much of Europe. He was defeated in the Battle of Waterloo and  imprisoned by the British on the remote Atlantic island of St Helena, where he died on 5 May 1821.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | <code>A strand of hair believed to be from the head of former French emperor Napoleon Bonaparte's head has sold for £130 at auction in Dorset.</code> |
+  | <code>Local Government Association figures show that councils will have spent £505m by 2017 on fighting obesity.<br>Councils use the money to measure children's weight at primary school, help people lose weight and offer free or cheaper leisure facilities.<br>Public health became the responsibility of local authorities in April 2013.<br>Before that, it was run by the NHS.<br>The Department of Health said it was committed to tackling obesity and the government had announced a sugar tax on soft drinks manufacturers earlier in the year.<br>The Local Government Association (LGA) receives money from the government to spend on public health, and this sum will fall from £3.38bn in 2016/17 to £3.13bn in 2020/21.<br>The association, which represents more than 370 councils - mostly in England and a few in Wales - said it was set to spend about half a billion pounds on obesity prevention in adults and children over four years.<br>This was made up as follows:<br>The LGA said the figures illustrated the amount of prevention work councils were carrying out and showed the scale of the obesity crisis.<br>The costs include running the government's National Child Measurement Programme, which involves calculating a child's BMI (body mass index) when they start primary school and again when they leave school in Year Six.<br>Recent figures showed that in 2014/15 in England, one in 10 children aged four and five was obese and one in five children aged 10 to 11 was obese.<br>The LGA said the overall cost of obesity was forecast to rise further.<br>It has previously called on the government to reduce sugar content in fizzy drinks, make sugar labelling clearer and provide more tap water in schools and restaurants.<br>Councils also want to have powers to ban junk food advertising near schools.<br>Izzi Seccombe, who is in charge of community wellbeing for the LGA, said councils were best placed to tackle obesity before it became a problem, but they needed more support.<br>"We would like assurances from the government's new administration that the long-awaited childhood obesity strategy is still on track and that it includes tough measures that will help to reverse the rise in costs and children becoming obese.<br>"Today's obese children will be tomorrow's obese adults, and with this comes a range of costly and debilitating major health conditions."</code> | <code>Local councils in England are warning that government cuts to public health funding could hamper their efforts to tackle obesity.</code>        |
 * Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters:
   ```json
   {
@@ -347,7 +479,7 @@ You can finetune this model on your own dataset.
 #### compression-pairs
 
 * Dataset: [compression-pairs](https://huggingface.co./datasets/sentence-transformers/sentence-compression) at [605bc91](https://huggingface.co./datasets/sentence-transformers/sentence-compression/tree/605bc91d95631895ba25b6eda51a3cb596976c90)
-* Size: 10,000 training samples
+* Size: 50,000 training samples
 * Columns: <code>sentence1</code> and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence1                                                                           | sentence2                                                                         |
@@ -371,7 +503,7 @@ You can finetune this model on your own dataset.
 #### sciq_pairs
 
 * Dataset: [sciq_pairs](https://huggingface.co./datasets/allenai/sciq) at [2c94ad3](https://huggingface.co./datasets/allenai/sciq/tree/2c94ad3e1aafab77146f384e23536f97a4849815)
-* Size: 10,000 training samples
+* Size: 11,679 training samples
 * Columns: <code>sentence1</code> and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence1                                                                         | sentence2                                                                          |
@@ -384,12 +516,13 @@ You can finetune this model on your own dataset.
   | <code>What type of organism is commonly used in preparation of foods such as cheese and yogurt?</code>                                                                                      | <code>Mesophiles grow best in moderate temperature, typically between 25°C and 40°C (77°F and 104°F). Mesophiles are often found living in or on the bodies of humans or other animals. The optimal growth temperature of many pathogenic mesophiles is 37°C (98°F), the normal human body temperature. Mesophilic organisms have important uses in food preparation, including cheese, yogurt, beer and wine.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
   | <code>What phenomenon makes global winds blow northeast to southwest or the reverse in the northern hemisphere and northwest to southeast or the reverse in the southern hemisphere?</code> | <code>Without Coriolis Effect the global winds would blow north to south or south to north. But Coriolis makes them blow northeast to southwest or the reverse in the Northern Hemisphere. The winds blow northwest to southeast or the reverse in the southern hemisphere.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
   | <code>Changes from a less-ordered state to a more-ordered state (such as a liquid to a solid) are always what?</code>                                                                       | <code>Summary Changes of state are examples of phase changes, or phase transitions. All phase changes are accompanied by changes in the energy of a system. Changes from a more-ordered state to a less-ordered state (such as a liquid to a gas) areendothermic. Changes from a less-ordered state to a more-ordered state (such as a liquid to a solid) are always exothermic. The conversion of a solid to a liquid is called fusion (or melting). The energy required to melt 1 mol of a substance is its enthalpy of fusion (ΔHfus). The energy change required to vaporize 1 mol of a substance is the enthalpy of vaporization (ΔHvap). The direct conversion of a solid to a gas is sublimation. The amount of energy needed to sublime 1 mol of a substance is its enthalpy of sublimation (ΔHsub) and is the sum of the enthalpies of fusion and vaporization. Plots of the temperature of a substance versus heat added or versus heating time at a constant rate of heating are calledheating curves. Heating curves relate temperature changes to phase transitions. A superheated liquid, a liquid at a temperature and pressure at which it should be a gas, is not stable. A cooling curve is not exactly the reverse of the heating curve because many liquids do not freeze at the expected temperature. Instead, they form a supercooled liquid, a metastable liquid phase that exists below the normal melting point. Supercooled liquids usually crystallize on standing, or adding a seed crystal of the same or another substance can induce crystallization.</code> |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 #### qasc_pairs
@@ -411,7 +544,7 @@ You can finetune this model on your own dataset.
 * Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
   {'guide': SentenceTransformer(
-    (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
     (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
     (2): Normalize()
   ), 'temperature': 0.05}
@@ -433,42 +566,37 @@ You can finetune this model on your own dataset.
   | <code>The sun is responsible for</code>          | <code>the sun is the source of energy for physical cycles on Earth</code> |
   | <code>When food is reduced in the stomach</code> | <code>digestion is when stomach acid breaks down food</code>              |
   | <code>Stars are</code>                           | <code>a star is made of gases</code>                                      |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 #### msmarco_pairs
 
-* Dataset: [msmarco_pairs](https://huggingface.co./datasets/sentence-transformers/msmarco-msmarco-distilbert-base-v3) at [28ff31e](https://huggingface.co./datasets/sentence-transformers/msmarco-msmarco-distilbert-base-v3/tree/28ff31e4c97cddd53d298497f766e653f1e666f9)
-* Size: 10,000 training samples
-* Columns: <code>sentence1</code> and <code>sentence2</code>
+* Dataset: msmarco_pairs
+* Size: 50,000 training samples
+* Columns: <code>query</code>, <code>positive</code>, <code>negative</code>, and <code>label</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                        | sentence2                                                                           |
-  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
-  | type    | string                                                                           | string                                                                              |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 8.61 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 75.09 tokens</li><li>max: 206 tokens</li></ul> |
+  |         | query                                                                            | positive                                                                            | negative                                                                            | label                                                           |
+  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                              | string                                                                              | float                                                           |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.61 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 75.09 tokens</li><li>max: 206 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 72.59 tokens</li><li>max: 216 tokens</li></ul> | <ul><li>min: -0.5</li><li>mean: 0.04</li><li>max: 0.6</li></ul> |
 * Samples:
-  | sentence1                                                                           | sentence2                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-  |:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-  | <code>what are the liberal arts?</code>                                             | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-  | <code>what is the mechanism of action of fibrinolytic or thrombolytic drugs?</code> | <code>Baillière's Clinical Haematology. 6 Mechanism of action of the thrombolytic agents. 6 Mechanism of action of the thrombolytic agents JEFFREY I. WEITZ Fibrin formed during the haemostatic, inflammatory or tissue repair process serves a temporary role, and must be degraded to restore normal tissue function and structure.</code>                                                                                                                                                                                                                                                                                                                                           |
-  | <code>what is normal plat count</code>                                              | <code>78 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).The average platelet count is 237,000 per mcL in men and 266,000 per mcL in women.8 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).</code> |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
-  ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
-  ```
+  | query                                                                               | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | negative                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | label                              |
+  |:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------|
+  | <code>what are the liberal arts?</code>                                             | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                        | <code>The New York State Education Department requires 60 Liberal Arts credits in a Bachelor of Science program and 90 Liberal Arts credits in a Bachelor of Arts program. In the list of course descriptions, courses which are liberal arts for all students are identified by (Liberal Arts) after the course number.</code>                                                                                                                                                                                                                                                                                                         | <code>0.12154221534729004</code>   |
+  | <code>what is the mechanism of action of fibrinolytic or thrombolytic drugs?</code> | <code>Baillière's Clinical Haematology. 6 Mechanism of action of the thrombolytic agents. 6 Mechanism of action of the thrombolytic agents JEFFREY I. WEITZ Fibrin formed during the haemostatic, inflammatory or tissue repair process serves a temporary role, and must be degraded to restore normal tissue function and structure.</code>                                                                                                                                                                                                                                                                                                                                           | <code>Fibrinolytic drug. Fibrinolytic drug, also called thrombolytic drug, any agent that is capable of stimulating the dissolution of a blood clot (thrombus). Fibrinolytic drugs work by activating the so-called fibrinolytic pathway.</code>                                                                                                                                                                                                                                                                                                                                                                                        | <code>-0.05174225568771362</code>  |
+  | <code>what is normal plat count</code>                                              | <code>78 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).The average platelet count is 237,000 per mcL in men and 266,000 per mcL in women.8 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).</code> | <code>Your blood test results should be written in your maternity notes. Your platelet count will look something like Plat. 160x10.9/L, which means you have a platelet count of 160, which is in the normal range.If your platelet count is low, the blood test should be done again.This will keep track of whether or not your count is dropping.our platelet count will look something like Plat. 160x10.9/L, which means you have a platelet count of 160, which is in the normal range. If your platelet count is low, the blood test should be done again. This will keep track of whether or not your count is dropping.</code> | <code>-0.037523627281188965</code> |
+* Loss: [<code>MarginMSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#marginmseloss)
 
 #### nq_pairs
 
 * Dataset: [nq_pairs](https://huggingface.co./datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co./datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
-* Size: 10,000 training samples
+* Size: 50,000 training samples
 * Columns: <code>sentence1</code> and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence1                                                                          | sentence2                                                                            |
@@ -481,18 +609,19 @@ You can finetune this model on your own dataset.
   | <code>when did richmond last play in a preliminary final</code> | <code>Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tigers took over the game as it progressed and scored seven straight goals at one point. They eventually would win by 48 points – 16.12 (108) to Adelaide's 8.12 (60) – to end their 37-year flag drought.[22] Dustin Martin also became the first player to win a Premiership medal, the Brownlow Medal and the Norm Smith Medal in the same season, while Damien Hardwick was named AFL Coaches Association Coach of the Year. Richmond's jump from 13th to premiers also marked the biggest jump from one AFL season to the next.</code> |
   | <code>who sang what in the world's come over you</code>         | <code>Jack Scott (singer) At the beginning of 1960, Scott again changed record labels, this time to Top Rank Records.[1] He then recorded four Billboard Hot 100 hits – "What in the World's Come Over You" (#5), "Burning Bridges" (#3) b/w "Oh Little One" (#34), and "It Only Happened Yesterday" (#38).[1] "What in the World's Come Over You" was Scott's second gold disc winner.[6] Scott continued to record and perform during the 1960s and 1970s.[1] His song "You're Just Gettin' Better" reached the country charts in 1974.[1] In May 1977, Scott recorded a Peel session for BBC Radio 1 disc jockey, John Peel.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
   | <code>who produces the most wool in the world</code>            | <code>Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 #### trivia_pairs
 
 * Dataset: [trivia_pairs](https://huggingface.co./datasets/sentence-transformers/trivia-qa) at [a7c36e3](https://huggingface.co./datasets/sentence-transformers/trivia-qa/tree/a7c36e3c8c8c01526bc094d79bf80d4c848b0ad0)
-* Size: 10,000 training samples
+* Size: 50,000 training samples
 * Columns: <code>sentence1</code> and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence1                                                                         | sentence2                                                                            |
@@ -505,18 +634,19 @@ You can finetune this model on your own dataset.
   | <code>Which American-born Sinclair won the Nobel Prize for Literature in 1930?</code>     | <code>The Nobel Prize in Literature 1930 The Nobel Prize in Literature 1930 Sinclair Lewis The Nobel Prize in Literature 1930 Sinclair Lewis Prize share: 1/1 The Nobel Prize in Literature 1930 was awarded to Sinclair Lewis "for his vigorous and graphic art of description and his ability to create, with wit and humour, new types of characters". Photos: Copyright © The Nobel Foundation Share this: To cite this page MLA style: "The Nobel Prize in Literature 1930". Nobelprize.org. Nobel Media AB 2014. Web. 18 Jan 2017. <http://www.nobelprize.org/nobel_prizes/literature/laureates/1930/></code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
   | <code>Where in England was Dame Judi Dench born?</code>                                   | <code>Judi Dench - IMDb IMDb Actress | Music Department | Soundtrack Judi Dench was born in York, England, to Eleanora Olive (Jones), who was from Dublin, Ireland, and Reginald Arthur Dench, a doctor from Dorset, England. She attended Mount School in York, and studied at the Central School of Speech and Drama. She has performed with Royal Shakespeare Company, the National Theatre, and at Old Vic Theatre. She is a ... See full bio » Born: a list of 35 people created 02 Jul 2011 a list of 35 people created 19 Apr 2012 a list of 35 people created 28 May 2014 a list of 25 people created 05 Aug 2014 a list of 26 people created 18 May 2015 Do you have a demo reel? Add it to your IMDbPage How much of Judi Dench's work have you seen? User Polls Won     1     Oscar. Another    59 wins & 163 nominations. See more awards  » Known For  2016 The Hollow Crown (TV Series) Cecily, Duchess of York  2015 The Vote (TV Movie) Christine Metcalfe - Total War (1996) ... Narrator (voice) - Stalemate (1996) ... Narrator (voice)  1992 The Torch (TV Mini-Series) Aba  1990 Screen One (TV Series) Anne  1989 Behaving Badly (TV Mini-Series) Bridget  1981 BBC2 Playhouse (TV Series) Sister Scarli  1976 Arena (TV Series documentary) Sweetie Simpkins  1973 Ooh La La! (TV Series) Amélie  1966 Court Martial (TV Series) Marthe  1963 Z Cars (TV Series) Elena Collins  1963 Love Story (TV Series) Pat McKendrick  1960 The Terrible Choice (TV Series) Good Angel Music department (1 credit)   A Fine Romance (TV Series) (theme sung by - 14 episodes, 1981 - 1983) (theme song sung by - 12 episodes, 1983 - 1984) - A Romantic Meal (1984) ... (theme song sung by) - Problems (1984) ... (theme song sung by)  2013 Fifty Years on Stage (TV Movie) (performer: "Send in the Clowns")  2009 Nine (performer: "Folies Bergère") - What's Wrong with Mrs Bale? (1997) ... (performer: "Raindrops Keep Fallin' On My Head" - uncredited) - Misunderstandings (1993) ... (performer: "Walkin' My Baby Back Home" - uncredited)  1982-1984 A Fine Romance (TV Series) (performer - 2 episodes) - The Telephone Call (1984) ... (performer: "Boogie Woogie Bugle Boy" - uncredited) - Furniture (1982) ... (performer: "Rule, Britannia!" - uncredited) Hide   2009 Waiting in Rhyme (Video short) (special thanks)  2007 Expresso (Short) (special thanks)  1999 Shakespeare in Love and on Film (TV Movie documentary) (thanks - as Dame Judi Dench) Hide   2016 Rio Olympics (TV Mini-Series) Herself  2015 In Conversation (TV Series documentary) Herself  2015 Entertainment Tonight (TV Series) Herself  2015 CBS This Morning (TV Series) Herself - Guest  2015 The Insider (TV Series) Herself  1999-2014 Cinema 3 (TV Series) Herself  2013 Good Day L.A. (TV Series) Herself - Guest  2013 Arena (TV Series documentary) Herself  2013 At the Movies (TV Series) Herself  2013 Shooting Bond (Video documentary) Herself  2013 Bond's Greatest Moments (TV Movie documentary) Herself  2012 Made in Hollywood (TV Series) Herself  1999-2012 Charlie Rose (TV Series) Herself - Guest  2008-2012 This Morning (TV Series) Herself - Guest  2012 The Secrets of Skyfall (TV Short documentary) Herself  2012 Anderson Live (TV Series) Herself  2012 J. Edgar: A Complicated Man (Video documentary short) Herself  2011 The Many Faces of... (TV Series documentary) Herself / Various Characters  2011 Na plovárne (TV Series) Herself  2010 BBC Proms (TV Series) Herself  2010 The South Bank Show Revisited (TV Series documentary) Herself - Episode #6.68 (2009) ... Herself - Guest (as Dame Judi Dench)  2007-2009 Breakfast (TV Series)  2009 Larry King Live (TV Series) Herself - Guest  2009 The One Show (TV Series) Herself  2009 Cranford in Detail (Video documentary short) Herself / Miss Matty Jenkins (as Dame Judi Dench)  2005-2008 The South Bank Show (TV Series documentary) Herself  2008 Tavis Smiley (TV Series) Herself - Guest  2007 ITV News (TV Series) Herself - BAFTA Nominee  2007 The Making of Cranford (Video documentary short) Herself / Miss Matty Jenkyns (as Dame Judi Dench)  2006 Becoming Bond (TV Movie documentary) Herself  2006 Corazón de... (TV Series) Hers</code> |
   | <code>In which decade did Billboard magazine first publish and American hit chart?</code> | <code>The US Billboard song chart The US Billboard song chart Search this site with Google Song chart US Billboard The Billboard magazine has published various music charts starting (with sheet music) in 1894, the first "Music Hit Parade" was published in 1936 , the first "Music Popularity Chart" was calculated in 1940 . These charts became less irregular until the weekly "Hot 100" was started in 1958 . The current chart combines sales, airplay and downloads. A music collector that calls himself Bullfrog has been consolidating the complete chart from 1894 to the present day.  he has published this information in a comprehenive spreadsheet (which can be obtained at bullfrogspond.com/ ). The Bullfrog data assigns each song a unique identifier, something like "1968_076" (which just happens to be the Bee Gees song "I've Gotta Get A Message To You"). This "Whitburn Number" is provided to match with the books of Joel Whitburn and consists of the year and a ranking within the year. A song that first entered the charts in December and has a long run is listed the following year. This numbering scheme means that songs which are still in the charts cannot be assigned a final id, because their ranking might change. So the definitive listing for a year cannot be final until about April. In our listing we only use songs with finalised IDs, this means that every year we have to wait until last year's entries are finalised before using them. (Source bullfrogspond.com/ , the original version used here was 20090808 with extra data from: the 2009 data from 20091219 the 2010 data from 20110305 the 2011 data from 20120929 the 2012 data from 20130330 the 2013 data from 20150328 The 20150328 data was the last one produced before the Billboard company forced the data to be withdrawn. As far as we know there are no more recent data sets available. This pattern of obtaining the data for a particular year in the middle of the following one comes from the way that the Bullfrog project generates the identifier for a song (what they call the "Prefix" in the spreadsheet). Recent entries are identified with keys like "2015-008" while older ones have keys like "2013_177". In the second case the underscore is significant, it indicates that this was the 177th biggest song released in 2013. Now, of course, during the year no one knows where a particular song will rank, so the underscore names can't be assigned until every song from a particular year has dropped out of the charts, so recent records are temporarily assigned a name with a dash. In about May of the following year the rankings are calculated and the final identifiers are assigned. That is why we at the Turret can only grab this data retrospectively. Attributes The original spreadsheet has a number of attributes, we have limited our attention to just a few of them: 134 9 The songs with the most entries on the chart were White Christmas (with 33 versions and a total of 110 weeks) and Stardust (with 19 and a total of 106 weeks). position The peak position that songs reached in the charts should show an smooth curve from number one down to the lowest position. This chart has more songs in the lower peak positions than one would expect. Before 1991 the profile of peak positions was exactly as you would expect, that year Billboard introduced the concept of "Recurrent" tracks, that is they removed any track from the chart which had spent more than twenty weeks in the chart and had fallen to the lower positions. weeks The effect of the "Recurrent" process, by which tracks are removed if they have spent at least twenty weeks in the chart and have fallen to the lower reaches, can clearly be seen in the strange spike in this attribute. This "adjustment" was intended to promote newer songs and ensure the chart does not become "stale". In fact since it was introduced in 1991 the length of long chart runs has increased, this might reflect the more conscious efforts of record companies to "game" the charts by controlling release times and promotions, or it coul</code>                                            |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 #### quora_pairs
 
 * Dataset: [quora_pairs](https://huggingface.co./datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co./datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
-* Size: 10,000 training samples
+* Size: 50,000 training samples
 * Columns: <code>sentence1</code> and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence1                                                                         | sentence2                                                                         |
@@ -540,7 +670,7 @@ You can finetune this model on your own dataset.
 #### gooaq_pairs
 
 * Dataset: [gooaq_pairs](https://huggingface.co./datasets/sentence-transformers/gooaq) at [b089f72](https://huggingface.co./datasets/sentence-transformers/gooaq/tree/b089f728748a068b7bc5234e5bcf5b25e3c8279c)
-* Size: 10,000 training samples
+* Size: 50,000 training samples
 * Columns: <code>sentence1</code> and <code>sentence2</code>
 * Approximate statistics based on the first 1000 samples:
   |         | sentence1                                                                        | sentence2                                                                           |
@@ -553,12 +683,13 @@ You can finetune this model on your own dataset.
   | <code>is toprol xl the same as metoprolol?</code>  | <code>Metoprolol succinate is also known by the brand name Toprol XL. It is the extended-release form of metoprolol. Metoprolol succinate is approved to treat high blood pressure, chronic chest pain, and congestive heart failure.</code>                                                                                                    |
   | <code>are you experienced cd steve hoffman?</code> | <code>The Are You Experienced album was apparently mastered from the original stereo UK master tapes (according to Steve Hoffman - one of the very few who has heard both the master tapes and the CDs produced over the years). ... The CD booklets were a little sparse, but at least they stayed true to the album's original design.</code> |
   | <code>how are babushka dolls made?</code>          | <code>Matryoshka dolls are made of wood from lime, balsa, alder, aspen, and birch trees; lime is probably the most common wood type. ... After cutting, the trees are stripped of most of their bark, although a few inner rings of bark are left to bind the wood and keep it from splitting.</code>                                           |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 ### Evaluation Datasets
@@ -579,12 +710,13 @@ You can finetune this model on your own dataset.
   | <code>Two women are embracing while holding to go packages.</code>                                                                                                             | <code>Two woman are holding packages.</code>                |
   | <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>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>            |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 #### scitail-pairs-pos
@@ -603,12 +735,13 @@ You can finetune this model on your own dataset.
   | <code>An introduction to atoms and elements, compounds, atomic structure and bonding, the molecule and chemical reactions.</code> | <code>Replace another in a molecule happens to atoms during a substitution reaction.</code>        | <code>0</code> |
   | <code>Wavelength The distance between two consecutive points on a sinusoidal wave that are in phase;</code>                       | <code>Wavelength is the distance between two corresponding points of adjacent waves called.</code> | <code>1</code> |
   | <code>humans normally have 23 pairs of chromosomes.</code>                                                                        | <code>Humans typically have 23 pairs pairs of chromosomes.</code>                                  | <code>1</code> |
-* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
   ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "cos_sim"
-  }
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+    (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+    (2): Normalize()
+  ), 'temperature': 0.05}
   ```
 
 #### qnli-contrastive
@@ -633,13 +766,13 @@ You can finetune this model on your own dataset.
 #### Non-Default Hyperparameters
 
 - `eval_strategy`: steps
-- `per_device_train_batch_size`: 28
+- `per_device_train_batch_size`: 30
 - `per_device_eval_batch_size`: 16
-- `learning_rate`: 2e-05
-- `weight_decay`: 1e-10
+- `learning_rate`: 1e-05
+- `weight_decay`: 5e-06
 - `num_train_epochs`: 2
 - `lr_scheduler_type`: cosine
-- `warmup_ratio`: 0.33
+- `warmup_ratio`: 0.5
 - `save_safetensors`: False
 - `fp16`: True
 - `push_to_hub`: True
@@ -654,14 +787,14 @@ You can finetune this model on your own dataset.
 - `do_predict`: False
 - `eval_strategy`: steps
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 28
+- `per_device_train_batch_size`: 30
 - `per_device_eval_batch_size`: 16
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
-- `learning_rate`: 2e-05
-- `weight_decay`: 1e-10
+- `learning_rate`: 1e-05
+- `weight_decay`: 5e-06
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
@@ -670,7 +803,7 @@ You can finetune this model on your own dataset.
 - `max_steps`: -1
 - `lr_scheduler_type`: cosine
 - `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.33
+- `warmup_ratio`: 0.5
 - `warmup_steps`: 0
 - `log_level`: passive
 - `log_level_replica`: warning
@@ -762,29 +895,19 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch | Step | Training Loss | nli-pairs loss | qnli-contrastive loss | scitail-pairs-pos loss |
-|:-----:|:----:|:-------------:|:--------------:|:---------------------:|:----------------------:|
-| None  | 0    | -             | 2.9404         | 4.1500                | 2.3949                 |
-| 0.1   | 471  | 3.3296        | 1.8879         | 2.2598                | 1.3439                 |
-| 0.2   | 942  | 1.8704        | 0.9546         | 1.8402                | 0.5629                 |
-| 0.3   | 1413 | 1.2621        | 0.7152         | 1.3887                | 0.4553                 |
-| 0.4   | 1884 | 1.2512        | 0.5274         | 0.8418                | 0.3621                 |
-| 0.5   | 2355 | 1.1724        | 0.4927         | 0.1424                | 0.3924                 |
-| 0.6   | 2826 | 0.9036        | 0.4621         | 0.3409                | 0.3777                 |
-| 0.7   | 3297 | 1.0374        | 0.4111         | 0.2125                | 0.3417                 |
-| 0.8   | 3768 | 0.9259        | 0.3853         | 0.1646                | 0.2819                 |
-| 0.9   | 4239 | 0.8709        | 0.3749         | 0.1157                | 0.2912                 |
-| 1.0   | 4710 | 0.8686        | 0.3636         | 0.0961                | 0.3109                 |
-| 1.1   | 5181 | 0.726         | 0.3744         | 0.0453                | 0.3424                 |
-| 1.2   | 5652 | 0.8151        | 0.3502         | 0.1835                | 0.2602                 |
-| 1.3   | 6123 | 0.7127        | 0.3362         | 0.1089                | 0.2460                 |
-| 1.4   | 6594 | 0.8408        | 0.3184         | 0.0701                | 0.2784                 |
-| 1.5   | 7065 | 0.7845        | 0.3191         | 0.0318                | 0.2822                 |
-| 1.6   | 7536 | 0.5766        | 0.3056         | 0.0566                | 0.2774                 |
-| 1.7   | 8007 | 0.7304        | 0.2991         | 0.0542                | 0.2736                 |
-| 1.8   | 8478 | 0.6639        | 0.2949         | 0.0515                | 0.2694                 |
-| 1.9   | 8949 | 0.6153        | 0.2938         | 0.0589                | 0.2718                 |
-| 2.0   | 9420 | 0.6665        | 0.2937         | 0.0569                | 0.2724                 |
+| Epoch | Step  | Training Loss | scitail-pairs-pos loss | nli-pairs loss | qnli-contrastive loss | sts-test_spearman_cosine |
+|:-----:|:-----:|:-------------:|:----------------------:|:--------------:|:---------------------:|:------------------------:|
+| 0     | 0     | -             | 3.4975                 | 4.3370         | 4.4702                | 0.2589                   |
+| 0.1   | 1757  | 3.8346        | 2.3231                 | 2.8535         | 3.0973                | -                        |
+| 0.2   | 3514  | 1.8532        | 0.9755                 | 1.3508         | 2.0603                | -                        |
+| 0.3   | 5271  | 1.2185        | 0.7407                 | 0.9381         | 1.2534                | -                        |
+| 0.4   | 7028  | 0.9584        | 0.6616                 | 0.7495         | 0.5140                | -                        |
+| 0.5   | 8785  | 0.8157        | 0.6057                 | 0.6550         | 0.3295                | -                        |
+| 0.6   | 10542 | 0.6698        | 0.5821                 | 0.5809         | 0.2423                | -                        |
+| 0.7   | 12299 | 0.6497        | 0.5040                 | 0.5178         | 0.2409                | -                        |
+| 0.8   | 14056 | 0.5737        | 0.4942                 | 0.5019         | 0.1500                | -                        |
+| 0.9   | 15813 | 0.5896        | 0.4757                 | 0.4804         | 0.1465                | -                        |
+| 1.0   | 17570 | 0.5174        | 0.5253                 | 0.4587         | 0.0534                | -                        |
 
 
 ### Framework Versions
@@ -813,15 +936,15 @@ You can finetune this model on your own dataset.
 }
 ```
 
-#### MultipleNegativesRankingLoss
+#### GISTEmbedLoss
 ```bibtex
-@misc{henderson2017efficient,
-    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
-    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},
-    year={2017},
-    eprint={1705.00652},
+@misc{solatorio2024gistembed,
+    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning}, 
+    author={Aivin V. Solatorio},
+    year={2024},
+    eprint={2402.16829},
     archivePrefix={arXiv},
-    primaryClass={cs.CL}
+    primaryClass={cs.LG}
 }
 ```
 
@@ -836,15 +959,15 @@ You can finetune this model on your own dataset.
 }
 ```
 
-#### GISTEmbedLoss
+#### MarginMSELoss
 ```bibtex
-@misc{solatorio2024gistembed,
-    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning}, 
-    author={Aivin V. Solatorio},
-    year={2024},
-    eprint={2402.16829},
+@misc{hofstätter2021improving,
+    title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation}, 
+    author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury},
+    year={2021},
+    eprint={2010.02666},
     archivePrefix={arXiv},
-    primaryClass={cs.LG}
+    primaryClass={cs.IR}
 }
 ```