Add new SentenceTransformer model.

README.md

@@ -27,52 +27,51 @@ tags:
 - sentence-similarity
 - feature-extraction
 - generated_from_trainer
-- dataset_size:3051
+- dataset_size:4275
 - loss:MatryoshkaLoss
 - loss:MultipleNegativesRankingLoss
 widget:
-- source_sentence: In the fiscal year of 2022, revenue in Productivity and Business
-    Processes was $53.5 billion, increasing 15%. The increase was driven by higher
-    revenue from LinkedIn, Office 366 commercial and Dynamics 365.
+- source_sentence: The fundamental elements of Goldman Sachs’ robust risk culture
+    include governance, risk identification, measurement, mitigation, culture and
+    conduct, and infrastructure. They believe these elements work together to complement
+    and reinforce each other to produce a comprehensive view of risk management.
   sentences:
-  - Who is the CEO of Berkshire Hathaway and how long have they been in the position?
-  - How does Microsoft's Office segment contribute to its overall revenue?
-  - What is the primary revenue stream for McDonald's?
-- source_sentence: According to the Cisco Systems, Inc. financial reports, the company
-    had cash and cash equivalents worth $30.1 billion at the end of fiscal year 2023.
+  - What are the financial highlights for Bank of America Corp. in its latest fiscal
+    year report?
+  - What is Berkshire Hathaway's involvement in the energy sector?
+  - What is Goldman Sach’s approach towards maintaining a robust risk culture?
+- source_sentence: HealthTech Inc.'s new drug for diabetes treatment, launched in
+    2021, contributed to approximately 30% of its total revenues for that year.
   sentences:
-  - How much cash and cash equivalents did Cisco Systems, Inc. hold at the end of
-    fiscal year 2023?
-  - In 2023, how much capital expenditure was done by Microsoft in the Information
-    Technology services sector?
-  - In 2023, how has the acquisition of ABC Corp affected the financial performance
-    of Microsoft corporation?
-- source_sentence: As of December 31, 2023, Bank of America had total loans and leases
-    in its consumer real estate portfolio amounting to approximately $262 billion.
+  - What is IBM's debt to equity ratio as of 2022?
+  - In what way does HealthTech Inc's new drug contribute to its revenue generation?
+  - What is the revenue breakdown of Alphabet for the year 2021?
+- source_sentence: The driving factor behind Tesla’s 2023 growth was the surge in
+    demand for electric vehicles.
   sentences:
-  - How many total loans were there in Bank of America's consumer real estate portfolio
-    as of December 31, 2023?
-  - How did Johnson & Johnson’s pharmaceutical segment perform in the fiscal year
-    2023?
-  - What is the source of most of Amazon's revenue in 2023?
-- source_sentence: The ongoing trade war between US and China has negatively impacted
-    the performance of Microsoft stock, with a decline of around 7.5% observed in
-    the last quarter.
+  - Why did McDonald's observe a decrease in overall revenue in 2023 relative to 2022?
+  - What key strategy did Walmart employ to boost its sales in 2016?
+  - What was the driving factor behind Tesla's growth in 2023?
+- source_sentence: Pfizer is committed to ensuring that people around the world have
+    access to its medical products. In line with this commitment, Pfizer has implemented
+    programs such as donation drives, price reduction initiatives, and patient assistance
+    programs to aid those in need. Furthermore, through partnerships with NGOs and
+    governments, Pfizer strives to strengthen healthcare systems in underprivileged
+    regions.
   sentences:
-  - What was the profit margin for Amazon in 2025?
-  - What was the growth rate in the consumer sector for Amazon in 2023?
-  - How has the ongoing trade war between US and China affected the performance of
-    the Microsoft stock in the past quarter?
-- source_sentence: For the fiscal year ending June 30, 2023, Procter & Gamble Company
-    reported a dividend payout ratio of 60%.
+  - What is the strategy of Pfizer to improve access to medicines in underprivileged
+    areas?
+  - What percentage of growth in revenue did Adobe Systems report in June 2020?
+  - How is Citigroup differentiating itself among other banks?
+- source_sentence: JP Morgan reported total deposits of $2.6 trillion in the year
+    ending December 31, 2023.
   sentences:
-  - What was the impact of the housing market on Wells Fargo's mortgage banking income
-    in 2023?
-  - What was the dividend payout ratio of Procter & Gamble Company for the fiscal
-    year ended 2023?
-  - What prompted Tesla's stock to surge in 2020?
+  - In the fiscal year 2023, what impact did the acquisition of T-Mobile bring to
+    the revenue of AT&T?
+  - What is the primary source of revenue for the software company, Microsoft?
+  - What were JP Morgan's total deposits in 2023?
 model-index:
-- name: gte-large-en-v1.5-financial-embeddings-matryoshka
+- name: gte-large-en-v1.5-financial-rag-matryoshka
   results:
   - task:
       type: information-retrieval
@@ -82,49 +81,49 @@ model-index:
       type: dim_1024
     metrics:
     - type: cosine_accuracy@1
-      value: 0.8436578171091446
+      value: 0.88
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.967551622418879
+      value: 0.96
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.9793510324483776
+      value: 0.9866666666666667
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9941002949852508
+      value: 0.9955555555555555
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.8436578171091446
+      value: 0.88
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.32251720747295964
+      value: 0.32
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19587020648967549
+      value: 0.19733333333333336
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09941002949852507
+      value: 0.09955555555555556
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.8436578171091446
+      value: 0.88
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.967551622418879
+      value: 0.96
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.9793510324483776
+      value: 0.9866666666666667
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9941002949852508
+      value: 0.9955555555555555
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.9266864251220158
+      value: 0.9426916896167131
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.9042480217258979
+      value: 0.9251851851851851
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.9045732618741468
+      value: 0.925362962962963
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -134,49 +133,49 @@ model-index:
       type: dim_768
     metrics:
     - type: cosine_accuracy@1
-      value: 0.8466076696165191
+      value: 0.88
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.9646017699115044
+      value: 0.96
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.9793510324483776
+      value: 0.9866666666666667
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9941002949852508
+      value: 0.9911111111111112
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.8466076696165191
+      value: 0.88
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.3215339233038348
+      value: 0.32
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19587020648967549
+      value: 0.19733333333333336
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09941002949852507
+      value: 0.09911111111111114
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.8466076696165191
+      value: 0.88
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.9646017699115044
+      value: 0.96
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.9793510324483776
+      value: 0.9866666666666667
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9941002949852508
+      value: 0.9911111111111112
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.9264205608498619
+      value: 0.940825047039427
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.9039893243433065
+      value: 0.924
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.9043029964425071
+      value: 0.9245274971941638
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -186,49 +185,49 @@ model-index:
       type: dim_512
     metrics:
     - type: cosine_accuracy@1
-      value: 0.8495575221238938
+      value: 0.8711111111111111
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.967551622418879
+      value: 0.96
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.9823008849557522
+      value: 0.9866666666666667
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9941002949852508
+      value: 0.9911111111111112
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.8495575221238938
+      value: 0.8711111111111111
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.3225172074729597
+      value: 0.32
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19646017699115043
+      value: 0.19733333333333336
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09941002949852507
+      value: 0.09911111111111114
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.8495575221238938
+      value: 0.8711111111111111
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.967551622418879
+      value: 0.96
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.9823008849557522
+      value: 0.9866666666666667
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9941002949852508
+      value: 0.9911111111111112
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.9284195153657646
+      value: 0.938126332642602
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.9066207800721073
+      value: 0.9202962962962962
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.9069134241700614
+      value: 0.9207248677248678
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -238,49 +237,49 @@ model-index:
       type: dim_256
     metrics:
     - type: cosine_accuracy@1
-      value: 0.8495575221238938
+      value: 0.8755555555555555
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.9646017699115044
+      value: 0.96
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.9823008849557522
+      value: 0.9866666666666667
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9911504424778761
+      value: 0.9911111111111112
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.8495575221238938
+      value: 0.8755555555555555
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.3215339233038348
+      value: 0.32
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19646017699115043
+      value: 0.19733333333333336
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.0991150442477876
+      value: 0.09911111111111114
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.8495575221238938
+      value: 0.8755555555555555
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.9646017699115044
+      value: 0.96
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.9823008849557522
+      value: 0.9866666666666667
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9911504424778761
+      value: 0.9911111111111112
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.9279790172476607
+      value: 0.9395718726230007
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.906915765322845
+      value: 0.9222962962962963
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.907374745870321
+      value: 0.9227724867724867
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -290,49 +289,49 @@ model-index:
       type: dim_128
     metrics:
     - type: cosine_accuracy@1
-      value: 0.8348082595870207
+      value: 0.8666666666666667
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.9616519174041298
+      value: 0.9555555555555556
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.976401179941003
+      value: 0.9866666666666667
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9852507374631269
+      value: 0.9911111111111112
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.8348082595870207
+      value: 0.8666666666666667
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.3205506391347099
+      value: 0.3185185185185185
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19528023598820055
+      value: 0.19733333333333336
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09852507374631266
+      value: 0.09911111111111114
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.8348082595870207
+      value: 0.8666666666666667
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.9616519174041298
+      value: 0.9555555555555556
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.976401179941003
+      value: 0.9866666666666667
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9852507374631269
+      value: 0.9911111111111112
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.9195345068147046
+      value: 0.9346269584282435
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.8974551669241934
+      value: 0.9157037037037037
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.898503034985336
+      value: 0.9160403095943067
       name: Cosine Map@100
   - task:
       type: information-retrieval
@@ -342,53 +341,53 @@ model-index:
       type: dim_64
     metrics:
     - type: cosine_accuracy@1
-      value: 0.8259587020648967
+      value: 0.8311111111111111
       name: Cosine Accuracy@1
     - type: cosine_accuracy@3
-      value: 0.9587020648967551
+      value: 0.96
       name: Cosine Accuracy@3
     - type: cosine_accuracy@5
-      value: 0.976401179941003
+      value: 0.9733333333333334
       name: Cosine Accuracy@5
     - type: cosine_accuracy@10
-      value: 0.9852507374631269
+      value: 0.9911111111111112
       name: Cosine Accuracy@10
     - type: cosine_precision@1
-      value: 0.8259587020648967
+      value: 0.8311111111111111
       name: Cosine Precision@1
     - type: cosine_precision@3
-      value: 0.319567354965585
+      value: 0.32
       name: Cosine Precision@3
     - type: cosine_precision@5
-      value: 0.19528023598820055
+      value: 0.19466666666666665
       name: Cosine Precision@5
     - type: cosine_precision@10
-      value: 0.09852507374631266
+      value: 0.09911111111111114
       name: Cosine Precision@10
     - type: cosine_recall@1
-      value: 0.8259587020648967
+      value: 0.8311111111111111
       name: Cosine Recall@1
     - type: cosine_recall@3
-      value: 0.9587020648967551
+      value: 0.96
       name: Cosine Recall@3
     - type: cosine_recall@5
-      value: 0.976401179941003
+      value: 0.9733333333333334
       name: Cosine Recall@5
     - type: cosine_recall@10
-      value: 0.9852507374631269
+      value: 0.9911111111111112
       name: Cosine Recall@10
     - type: cosine_ndcg@10
-      value: 0.9154633119580834
+      value: 0.9208110890988729
       name: Cosine Ndcg@10
     - type: cosine_mrr@10
-      value: 0.8919897457508078
+      value: 0.8971957671957672
       name: Cosine Mrr@10
     - type: cosine_map@100
-      value: 0.8929899218270423
+      value: 0.8975242479721762
       name: Cosine Map@100
 ---
 
-# gte-large-en-v1.5-financial-embeddings-matryoshka
+# gte-large-en-v1.5-financial-rag-matryoshka
 
 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
@@ -437,9 +436,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("rbhatia46/gte-large-en-v1.5-financial-rag-matryoshka")
 # Run inference
 sentences = [
-    'For the fiscal year ending June 30, 2023, Procter & Gamble Company reported a dividend payout ratio of 60%.',
-    'What was the dividend payout ratio of Procter & Gamble Company for the fiscal year ended 2023?',
-    "What prompted Tesla's stock to surge in 2020?",
+    'JP Morgan reported total deposits of $2.6 trillion in the year ending December 31, 2023.',
+    "What were JP Morgan's total deposits in 2023?",
+    'What is the primary source of revenue for the software company, Microsoft?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -485,21 +484,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.8437     |
-| cosine_accuracy@3   | 0.9676     |
-| cosine_accuracy@5   | 0.9794     |
-| cosine_accuracy@10  | 0.9941     |
-| cosine_precision@1  | 0.8437     |
-| cosine_precision@3  | 0.3225     |
-| cosine_precision@5  | 0.1959     |
-| cosine_precision@10 | 0.0994     |
-| cosine_recall@1     | 0.8437     |
-| cosine_recall@3     | 0.9676     |
-| cosine_recall@5     | 0.9794     |
-| cosine_recall@10    | 0.9941     |
-| cosine_ndcg@10      | 0.9267     |
-| cosine_mrr@10       | 0.9042     |
-| **cosine_map@100**  | **0.9046** |
+| cosine_accuracy@1   | 0.88       |
+| cosine_accuracy@3   | 0.96       |
+| cosine_accuracy@5   | 0.9867     |
+| cosine_accuracy@10  | 0.9956     |
+| cosine_precision@1  | 0.88       |
+| cosine_precision@3  | 0.32       |
+| cosine_precision@5  | 0.1973     |
+| cosine_precision@10 | 0.0996     |
+| cosine_recall@1     | 0.88       |
+| cosine_recall@3     | 0.96       |
+| cosine_recall@5     | 0.9867     |
+| cosine_recall@10    | 0.9956     |
+| cosine_ndcg@10      | 0.9427     |
+| cosine_mrr@10       | 0.9252     |
+| **cosine_map@100**  | **0.9254** |
 
 #### Information Retrieval
 * Dataset: `dim_768`
@@ -507,21 +506,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.8466     |
-| cosine_accuracy@3   | 0.9646     |
-| cosine_accuracy@5   | 0.9794     |
-| cosine_accuracy@10  | 0.9941     |
-| cosine_precision@1  | 0.8466     |
-| cosine_precision@3  | 0.3215     |
-| cosine_precision@5  | 0.1959     |
-| cosine_precision@10 | 0.0994     |
-| cosine_recall@1     | 0.8466     |
-| cosine_recall@3     | 0.9646     |
-| cosine_recall@5     | 0.9794     |
-| cosine_recall@10    | 0.9941     |
-| cosine_ndcg@10      | 0.9264     |
-| cosine_mrr@10       | 0.904      |
-| **cosine_map@100**  | **0.9043** |
+| cosine_accuracy@1   | 0.88       |
+| cosine_accuracy@3   | 0.96       |
+| cosine_accuracy@5   | 0.9867     |
+| cosine_accuracy@10  | 0.9911     |
+| cosine_precision@1  | 0.88       |
+| cosine_precision@3  | 0.32       |
+| cosine_precision@5  | 0.1973     |
+| cosine_precision@10 | 0.0991     |
+| cosine_recall@1     | 0.88       |
+| cosine_recall@3     | 0.96       |
+| cosine_recall@5     | 0.9867     |
+| cosine_recall@10    | 0.9911     |
+| cosine_ndcg@10      | 0.9408     |
+| cosine_mrr@10       | 0.924      |
+| **cosine_map@100**  | **0.9245** |
 
 #### Information Retrieval
 * Dataset: `dim_512`
@@ -529,21 +528,21 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.8496     |
-| cosine_accuracy@3   | 0.9676     |
-| cosine_accuracy@5   | 0.9823     |
-| cosine_accuracy@10  | 0.9941     |
-| cosine_precision@1  | 0.8496     |
-| cosine_precision@3  | 0.3225     |
-| cosine_precision@5  | 0.1965     |
-| cosine_precision@10 | 0.0994     |
-| cosine_recall@1     | 0.8496     |
-| cosine_recall@3     | 0.9676     |
-| cosine_recall@5     | 0.9823     |
-| cosine_recall@10    | 0.9941     |
-| cosine_ndcg@10      | 0.9284     |
-| cosine_mrr@10       | 0.9066     |
-| **cosine_map@100**  | **0.9069** |
+| cosine_accuracy@1   | 0.8711     |
+| cosine_accuracy@3   | 0.96       |
+| cosine_accuracy@5   | 0.9867     |
+| cosine_accuracy@10  | 0.9911     |
+| cosine_precision@1  | 0.8711     |
+| cosine_precision@3  | 0.32       |
+| cosine_precision@5  | 0.1973     |
+| cosine_precision@10 | 0.0991     |
+| cosine_recall@1     | 0.8711     |
+| cosine_recall@3     | 0.96       |
+| cosine_recall@5     | 0.9867     |
+| cosine_recall@10    | 0.9911     |
+| cosine_ndcg@10      | 0.9381     |
+| cosine_mrr@10       | 0.9203     |
+| **cosine_map@100**  | **0.9207** |
 
 #### Information Retrieval
 * Dataset: `dim_256`
@@ -551,65 +550,65 @@ You can finetune this model on your own dataset.
 
 | Metric              | Value      |
 |:--------------------|:-----------|
-| cosine_accuracy@1   | 0.8496     |
-| cosine_accuracy@3   | 0.9646     |
-| cosine_accuracy@5   | 0.9823     |
-| cosine_accuracy@10  | 0.9912     |
-| cosine_precision@1  | 0.8496     |
-| cosine_precision@3  | 0.3215     |
-| cosine_precision@5  | 0.1965     |
+| cosine_accuracy@1   | 0.8756     |
+| cosine_accuracy@3   | 0.96       |
+| cosine_accuracy@5   | 0.9867     |
+| cosine_accuracy@10  | 0.9911     |
+| cosine_precision@1  | 0.8756     |
+| cosine_precision@3  | 0.32       |
+| cosine_precision@5  | 0.1973     |
 | cosine_precision@10 | 0.0991     |
-| cosine_recall@1     | 0.8496     |
-| cosine_recall@3     | 0.9646     |
-| cosine_recall@5     | 0.9823     |
-| cosine_recall@10    | 0.9912     |
-| cosine_ndcg@10      | 0.928      |
-| cosine_mrr@10       | 0.9069     |
-| **cosine_map@100**  | **0.9074** |
+| cosine_recall@1     | 0.8756     |
+| cosine_recall@3     | 0.96       |
+| cosine_recall@5     | 0.9867     |
+| cosine_recall@10    | 0.9911     |
+| cosine_ndcg@10      | 0.9396     |
+| cosine_mrr@10       | 0.9223     |
+| **cosine_map@100**  | **0.9228** |
 
 #### Information Retrieval
 * Dataset: `dim_128`
 * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
 
-| Metric              | Value      |
-|:--------------------|:-----------|
-| cosine_accuracy@1   | 0.8348     |
-| cosine_accuracy@3   | 0.9617     |
-| cosine_accuracy@5   | 0.9764     |
-| cosine_accuracy@10  | 0.9853     |
-| cosine_precision@1  | 0.8348     |
-| cosine_precision@3  | 0.3206     |
-| cosine_precision@5  | 0.1953     |
-| cosine_precision@10 | 0.0985     |
-| cosine_recall@1     | 0.8348     |
-| cosine_recall@3     | 0.9617     |
-| cosine_recall@5     | 0.9764     |
-| cosine_recall@10    | 0.9853     |
-| cosine_ndcg@10      | 0.9195     |
-| cosine_mrr@10       | 0.8975     |
-| **cosine_map@100**  | **0.8985** |
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.8667    |
+| cosine_accuracy@3   | 0.9556    |
+| cosine_accuracy@5   | 0.9867    |
+| cosine_accuracy@10  | 0.9911    |
+| cosine_precision@1  | 0.8667    |
+| cosine_precision@3  | 0.3185    |
+| cosine_precision@5  | 0.1973    |
+| cosine_precision@10 | 0.0991    |
+| cosine_recall@1     | 0.8667    |
+| cosine_recall@3     | 0.9556    |
+| cosine_recall@5     | 0.9867    |
+| cosine_recall@10    | 0.9911    |
+| cosine_ndcg@10      | 0.9346    |
+| cosine_mrr@10       | 0.9157    |
+| **cosine_map@100**  | **0.916** |
 
 #### Information Retrieval
 * Dataset: `dim_64`
 * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
 
-| Metric              | Value     |
-|:--------------------|:----------|
-| cosine_accuracy@1   | 0.826     |
-| cosine_accuracy@3   | 0.9587    |
-| cosine_accuracy@5   | 0.9764    |
-| cosine_accuracy@10  | 0.9853    |
-| cosine_precision@1  | 0.826     |
-| cosine_precision@3  | 0.3196    |
-| cosine_precision@5  | 0.1953    |
-| cosine_precision@10 | 0.0985    |
-| cosine_recall@1     | 0.826     |
-| cosine_recall@3     | 0.9587    |
-| cosine_recall@5     | 0.9764    |
-| cosine_recall@10    | 0.9853    |
-| cosine_ndcg@10      | 0.9155    |
-| cosine_mrr@10       | 0.892     |
-| **cosine_map@100**  | **0.893** |
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.8311     |
+| cosine_accuracy@3   | 0.96       |
+| cosine_accuracy@5   | 0.9733     |
+| cosine_accuracy@10  | 0.9911     |
+| cosine_precision@1  | 0.8311     |
+| cosine_precision@3  | 0.32       |
+| cosine_precision@5  | 0.1947     |
+| cosine_precision@10 | 0.0991     |
+| cosine_recall@1     | 0.8311     |
+| cosine_recall@3     | 0.96       |
+| cosine_recall@5     | 0.9733     |
+| cosine_recall@10    | 0.9911     |
+| cosine_ndcg@10      | 0.9208     |
+| cosine_mrr@10       | 0.8972     |
+| **cosine_map@100**  | **0.8975** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -630,19 +629,19 @@ You can finetune this model on your own dataset.
 #### Unnamed Dataset
 
 
-* Size: 3,051 training samples
+* Size: 4,275 training samples
 * Columns: <code>positive</code> and <code>anchor</code>
 * Approximate statistics based on the first 1000 samples:
   |         | positive                                                                            | anchor                                                                            |
   |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                              | string                                                                            |
-  | details | <ul><li>min: 15 tokens</li><li>mean: 44.56 tokens</li><li>max: 116 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 18.23 tokens</li><li>max: 32 tokens</li></ul> |
+  | details | <ul><li>min: 15 tokens</li><li>mean: 44.74 tokens</li><li>max: 114 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 18.12 tokens</li><li>max: 32 tokens</li></ul> |
 * Samples:
-  | positive                                                                                                                                                                                                                                                                                                     | anchor                                                                            |
-  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | <code>Amazon had a strong Q1 in 2021, with net sales increasing 44% to $108.5 billion in the first quarter, compared with $75.5 billion in first quarter 2020. Operating income increased to $8.9 billion in the first quarter, compared with operating income of $4.0 billion in first quarter 2020.</code> | <code>What were the key findings of Amazon's Q1 financial report for 2021?</code> |
-  | <code>Apple Inc. reported total revenue of $102.4 billion for the second quarter of fiscal 2023, up 22% from the same quarter in the previous year. This has been attributed to increased sales of iPhones, iPads, and other hardware products as well as the expansion of their services business.</code>   | <code>What was the revenue of Apple Inc. in 2023?</code>                          |
-  | <code>JPMorgan Chase & Co. was formed through the merger of Chase Manhattan Corporation and J.P. Morgan & Co. The origins of the company can be traced back to the founding of The Manhattan Company by Aaron Burr in 1799.</code>                                                                           | <code>Who founded JPMorgan Chase & Co.?</code>                                    |
+  | positive                                                                                                                                                                                                                                                                         | anchor                                                                                         |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|
+  | <code>At the end of fiscal year 2023, Exxon Mobil reported a debt-to-equity ratio of 0.32, implying that the company used more equity than debt in its capital structure.</code>                                                                                                 | <code>What was the debt-to-equity ratio for Exxon Mobil at the end of fiscal year 2023?</code> |
+  | <code>Amazon Web Services (AWS) generated $12.7 billion in net sales in the fourth quarter of 2020, up 28% from the same period of the previous year. It accounted for about 10% of Amazon’s total net sales for the quarter.</code>                                             | <code>How did Amazon's AWS segment perform in the fourth quarter of 2020?</code>               |
+  | <code>JPMorgan Chase generates revenues by providing a wide range of banking and financial services. These include investment banking (M&As, advisory), consumer and community banking (home mortgages, auto loans), commercial banking, and asset and wealth management.</code> | <code>What are the key revenue sources for JPMorgan Chase?</code>                              |
 * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
   ```json
   {
@@ -675,7 +674,7 @@ You can finetune this model on your own dataset.
 - `per_device_eval_batch_size`: 16
 - `gradient_accumulation_steps`: 16
 - `learning_rate`: 2e-05
-- `num_train_epochs`: 4
+- `num_train_epochs`: 10
 - `lr_scheduler_type`: cosine
 - `warmup_ratio`: 0.1
 - `bf16`: True
@@ -703,7 +702,7 @@ You can finetune this model on your own dataset.
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
-- `num_train_epochs`: 4
+- `num_train_epochs`: 10
 - `max_steps`: -1
 - `lr_scheduler_type`: cosine
 - `lr_scheduler_kwargs`: {}
@@ -801,12 +800,22 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch   | Step   | Training Loss | dim_1024_cosine_map@100 | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
 |:-------:|:------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
-| 1.0     | 6      | -             | 0.9015                  | 0.8932                 | 0.9017                 | 0.8958                 | 0.8925                | 0.8935                 |
-| 1.6667  | 10     | 0.3905        | -                       | -                      | -                      | -                      | -                     | -                      |
-| **2.0** | **12** | **-**         | **0.9038**              | **0.901**              | **0.9018**             | **0.909**              | **0.8903**            | **0.9039**             |
-| 3.0     | 18     | -             | 0.9046                  | 0.8982                 | 0.9065                 | 0.9055                 | 0.8916                | 0.9033                 |
-| 3.3333  | 20     | 0.0493        | -                       | -                      | -                      | -                      | -                     | -                      |
-| 4.0     | 24     | -             | 0.9046                  | 0.8985                 | 0.9074                 | 0.9069                 | 0.8930                | 0.9043                 |
+| 0.9552  | 8      | -             | 0.9090                  | 0.8848                 | 0.8992                 | 0.9052                 | 0.8775                | 0.9030                 |
+| 1.1940  | 10     | 0.4749        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 1.9104  | 16     | -             | 0.9170                  | 0.9095                 | 0.9109                 | 0.9201                 | 0.8961                | 0.9212                 |
+| 2.3881  | 20     | 0.0862        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 2.9851  | 25     | -             | 0.9190                  | 0.9071                 | 0.9160                 | 0.9278                 | 0.8998                | 0.9234                 |
+| 3.5821  | 30     | 0.0315        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 3.9403  | 33     | -             | 0.9183                  | 0.9053                 | 0.9122                 | 0.9287                 | 0.8998                | 0.9183                 |
+| 4.7761  | 40     | 0.0184        | -                       | -                      | -                      | -                      | -                     | -                      |
+| 4.8955  | 41     | -             | 0.9225                  | 0.9125                 | 0.9164                 | 0.9260                 | 0.8985                | 0.9220                 |
+| 5.9701  | 50     | 0.0135        | 0.9268                  | 0.9132                 | 0.9208                 | 0.9257                 | 0.8961                | 0.9271                 |
+| 6.9254  | 58     | -             | 0.9254                  | 0.9158                 | 0.9202                 | 0.9212                 | 0.8938                | 0.9213                 |
+| 7.1642  | 60     | 0.0123        | -                       | -                      | -                      | -                      | -                     | -                      |
+| **8.0** | **67** | **-**         | **0.9253**              | **0.916**              | **0.9228**             | **0.9207**             | **0.8972**            | **0.9243**             |
+| 8.3582  | 70     | 0.01          | -                       | -                      | -                      | -                      | -                     | -                      |
+| 8.9552  | 75     | -             | 0.9254                  | 0.9160                 | 0.9213                 | 0.9207                 | 0.9005                | 0.9245                 |
+| 9.5522  | 80     | 0.0088        | 0.9254                  | 0.9160                 | 0.9228                 | 0.9207                 | 0.8975                | 0.9245                 |
 
 * The bold row denotes the saved checkpoint.
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb5caa2f1c0b65eeed7770c657480d99fa8fd2b48d11771885b26587b5adfa42
+oid sha256:c8ea20cd7be4fdac5063bfc2b9a9b8d2cb4437a36c5697f43a0f9a2f6326bfc1
 size 1736585680