Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "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
+}

README.md

@@ -0,0 +1,851 @@
+---
+base_model: Snowflake/snowflake-arctic-embed-m
+language:
+- en
+library_name: sentence-transformers
+license: apache-2.0
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:1K<n<10K
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: kim był Steve Yzerman?
+  sentences:
+  - Łazik marsjański Opportunity
+  - w jakim kraju jest przyznawany Order Białego Lotosu?
+  - do powstania jakich instytucji przyczynił się pierwszy biskup Makau?
+- source_sentence: gdzie rośnie bokkonia?
+  sentences:
+  - jak rozmnażają się Aeolosomatidae?
+  - kto 1 stycznia 2011 został gubernatorem Nowego Jorku?
+  - w której świątyni koronowany był król jerozolimski Baldwin I?
+- source_sentence: Godło Republiki Ałtaju
+  sentences:
+  - co przedstawia godło Republiki Ałtaju?
+  - w którym kraju w noc sylwestrową je się oliebollen?
+  - który z członków załogi Międzynarodowej Stacji Kosmicznej nie ma nóg?
+- source_sentence: co to jest meszne?
+  sentences:
+  - co to jest Mammoth Hot Springs?
+  - jak przebiegała kariera sportowa Witolda Sikorskiego?
+  - do uratowania ilu dzieł sztuki przyczynił się Borys Woźnicki?
+- source_sentence: Chłopiec z Nariokotome
+  sentences:
+  - ile wynosiła objętość mózgu chłopca z Nariokotome?
+  - gdzie znajduje się czwarty polski cmentarz katyński?
+  - w jakich miejscach stał warszawski pomnik Ignacego Jana Paderewskiego?
+model-index:
+- name: snowflake-arctic-embed-m-klej-dyk
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.18509615384615385
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.4807692307692308
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.625
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7259615384615384
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.18509615384615385
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.16025641025641024
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.125
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07259615384615384
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.18509615384615385
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.4807692307692308
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.625
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7259615384615384
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.44786216254546357
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.358972451159951
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.3672210078826913
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.17548076923076922
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.47115384615384615
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6129807692307693
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7019230769230769
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.17548076923076922
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.15705128205128205
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.12259615384615384
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07019230769230768
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.17548076923076922
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.47115384615384615
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6129807692307693
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7019230769230769
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.43344535381311455
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.3473920177045177
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.3563798565478224
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.15625
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.4543269230769231
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.5649038461538461
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.6730769230769231
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.15625
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.15144230769230768
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.11298076923076923
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0673076923076923
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.15625
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.4543269230769231
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.5649038461538461
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.6730769230769231
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.4102597093872519
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.32613324175824177
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.3350744652348361
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.16346153846153846
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3918269230769231
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.5072115384615384
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.6057692307692307
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.16346153846153846
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.13060897435897434
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.10144230769230769
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.06057692307692307
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.16346153846153846
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.3918269230769231
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.5072115384615384
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.6057692307692307
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.3757626519143444
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.30273962148962136
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.3116992239855167
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14903846153846154
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.3389423076923077
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.4182692307692308
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.49278846153846156
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14903846153846154
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.11298076923076923
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.08365384615384615
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04927884615384615
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14903846153846154
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.3389423076923077
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.4182692307692308
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.49278846153846156
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.31783226267644227
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.26212320665445676
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.27044860532149884
+      name: Cosine Map@100
+---
+
+# snowflake-arctic-embed-m-klej-dyk
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-m](https://huggingface.co/Snowflake/snowflake-arctic-embed-m). 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
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Snowflake/snowflake-arctic-embed-m](https://huggingface.co/Snowflake/snowflake-arctic-embed-m) <!-- at revision 2ca412ec9505022eebd7d10286fbbad4b779f6e0 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, '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()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Chłopiec z Nariokotome',
+    'ile wynosiła objętość mózgu chłopca z Nariokotome?',
+    'gdzie znajduje się czwarty polski cmentarz katyński?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1851     |
+| cosine_accuracy@3   | 0.4808     |
+| cosine_accuracy@5   | 0.625      |
+| cosine_accuracy@10  | 0.726      |
+| cosine_precision@1  | 0.1851     |
+| cosine_precision@3  | 0.1603     |
+| cosine_precision@5  | 0.125      |
+| cosine_precision@10 | 0.0726     |
+| cosine_recall@1     | 0.1851     |
+| cosine_recall@3     | 0.4808     |
+| cosine_recall@5     | 0.625      |
+| cosine_recall@10    | 0.726      |
+| cosine_ndcg@10      | 0.4479     |
+| cosine_mrr@10       | 0.359      |
+| **cosine_map@100**  | **0.3672** |
+
+#### Information Retrieval
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1755     |
+| cosine_accuracy@3   | 0.4712     |
+| cosine_accuracy@5   | 0.613      |
+| cosine_accuracy@10  | 0.7019     |
+| cosine_precision@1  | 0.1755     |
+| cosine_precision@3  | 0.1571     |
+| cosine_precision@5  | 0.1226     |
+| cosine_precision@10 | 0.0702     |
+| cosine_recall@1     | 0.1755     |
+| cosine_recall@3     | 0.4712     |
+| cosine_recall@5     | 0.613      |
+| cosine_recall@10    | 0.7019     |
+| cosine_ndcg@10      | 0.4334     |
+| cosine_mrr@10       | 0.3474     |
+| **cosine_map@100**  | **0.3564** |
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1562     |
+| cosine_accuracy@3   | 0.4543     |
+| cosine_accuracy@5   | 0.5649     |
+| cosine_accuracy@10  | 0.6731     |
+| cosine_precision@1  | 0.1562     |
+| cosine_precision@3  | 0.1514     |
+| cosine_precision@5  | 0.113      |
+| cosine_precision@10 | 0.0673     |
+| cosine_recall@1     | 0.1562     |
+| cosine_recall@3     | 0.4543     |
+| cosine_recall@5     | 0.5649     |
+| cosine_recall@10    | 0.6731     |
+| cosine_ndcg@10      | 0.4103     |
+| cosine_mrr@10       | 0.3261     |
+| **cosine_map@100**  | **0.3351** |
+
+#### 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   | 0.1635     |
+| cosine_accuracy@3   | 0.3918     |
+| cosine_accuracy@5   | 0.5072     |
+| cosine_accuracy@10  | 0.6058     |
+| cosine_precision@1  | 0.1635     |
+| cosine_precision@3  | 0.1306     |
+| cosine_precision@5  | 0.1014     |
+| cosine_precision@10 | 0.0606     |
+| cosine_recall@1     | 0.1635     |
+| cosine_recall@3     | 0.3918     |
+| cosine_recall@5     | 0.5072     |
+| cosine_recall@10    | 0.6058     |
+| cosine_ndcg@10      | 0.3758     |
+| cosine_mrr@10       | 0.3027     |
+| **cosine_map@100**  | **0.3117** |
+
+#### 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   | 0.149      |
+| cosine_accuracy@3   | 0.3389     |
+| cosine_accuracy@5   | 0.4183     |
+| cosine_accuracy@10  | 0.4928     |
+| cosine_precision@1  | 0.149      |
+| cosine_precision@3  | 0.113      |
+| cosine_precision@5  | 0.0837     |
+| cosine_precision@10 | 0.0493     |
+| cosine_recall@1     | 0.149      |
+| cosine_recall@3     | 0.3389     |
+| cosine_recall@5     | 0.4183     |
+| cosine_recall@10    | 0.4928     |
+| cosine_ndcg@10      | 0.3178     |
+| cosine_mrr@10       | 0.2621     |
+| **cosine_map@100**  | **0.2704** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 3,738 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: 6 tokens</li><li>mean: 94.61 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 30.71 tokens</li><li>max: 76 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | anchor                                                                                                                                            |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Marsz Ochotników (chin.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | <code>kto jest kompozytorem chińskiego hymnu narodowego Marsz Ochotników?</code>                                                                  |
+  | <code>Wybrane przykłady: Święta Rodzina – Maryja z Dzieciątkiem na ręku, niekiedy obok niej stoi św. Józef Rodzina Marii – przedstawienie w którym pojawia się Święta Rodzina oraz postaci spokrewnione z Marią. Maria w połogu (Maria in puerperio) – leżąca na łożu Maria opiekuje się Dzieciątkiem Maria karmiąca (Maria lactans) – Maria karmiąca swą piersią Dzieciątko Orantka – kobieta modląca się z podniesionymi rękami (częsty motyw ikon wschodnich); Sacra Conversazione – Matka Boska tronująca z Dzieciątkiem, otoczona stojącymi postaciami świętych Pietà – opłakująca Jezusa, trzymając na kolanach jego ciało po śmierci na krzyżu; Hodegetria – ujęcie popiersia Maryi, trzymającej na rękach małego Jezusa, częsty motyw w ikonach Eleusa – formalnie podobne do przedstawienia Hodegetrii lecz Maryja policzkiem przytula się do policzka Jezusa Immaculata – Niepokalane Poczęcie Najświętszej Maryi Panny.</code> | <code>kto zamiast Maryi trzyma nowonarodzonego Jezusa w scenie Bożego Narodzenia przedstawionej na poliptyku z Marią i Dzieciątkiem Jezus?</code> |
+  | <code>Pomnik Josepha von Eichendorffa w Brzeziu Pomnik Josepha von Eichendorffa – odtworzony w 2006 roku pomnik znanego niemieckiego poety epoki romantyzmu związanego z ziemią raciborską, Josepha von Eichendorffa.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | <code>po ilu latach odtworzono wysadzony w 1945 roku pomnik Josepha von Eichendorffa w Raciborzu-Brzeziu?</code>                                  |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | 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 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.0684     | 1      | 9.3155        | -                      | -                      | -                      | -                     | -                      |
+| 0.1368     | 2      | 9.1788        | -                      | -                      | -                      | -                     | -                      |
+| 0.2051     | 3      | 8.8387        | -                      | -                      | -                      | -                     | -                      |
+| 0.2735     | 4      | 8.2961        | -                      | -                      | -                      | -                     | -                      |
+| 0.3419     | 5      | 8.0242        | -                      | -                      | -                      | -                     | -                      |
+| 0.4103     | 6      | 7.2329        | -                      | -                      | -                      | -                     | -                      |
+| 0.4786     | 7      | 5.4386        | -                      | -                      | -                      | -                     | -                      |
+| 0.5470     | 8      | 6.1186        | -                      | -                      | -                      | -                     | -                      |
+| 0.6154     | 9      | 4.9714        | -                      | -                      | -                      | -                     | -                      |
+| 0.6838     | 10     | 5.1958        | -                      | -                      | -                      | -                     | -                      |
+| 0.7521     | 11     | 5.1135        | -                      | -                      | -                      | -                     | -                      |
+| 0.8205     | 12     | 4.6971        | -                      | -                      | -                      | -                     | -                      |
+| 0.8889     | 13     | 4.5559        | -                      | -                      | -                      | -                     | -                      |
+| 0.9573     | 14     | 3.9357        | 0.2842                 | 0.3098                 | 0.3191                 | 0.2238                | 0.3209                 |
+| 1.0256     | 15     | 3.7916        | -                      | -                      | -                      | -                     | -                      |
+| 1.0940     | 16     | 3.6393        | -                      | -                      | -                      | -                     | -                      |
+| 1.1624     | 17     | 3.7733        | -                      | -                      | -                      | -                     | -                      |
+| 1.2308     | 18     | 3.6974        | -                      | -                      | -                      | -                     | -                      |
+| 1.2991     | 19     | 3.5964        | -                      | -                      | -                      | -                     | -                      |
+| 1.3675     | 20     | 3.4118        | -                      | -                      | -                      | -                     | -                      |
+| 1.4359     | 21     | 3.2022        | -                      | -                      | -                      | -                     | -                      |
+| 1.5043     | 22     | 2.8133        | -                      | -                      | -                      | -                     | -                      |
+| 1.5726     | 23     | 3.0871        | -                      | -                      | -                      | -                     | -                      |
+| 1.6410     | 24     | 2.9559        | -                      | -                      | -                      | -                     | -                      |
+| 1.7094     | 25     | 2.8192        | -                      | -                      | -                      | -                     | -                      |
+| 1.7778     | 26     | 3.462         | -                      | -                      | -                      | -                     | -                      |
+| 1.8462     | 27     | 3.1435        | -                      | -                      | -                      | -                     | -                      |
+| 1.9145     | 28     | 2.8001        | -                      | -                      | -                      | -                     | -                      |
+| 1.9829     | 29     | 2.5643        | 0.3134                 | 0.3359                 | 0.3563                 | 0.2588                | 0.3671                 |
+| 2.0513     | 30     | 2.4295        | -                      | -                      | -                      | -                     | -                      |
+| 2.1197     | 31     | 2.3892        | -                      | -                      | -                      | -                     | -                      |
+| 2.1880     | 32     | 2.5228        | -                      | -                      | -                      | -                     | -                      |
+| 2.2564     | 33     | 2.4906        | -                      | -                      | -                      | -                     | -                      |
+| 2.3248     | 34     | 2.5358        | -                      | -                      | -                      | -                     | -                      |
+| 2.3932     | 35     | 2.2806        | -                      | -                      | -                      | -                     | -                      |
+| 2.4615     | 36     | 2.0083        | -                      | -                      | -                      | -                     | -                      |
+| 2.5299     | 37     | 2.5088        | -                      | -                      | -                      | -                     | -                      |
+| 2.5983     | 38     | 2.0628        | -                      | -                      | -                      | -                     | -                      |
+| 2.6667     | 39     | 2.193         | -                      | -                      | -                      | -                     | -                      |
+| 2.7350     | 40     | 2.4783        | -                      | -                      | -                      | -                     | -                      |
+| 2.8034     | 41     | 2.382         | -                      | -                      | -                      | -                     | -                      |
+| 2.8718     | 42     | 2.2017        | -                      | -                      | -                      | -                     | -                      |
+| 2.9402     | 43     | 1.9739        | 0.3111                 | 0.3392                 | 0.3572                 | 0.2657                | 0.3659                 |
+| 3.0085     | 44     | 2.0332        | -                      | -                      | -                      | -                     | -                      |
+| 3.0769     | 45     | 1.9983        | -                      | -                      | -                      | -                     | -                      |
+| 3.1453     | 46     | 1.8612        | -                      | -                      | -                      | -                     | -                      |
+| 3.2137     | 47     | 1.9897        | -                      | -                      | -                      | -                     | -                      |
+| 3.2821     | 48     | 2.2514        | -                      | -                      | -                      | -                     | -                      |
+| 3.3504     | 49     | 2.0092        | -                      | -                      | -                      | -                     | -                      |
+| 3.4188     | 50     | 1.7399        | -                      | -                      | -                      | -                     | -                      |
+| 3.4872     | 51     | 1.5825        | -                      | -                      | -                      | -                     | -                      |
+| 3.5556     | 52     | 2.1501        | -                      | -                      | -                      | -                     | -                      |
+| 3.6239     | 53     | 1.4505        | -                      | -                      | -                      | -                     | -                      |
+| 3.6923     | 54     | 1.8575        | -                      | -                      | -                      | -                     | -                      |
+| 3.7607     | 55     | 2.3882        | -                      | -                      | -                      | -                     | -                      |
+| 3.8291     | 56     | 2.1119        | -                      | -                      | -                      | -                     | -                      |
+| 3.8974     | 57     | 1.8992        | -                      | -                      | -                      | -                     | -                      |
+| 3.9658     | 58     | 1.8323        | 0.3117                 | 0.3365                 | 0.3558                 | 0.2683                | 0.3670                 |
+| 4.0342     | 59     | 1.5938        | -                      | -                      | -                      | -                     | -                      |
+| 4.1026     | 60     | 1.552         | -                      | -                      | -                      | -                     | -                      |
+| 4.1709     | 61     | 1.907         | -                      | -                      | -                      | -                     | -                      |
+| 4.2393     | 62     | 1.8304        | -                      | -                      | -                      | -                     | -                      |
+| 4.3077     | 63     | 1.8775        | -                      | -                      | -                      | -                     | -                      |
+| 4.3761     | 64     | 1.8654        | -                      | -                      | -                      | -                     | -                      |
+| 4.4444     | 65     | 1.7944        | -                      | -                      | -                      | -                     | -                      |
+| 4.5128     | 66     | 1.8335        | -                      | -                      | -                      | -                     | -                      |
+| 4.5812     | 67     | 1.8823        | -                      | -                      | -                      | -                     | -                      |
+| 4.6496     | 68     | 1.6479        | -                      | -                      | -                      | -                     | -                      |
+| 4.7179     | 69     | 1.5771        | -                      | -                      | -                      | -                     | -                      |
+| **4.7863** | **70** | **2.1911**    | **0.3117**             | **0.3351**             | **0.3564**             | **0.2704**            | **0.3672**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.2
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.2
+- PyTorch: 2.3.1
+- Accelerate: 0.27.2
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```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},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "models/snowflake-arctic-embed-m-klej-dyk-v0.1",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,12 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0.dev0",
+    "transformers": "4.39.3",
+    "pytorch": "2.1.0+cu121"
+  },
+  "prompts": {
+    "query": "Represent this sentence for searching relevant passages: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b76690dcbee05cc5e2b8bb778c18bee047eb1a9187844e4664a967a4b8dea7
+size 437951328

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}