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 +1,805 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+datasets: []
+language: []
+library_name: sentence-transformers
+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
+- generated_from_trainer
+- dataset_size:111
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Template la - Spy cepA s3062 F30 Sequence ( 5' /3') Oligo [ l AGACTCCATATGGAGTCTAGCCAAACAG500
+    nM GAACA (SEQ ID NO, 1) In addition to containing the reagents necessary for driv­
+    ing the GAS NEAR assay, the lyophilized material also contains the lytic agent
+    for GAS, the protein plyC; therefore, 65 GAS lysis does not occur until the lyophilized
+    material is re-suspended. In some cases, the lyophilized material does not contain
+    a lytic agent for GAS, for example, in some
+  sentences:
+  - (45) Date of Patent
+  - http
+  - ID
+- source_sentence: :-"<-------t 40000 -1-----/-f-~~-----I 35000 -----+-IN----------
+    § 30000 ----t+t---=~--- ~ 25000 ----~---++------t ~ 20000 -1----ff-r-ff.,.__----->t''n-\--------l
+  sentences:
+  - 45000 -------,-----=.....
+  - -~' ~-- -~<
+  - comprises
+- source_sentence: 55 1. A composition comprising i) a forward template comprising
+    a nucleic acid sequence comprising a recognition region at the 3' end that is
+    complementary to the 3' end of the Streptococcus pyogenes (S. pyogenes) cell envelope
+    proteinase A 60 (cepA) gene antisense strand; a nicking enzyme bind­ ing site
+    and a nicking site upstream of said recognition region; and a stabilizing region
+    upstream of said nick­ ing site, the forward template comprising a nucleotide
+    sequence having at least 80, 85, or 95% identity to SEQ 65
+  sentences:
+  - ''' -- ,'' ,.,,,..,,,. _..,,,,.,,, .... ~-__ .... , , _,. ........-----.'
+  - What is claimed is
+  - annotated as follows
+- source_sentence: 0 1 2 3 4 5 6 7 8 9 10 Time (minutes) FIG. 1 (Cont.)
+  sentences:
+  - ',-;.-'
+  - I I I I I I I I I
+  - (21) Appl. No.
+- source_sentence: '~ " ''"-''-en 25000 1 ,.,,µ,· ,, · .,-,.. •~h • 1 (1) ,\ II J
+    } 7; . \ \(9,i, .,u, 4\:'
+  sentences:
+  - 80, 85, or 95% identity to SEQ ID NO
+  - u
+  - en 25000 I ' 'lJVL' • -. • . .,.. ""~" '' ' I Q) l!J "667 7 ..._7 ... -,
+model-index:
+- name: SentenceTransformer based on BAAI/bge-base-en-v1.5
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.0
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.07692307692307693
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.07692307692307693
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.23076923076923078
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.02564102564102564
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.015384615384615385
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.02307692307692308
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.07692307692307693
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.07692307692307693
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.23076923076923078
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.10157463646252407
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.06227106227106227
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.08137504276350917
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.0
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.07692307692307693
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.07692307692307693
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.23076923076923078
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.02564102564102564
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.015384615384615385
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.02307692307692308
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.07692307692307693
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.07692307692307693
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.23076923076923078
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.09595574046316672
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.05662393162393163
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.0744997471979569
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.0
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.07692307692307693
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.07692307692307693
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.23076923076923078
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.02564102564102564
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.015384615384615385
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.02307692307692308
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.07692307692307693
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.07692307692307693
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.23076923076923078
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.0981693666921052
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.05897435897435897
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.08277736107354086
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.07692307692307693
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.23076923076923078
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.23076923076923078
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.38461538461538464
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.07692307692307693
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.07692307692307693
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.04615384615384616
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.038461538461538464
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.07692307692307693
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.23076923076923078
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.23076923076923078
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.38461538461538464
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.21938110224036803
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.1700854700854701
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.1860790779646314
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.0
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.07692307692307693
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.15384615384615385
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.3076923076923077
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.0
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.02564102564102564
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03076923076923077
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.03076923076923077
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.0
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.07692307692307693
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.15384615384615385
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.3076923076923077
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.1299580480538269
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.07628205128205127
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.10015432076692518
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-base-en-v1.5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### 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': True}) 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("kr-manish/bge-base-raw_pdf_finetuned_vf1")
+# Run inference
+sentences = [
+    '~ " \'"-\'-en 25000 1 ,.,,µ,· ,, · .,-,.. •~h • 1 (1) ,\\ II J } 7; . \\ \\(9,i, .,u, 4\\:',
+    'en 25000 I \' \'lJVL\' • -. • . .,.. ""~" \'\' \' I Q) l!J "667 7 ..._7 ... -,',
+    '80, 85, or 95% identity to SEQ ID NO',
+]
+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   | 0.0        |
+| cosine_accuracy@3   | 0.0769     |
+| cosine_accuracy@5   | 0.0769     |
+| cosine_accuracy@10  | 0.2308     |
+| cosine_precision@1  | 0.0        |
+| cosine_precision@3  | 0.0256     |
+| cosine_precision@5  | 0.0154     |
+| cosine_precision@10 | 0.0231     |
+| cosine_recall@1     | 0.0        |
+| cosine_recall@3     | 0.0769     |
+| cosine_recall@5     | 0.0769     |
+| cosine_recall@10    | 0.2308     |
+| cosine_ndcg@10      | 0.1016     |
+| cosine_mrr@10       | 0.0623     |
+| **cosine_map@100**  | **0.0814** |
+
+#### 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   | 0.0        |
+| cosine_accuracy@3   | 0.0769     |
+| cosine_accuracy@5   | 0.0769     |
+| cosine_accuracy@10  | 0.2308     |
+| cosine_precision@1  | 0.0        |
+| cosine_precision@3  | 0.0256     |
+| cosine_precision@5  | 0.0154     |
+| cosine_precision@10 | 0.0231     |
+| cosine_recall@1     | 0.0        |
+| cosine_recall@3     | 0.0769     |
+| cosine_recall@5     | 0.0769     |
+| cosine_recall@10    | 0.2308     |
+| cosine_ndcg@10      | 0.096      |
+| cosine_mrr@10       | 0.0566     |
+| **cosine_map@100**  | **0.0745** |
+
+#### 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   | 0.0        |
+| cosine_accuracy@3   | 0.0769     |
+| cosine_accuracy@5   | 0.0769     |
+| cosine_accuracy@10  | 0.2308     |
+| cosine_precision@1  | 0.0        |
+| cosine_precision@3  | 0.0256     |
+| cosine_precision@5  | 0.0154     |
+| cosine_precision@10 | 0.0231     |
+| cosine_recall@1     | 0.0        |
+| cosine_recall@3     | 0.0769     |
+| cosine_recall@5     | 0.0769     |
+| cosine_recall@10    | 0.2308     |
+| cosine_ndcg@10      | 0.0982     |
+| cosine_mrr@10       | 0.059      |
+| **cosine_map@100**  | **0.0828** |
+
+#### 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   | 0.0769     |
+| cosine_accuracy@3   | 0.2308     |
+| cosine_accuracy@5   | 0.2308     |
+| cosine_accuracy@10  | 0.3846     |
+| cosine_precision@1  | 0.0769     |
+| cosine_precision@3  | 0.0769     |
+| cosine_precision@5  | 0.0462     |
+| cosine_precision@10 | 0.0385     |
+| cosine_recall@1     | 0.0769     |
+| cosine_recall@3     | 0.2308     |
+| cosine_recall@5     | 0.2308     |
+| cosine_recall@10    | 0.3846     |
+| cosine_ndcg@10      | 0.2194     |
+| cosine_mrr@10       | 0.1701     |
+| **cosine_map@100**  | **0.1861** |
+
+#### 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   | 0.0        |
+| cosine_accuracy@3   | 0.0769     |
+| cosine_accuracy@5   | 0.1538     |
+| cosine_accuracy@10  | 0.3077     |
+| cosine_precision@1  | 0.0        |
+| cosine_precision@3  | 0.0256     |
+| cosine_precision@5  | 0.0308     |
+| cosine_precision@10 | 0.0308     |
+| cosine_recall@1     | 0.0        |
+| cosine_recall@3     | 0.0769     |
+| cosine_recall@5     | 0.1538     |
+| cosine_recall@10    | 0.3077     |
+| cosine_ndcg@10      | 0.13       |
+| cosine_mrr@10       | 0.0763     |
+| **cosine_map@100**  | **0.1002** |
+
+<!--
+## 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: 111 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: 2 tokens</li><li>mean: 124.53 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 11.15 tokens</li><li>max: 60 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       | anchor                                    |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------|
+  | <code>ply C Tris pH8.0 Dextran Trehalose dNTPS Na2SO4 Triton X-100 DTT TABLE 3 GAS Lyophilization Mix -Reagent Composition vl.0 v2.0 Strep A (Target) Lyo Conditions 500 nM F30 500 nM F30b.5om 100 nM R41m 100 nM R41m.lb.5om 200 nM MB4 FAM 200 nM MB4_ Fam 3.0. ug 5.0 ug 30U 0.7 ug 1 ug 1 ug 50mM 50 mM Dextran 150 Dextran 500 5% in 2x Iyo 5% in 2x Iyo 100 mM in 2x Iyo 100 mM in 2x Iyo 0.3 mM 0.3 mM 15 mM 22.5 mM 0.10% 0.10% 2mM 2mM Strep A (IC) Lyo Conditions</code>                                                                                                                                                                                                                                                                                                                                                            | <code>NE</code>                           |
+  | <code>CTGTTTG (SEQ ID NO, 5) To confirm that the targeted sequence was conserved among all GAS cepA sequences found in the public domain as well as unique to GAS, multiple sequence alignments and BLAST analyses were performed. Multiple alignment analysis of these sequences showed complete homology for the region of the gene targeted by the 3062 assay. Further, there are currently 24 complete GAS genomes (including whole genome shotgun sequence) available for sequence analysis in NCBI Genome. The cepA gene is present in all 24 genomes, and the 3062 target region within cepA is conserved among all 24 genomes. Upon BLAST analysis, it was confirmed that no other species contain significant homology to the 3062 target sequence. Assay Development As a reference, the reagent mixtures discussed below are</code> | <code>GCAATCTGAGGAGAGGCCATACTTGTTC</code> |
+  | <code>AGATTGC (SEQ ID NO, 4)</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            | <code>CAAACAGGAACAAGTATGGCCTCTCCTC</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`: 32
+- `num_train_epochs`: 15
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+
+#### 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`: 32
+- `eval_accumulation_steps`: None
+- `learning_rate`: 5e-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`: 15
+- `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`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `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`: batch_sampler
+- `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       | 0     | -             | 0.0747                 | 0.0694                 | 0.0681                 | 0.1224                | 0.0705                 |
+| 1.0     | 1     | -             | 0.0750                 | 0.0694                 | 0.0681                 | 0.1224                | 0.0705                 |
+| 2.0     | 2     | -             | 0.1008                 | 0.0724                 | 0.0696                 | 0.0719                | 0.0710                 |
+| **3.0** | **3** | **-**         | **0.1861**             | **0.0828**             | **0.0745**             | **0.1002**            | **0.0814**             |
+| 4.0     | 4     | -             | 0.1711                 | 0.0968                 | 0.0825                 | 0.0861                | 0.1001                 |
+| 5.0     | 6     | -             | 0.1505                 | 0.1140                 | 0.1094                 | 0.1534                | 0.1502                 |
+| 6.0     | 7     | -             | 0.1222                 | 0.1143                 | 0.1108                 | 0.1528                | 0.1520                 |
+| 7.0     | 8     | -             | 0.1589                 | 0.1536                 | 0.1512                 | 0.1513                | 0.1516                 |
+| 8.0     | 9     | -             | 0.1561                 | 0.1550                 | 0.1531                 | 0.1495                | 0.1520                 |
+| 9.0     | 10    | 1.8482        | 0.1565                 | 0.1558                 | 0.1544                 | 0.1483                | 0.1522                 |
+| 10.0    | 12    | -             | 0.1562                 | 0.1551                 | 0.1557                 | 0.1416                | 0.1531                 |
+| 11.0    | 13    | -             | 0.1561                 | 0.1558                 | 0.1562                 | 0.1401                | 0.1533                 |
+| 12.0    | 14    | -             | 0.1559                 | 0.1559                 | 0.1562                 | 0.1402                | 0.1533                 |
+| 13.0    | 15    | -             | 0.1861                 | 0.0828                 | 0.0745                 | 0.1002                | 0.0814                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.20.0
+- 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 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc536359a75765632574b90995b4b8c4cdf8ee24181c503bd9933cabcce73b5
+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": true
+}

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 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}