Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,865 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dataset_size:100K<n<1M
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: distilbert/distilroberta-base
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Test Rocks
+  sentences:
+  - Number of testimonies
+  - People are at a pool.
+  - I've never been to Asia
+- source_sentence: No animals.
+  sentences:
+  - We don't have a dog.
+  - These boys are on bikes
+  - A person is climbing.
+- source_sentence: Shrinking.
+  sentences:
+  - That doesn't seem fair.
+  - A man reads the paper.
+  - I've never been to Asia
+- source_sentence: Loire Valley
+  sentences:
+  - A Lake in Loire.
+  - people stand near pole
+  - A cat is licking itself.
+- source_sentence: It is well.
+  sentences:
+  - That's convenient.
+  - away from the children
+  - She hated the restaurant!
+pipeline_tag: sentence-similarity
+model-index:
+- name: SentenceTransformer based on distilbert/distilroberta-base
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 768
+      type: sts-dev-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8413274730706258
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8478057476815382
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8414182910991368
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8394684211369814
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8423380151813549
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8401129676358965
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7854982058734802
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7814388303641997
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8423380151813549
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8478057476815382
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 512
+      type: sts-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8394744649386727
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8469596264857904
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8398552366754626
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8377241640608183
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8406514989809173
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8380050330376462
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7811135781647157
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7776714775017128
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8406514989809173
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8469596264857904
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 256
+      type: sts-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8326846589795867
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8435757360139872
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.835121668379584
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.833167770567356
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8359785864160201
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8337674519096212
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7499541215721716
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7452815230357489
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8359785864160201
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8435757360139872
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 128
+      type: sts-dev-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8243384464323462
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8399706247679909
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8281897604718583
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8270317815639731
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8281918243965822
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8267242273030063
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7110017325551932
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.7049602384186016
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8281918243965822
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8399706247679909
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 64
+      type: sts-dev-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.811599959622093
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8316629408285197
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8113103800424869
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8104916438729426
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8113924334973999
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8110877753624469
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.641225674602723
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.6346995881423587
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.811599959622093
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8316629408285197
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 32
+      type: sts-dev-32
+    metrics:
+    - type: pearson_cosine
+      value: 0.7834130163353433
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.814057381112976
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7831854350286095
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.7859760066096324
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7868628503474937
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.7893614397994021
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.5533705216922039
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.5449230360083127
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7868628503474937
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.814057381112976
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 16
+      type: sts-dev-16
+    metrics:
+    - type: pearson_cosine
+      value: 0.7259201534121641
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7751337117844075
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.7420762055565752
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.7552849049126117
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.7483211915991654
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.759888035465032
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.4387404126202509
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.42591442860202633
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.7483211915991654
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.7751337117844075
+      name: Spearman Max
+---
+
+# SentenceTransformer based on distilbert/distilroberta-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) dataset. 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:** [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) <!-- at revision fb53ab8802853c8e4fbdbcd0529f21fc6f459b2b -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli)
+- **Language:** en
+<!-- - **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': False}) with Transformer model: RobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## 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("mrm8488/distilroberta-base-ft-allnli-matryoshka-768-16-1e-128bs")
+# Run inference
+sentences = [
+    'It is well.',
+    "That's convenient.",
+    'away from the children',
+]
+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
+
+#### Semantic Similarity
+* Dataset: `sts-dev-768`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8413     |
+| **spearman_cosine** | **0.8478** |
+| pearson_manhattan   | 0.8414     |
+| spearman_manhattan  | 0.8395     |
+| pearson_euclidean   | 0.8423     |
+| spearman_euclidean  | 0.8401     |
+| pearson_dot         | 0.7855     |
+| spearman_dot        | 0.7814     |
+| pearson_max         | 0.8423     |
+| spearman_max        | 0.8478     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-512`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.8395    |
+| **spearman_cosine** | **0.847** |
+| pearson_manhattan   | 0.8399    |
+| spearman_manhattan  | 0.8377    |
+| pearson_euclidean   | 0.8407    |
+| spearman_euclidean  | 0.838     |
+| pearson_dot         | 0.7811    |
+| spearman_dot        | 0.7777    |
+| pearson_max         | 0.8407    |
+| spearman_max        | 0.847     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8327     |
+| **spearman_cosine** | **0.8436** |
+| pearson_manhattan   | 0.8351     |
+| spearman_manhattan  | 0.8332     |
+| pearson_euclidean   | 0.836      |
+| spearman_euclidean  | 0.8338     |
+| pearson_dot         | 0.75       |
+| spearman_dot        | 0.7453     |
+| pearson_max         | 0.836      |
+| spearman_max        | 0.8436     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value    |
+|:--------------------|:---------|
+| pearson_cosine      | 0.8243   |
+| **spearman_cosine** | **0.84** |
+| pearson_manhattan   | 0.8282   |
+| spearman_manhattan  | 0.827    |
+| pearson_euclidean   | 0.8282   |
+| spearman_euclidean  | 0.8267   |
+| pearson_dot         | 0.711    |
+| spearman_dot        | 0.705    |
+| pearson_max         | 0.8282   |
+| spearman_max        | 0.84     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8116     |
+| **spearman_cosine** | **0.8317** |
+| pearson_manhattan   | 0.8113     |
+| spearman_manhattan  | 0.8105     |
+| pearson_euclidean   | 0.8114     |
+| spearman_euclidean  | 0.8111     |
+| pearson_dot         | 0.6412     |
+| spearman_dot        | 0.6347     |
+| pearson_max         | 0.8116     |
+| spearman_max        | 0.8317     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-32`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7834     |
+| **spearman_cosine** | **0.8141** |
+| pearson_manhattan   | 0.7832     |
+| spearman_manhattan  | 0.786      |
+| pearson_euclidean   | 0.7869     |
+| spearman_euclidean  | 0.7894     |
+| pearson_dot         | 0.5534     |
+| spearman_dot        | 0.5449     |
+| pearson_max         | 0.7869     |
+| spearman_max        | 0.8141     |
+
+#### Semantic Similarity
+* Dataset: `sts-dev-16`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.7259     |
+| **spearman_cosine** | **0.7751** |
+| pearson_manhattan   | 0.7421     |
+| spearman_manhattan  | 0.7553     |
+| pearson_euclidean   | 0.7483     |
+| spearman_euclidean  | 0.7599     |
+| pearson_dot         | 0.4387     |
+| spearman_dot        | 0.4259     |
+| pearson_max         | 0.7483     |
+| spearman_max        | 0.7751     |
+
+<!--
+## 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
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 557,850 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                         | negative                                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 10.38 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.8 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.4 tokens</li><li>max: 50 tokens</li></ul> |
+* Samples:
+  | anchor                                                                     | positive                                         | negative                                                   |
+  |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code>        | <code>A person is outdoors, on a horse.</code>   | <code>A person is at a diner, ordering an omelette.</code> |
+  | <code>Children smiling and waving at camera</code>                         | <code>There are children present</code>          | <code>The kids are frowning</code>                         |
+  | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</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,
+          32,
+          16
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/all-nli
+
+* Dataset: [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
+* Size: 6,584 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                         | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 18.02 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 9.81 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.37 tokens</li><li>max: 29 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                         | positive                                                    | negative                                                |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------|:--------------------------------------------------------|
+  | <code>Two women are embracing while holding to go packages.</code>                                                                                                             | <code>Two woman are holding packages.</code>                | <code>The men are fighting outside a deli.</code>       |
+  | <code>Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.</code> | <code>Two kids in numbered jerseys wash their hands.</code> | <code>Two kids in jackets walk to school.</code>        |
+  | <code>A man selling donuts to a customer during a world exhibition event held in the city of Angeles</code>                                                                    | <code>A man selling donuts to a customer.</code>            | <code>A woman drinks her coffee in a small cafe.</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,
+          32,
+          16
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `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`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `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`: False
+- `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
+- `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 | loss    | sts-dev-128_spearman_cosine | sts-dev-16_spearman_cosine | sts-dev-256_spearman_cosine | sts-dev-32_spearman_cosine | sts-dev-512_spearman_cosine | sts-dev-64_spearman_cosine | sts-dev-768_spearman_cosine |
+|:------:|:----:|:-------------:|:-------:|:---------------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|
+| 0.0229 | 100  | 29.0917       | 14.1514 | 0.7659                      | 0.7440                     | 0.7915                      | 0.7749                     | 0.7999                      | 0.7909                     | 0.7918                      |
+| 0.0459 | 200  | 15.6915       | 11.7031 | 0.7718                      | 0.7487                     | 0.7940                      | 0.7776                     | 0.8005                      | 0.7931                     | 0.7871                      |
+| 0.0688 | 300  | 14.3136       | 11.1970 | 0.7744                      | 0.7389                     | 0.7952                      | 0.7728                     | 0.8036                      | 0.7925                     | 0.7938                      |
+| 0.0918 | 400  | 12.8122       | 10.4416 | 0.7899                      | 0.7536                     | 0.8040                      | 0.7764                     | 0.8065                      | 0.7953                     | 0.8018                      |
+| 0.1147 | 500  | 12.1747       | 10.5491 | 0.7871                      | 0.7513                     | 0.8035                      | 0.7785                     | 0.8094                      | 0.7978                     | 0.8008                      |
+| 0.1376 | 600  | 11.6784       | 9.6618  | 0.7785                      | 0.7465                     | 0.7956                      | 0.7762                     | 0.8027                      | 0.7953                     | 0.7935                      |
+| 0.1606 | 700  | 11.9351       | 9.3279  | 0.7907                      | 0.7403                     | 0.7995                      | 0.7706                     | 0.8036                      | 0.7894                     | 0.7982                      |
+| 0.1835 | 800  | 10.4998       | 9.1538  | 0.7911                      | 0.7516                     | 0.8043                      | 0.7820                     | 0.8078                      | 0.8025                     | 0.8010                      |
+| 0.2065 | 900  | 10.6069       | 9.0531  | 0.7874                      | 0.7371                     | 0.7974                      | 0.7704                     | 0.8042                      | 0.7910                     | 0.8010                      |
+| 0.2294 | 1000 | 10.0316       | 8.9759  | 0.7842                      | 0.7356                     | 0.7981                      | 0.7721                     | 0.8024                      | 0.7905                     | 0.7955                      |
+| 0.2524 | 1100 | 10.199        | 8.5398  | 0.7863                      | 0.7322                     | 0.7961                      | 0.7691                     | 0.8002                      | 0.7910                     | 0.7936                      |
+| 0.2753 | 1200 | 9.9393        | 8.1356  | 0.7860                      | 0.7304                     | 0.7990                      | 0.7682                     | 0.8025                      | 0.7908                     | 0.7954                      |
+| 0.2982 | 1300 | 9.8711        | 7.9177  | 0.7932                      | 0.7319                     | 0.8028                      | 0.7708                     | 0.8067                      | 0.7924                     | 0.8013                      |
+| 0.3212 | 1400 | 9.3594        | 7.8870  | 0.7892                      | 0.7296                     | 0.8032                      | 0.7710                     | 0.8070                      | 0.7961                     | 0.8030                      |
+| 0.3441 | 1500 | 9.4534        | 7.5756  | 0.8003                      | 0.7518                     | 0.8078                      | 0.7857                     | 0.8112                      | 0.8063                     | 0.8068                      |
+| 0.3671 | 1600 | 8.9061        | 7.8164  | 0.7781                      | 0.7390                     | 0.7942                      | 0.7761                     | 0.8002                      | 0.7968                     | 0.7941                      |
+| 0.3900 | 1700 | 8.5164        | 7.4869  | 0.7934                      | 0.7530                     | 0.8063                      | 0.7864                     | 0.8120                      | 0.8055                     | 0.8080                      |
+| 0.4129 | 1800 | 8.9262        | 7.7155  | 0.7846                      | 0.7301                     | 0.7991                      | 0.7728                     | 0.8065                      | 0.7945                     | 0.8003                      |
+| 0.4359 | 1900 | 8.3242        | 7.3068  | 0.7850                      | 0.7273                     | 0.7976                      | 0.7710                     | 0.8020                      | 0.7904                     | 0.7976                      |
+| 0.4588 | 2000 | 8.5374        | 7.1026  | 0.7845                      | 0.7272                     | 0.7993                      | 0.7717                     | 0.8042                      | 0.7925                     | 0.7963                      |
+| 0.4818 | 2100 | 8.2304        | 7.1601  | 0.7879                      | 0.7354                     | 0.8015                      | 0.7719                     | 0.8059                      | 0.7944                     | 0.8029                      |
+| 0.5047 | 2200 | 8.1347        | 7.8267  | 0.7715                      | 0.7230                     | 0.7889                      | 0.7626                     | 0.7956                      | 0.7849                     | 0.7930                      |
+| 0.5276 | 2300 | 8.3057        | 8.0057  | 0.7622                      | 0.7148                     | 0.7814                      | 0.7572                     | 0.7881                      | 0.7769                     | 0.7836                      |
+| 0.5506 | 2400 | 8.215         | 7.6922  | 0.7772                      | 0.7210                     | 0.7929                      | 0.7637                     | 0.7995                      | 0.7858                     | 0.7956                      |
+| 0.5735 | 2500 | 8.4343        | 7.2104  | 0.7869                      | 0.7307                     | 0.8017                      | 0.7707                     | 0.8071                      | 0.7929                     | 0.8048                      |
+| 0.5965 | 2600 | 8.159         | 6.9977  | 0.7893                      | 0.7297                     | 0.8031                      | 0.7733                     | 0.8071                      | 0.7928                     | 0.8045                      |
+| 0.6194 | 2700 | 8.2048        | 6.9465  | 0.7859                      | 0.7280                     | 0.8006                      | 0.7725                     | 0.8052                      | 0.7926                     | 0.8004                      |
+| 0.6423 | 2800 | 8.187         | 7.3185  | 0.7790                      | 0.7266                     | 0.7960                      | 0.7690                     | 0.8018                      | 0.7911                     | 0.7964                      |
+| 0.6653 | 2900 | 8.4768        | 7.5535  | 0.7756                      | 0.7192                     | 0.7913                      | 0.7618                     | 0.7958                      | 0.7827                     | 0.7907                      |
+| 0.6882 | 3000 | 8.4153        | 7.3732  | 0.7825                      | 0.7276                     | 0.7988                      | 0.7692                     | 0.8029                      | 0.7899                     | 0.7988                      |
+| 0.7112 | 3100 | 7.9226        | 6.8469  | 0.7912                      | 0.7311                     | 0.8055                      | 0.7765                     | 0.8101                      | 0.7977                     | 0.8058                      |
+| 0.7341 | 3200 | 8.1155        | 6.7604  | 0.7880                      | 0.7298                     | 0.8024                      | 0.7747                     | 0.8071                      | 0.7959                     | 0.8025                      |
+| 0.7571 | 3300 | 6.8463        | 5.4863  | 0.8357                      | 0.7638                     | 0.8407                      | 0.8085                     | 0.8431                      | 0.8283                     | 0.8440                      |
+| 0.7800 | 3400 | 5.2008        | 5.2472  | 0.8362                      | 0.7655                     | 0.8401                      | 0.8105                     | 0.8429                      | 0.8279                     | 0.8445                      |
+| 0.8029 | 3500 | 4.5415        | 5.1649  | 0.8385                      | 0.7700                     | 0.8421                      | 0.8138                     | 0.8454                      | 0.8304                     | 0.8465                      |
+| 0.8259 | 3600 | 4.4474        | 5.0933  | 0.8371                      | 0.7693                     | 0.8410                      | 0.8112                     | 0.8443                      | 0.8288                     | 0.8451                      |
+| 0.8488 | 3700 | 4.12          | 5.0555  | 0.8396                      | 0.7718                     | 0.8439                      | 0.8140                     | 0.8463                      | 0.8311                     | 0.8471                      |
+| 0.8718 | 3800 | 3.9104        | 5.0147  | 0.8386                      | 0.7749                     | 0.8432                      | 0.8129                     | 0.8459                      | 0.8304                     | 0.8471                      |
+| 0.8947 | 3900 | 3.9054        | 4.9966  | 0.8379                      | 0.7733                     | 0.8424                      | 0.8125                     | 0.8456                      | 0.8296                     | 0.8464                      |
+| 0.9176 | 4000 | 3.757         | 4.9892  | 0.8407                      | 0.7763                     | 0.8447                      | 0.8156                     | 0.8478                      | 0.8326                     | 0.8488                      |
+| 0.9406 | 4100 | 3.7729        | 4.9859  | 0.8400                      | 0.7751                     | 0.8436                      | 0.8141                     | 0.8470                      | 0.8317                     | 0.8478                      |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.1
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.2
+- 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 +1,27 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/matryoshka_nli_distilroberta-base_128_bs_1_e_768-16/checkpoint-4100",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

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 sha256:80c515d8e10f0472f601cb7863a8b93b9ff9f87442df20ac7ed8e4bb8e412bdb
+size 328485128

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "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": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}