Upload v1

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

@@ -1,3 +1,837 @@
----
-license: mit
----
+---
+base_model: Alibaba-NLP/gte-base-en-v1.5
+datasets: []
+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
+- generated_from_trainer
+- dataset_size:32833
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Anonymity in online interactions can lead to a disinhibition effect,
+    where individuals feel free to express hostile or aggressive opinions they might
+    otherwise suppress.
+  sentences:
+  - What are the implications of anonymity in online interactions?
+  - How does creativity function as a form of costly signalling in personal expressions
+    such as invitations?
+  - Why is conflict considered essential in a creative organization?
+- source_sentence: The author decides to release their novel into the world despite
+    its imperfections, and finds that this allows them to move on to new projects
+    and experiences, and to focus on the value of the work itself rather than its
+    flaws.
+  sentences:
+  - How does the author's experience with their novel illustrate the concept of 'embracing
+    imperfection' in creative work?
+  - What does the author mean by 'ambitious programmers are better off doing their
+    own thing'?
+  - What is the role of 'show me' in the design process?
+- source_sentence: Tokens become more valuable as more users adopt them, creating
+    a positive feedback loop that enhances their utility and encourages further adoption
+    across various applications.
+  sentences:
+  - In what ways do tokens exhibit network effects?
+  - What can sometimes be found when considering a startup with a lame-sounding idea?
+  - How do social norms influence decision-making in the context of airport choices?
+- source_sentence: Philosophers are often viewed as the guardians of critical thinking;
+    however, their reliance on bureaucratic structures and abstract discussions can
+    become problematic. Instead of fostering open-mindedness, they may perpetuate
+    dogmatic thinking and limit the exploration of diverse perspectives, thereby failing
+    to fulfill their duty of promoting genuine critical engagement.
+  sentences:
+  - In what ways can the role of philosophers be seen as essential or problematic
+    within the context of critical thinking?
+  - How does the evolution of pair-bonding facilitate cultural exchange between groups?
+  - What is the role of autonomy in the success of acquired startups?
+- source_sentence: Society tends to admire those who despair when others hope, viewing
+    them as sages or wise figures.
+  sentences:
+  - What is often the societal perception of those who express pessimism about the
+    future?
+  - How did the realization about user engagement influence the app development strategy?
+  - What lessons can be learned from the historical context of employee relations
+    in large corporations?
+model-index:
+- name: Custom Embedding Test - Anudit Nagar
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7683027145599123
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8755141211955032
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9097888675623801
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9465313956676721
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7683027145599123
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.29183804039850103
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18195777351247602
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09465313956676721
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7683027145599123
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8755141211955032
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9097888675623801
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9465313956676721
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8566925927271383
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8279207524340517
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8302321946792381
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.762818755141212
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8700301617768028
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9062242939402249
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.946257197696737
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.762818755141212
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2900100539256009
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18124485878804497
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09462571976967371
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.762818755141212
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8700301617768028
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9062242939402249
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.946257197696737
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8529743473843932
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8231949721667308
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.825407004380477
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.762818755141212
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8683849739511927
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9015629284343296
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9418700301617768
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.762818755141212
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28946165798373086
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.18031258568686592
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09418700301617768
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.762818755141212
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8683849739511927
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9015629284343296
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9418700301617768
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.850685453111757
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8215859088357048
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8239714751253995
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7573347957225116
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8634494104743625
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8952563751028242
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9347408829174664
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7573347957225116
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2878164701581208
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17905127502056484
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09347408829174664
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7573347957225116
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8634494104743625
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8952563751028242
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9347408829174664
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8445055968214926
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8157123053956075
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8184088689781863
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7419797093501508
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8530298875788319
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8859336440910337
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9284343295859611
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7419797093501508
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28434329585961066
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17718672881820677
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09284343295859611
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7419797093501508
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8530298875788319
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8859336440910337
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9284343295859611
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8334906130922063
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8032139919307455
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8057146368194794
+      name: Cosine Map@100
+---
+
+# Custom Embedding Test - Anudit Nagar
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Alibaba-NLP/gte-base-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-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:** [Alibaba-NLP/gte-base-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5) <!-- at revision a8e4f3e0ee719c75bc30d12b8eae0f8440502718 -->
+- **Maximum Sequence Length:** 8192 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': 8192, 'do_lower_case': False}) with Transformer model: NewModel 
+  (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})
+)
+```
+
+## 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 = [
+    'Society tends to admire those who despair when others hope, viewing them as sages or wise figures.',
+    'What is often the societal perception of those who express pessimism about the future?',
+    'How did the realization about user engagement influence the app development strategy?',
+]
+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   | 0.7683     |
+| cosine_accuracy@3   | 0.8755     |
+| cosine_accuracy@5   | 0.9098     |
+| cosine_accuracy@10  | 0.9465     |
+| cosine_precision@1  | 0.7683     |
+| cosine_precision@3  | 0.2918     |
+| cosine_precision@5  | 0.182      |
+| cosine_precision@10 | 0.0947     |
+| cosine_recall@1     | 0.7683     |
+| cosine_recall@3     | 0.8755     |
+| cosine_recall@5     | 0.9098     |
+| cosine_recall@10    | 0.9465     |
+| cosine_ndcg@10      | 0.8567     |
+| cosine_mrr@10       | 0.8279     |
+| **cosine_map@100**  | **0.8302** |
+
+#### 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   | 0.7628     |
+| cosine_accuracy@3   | 0.87       |
+| cosine_accuracy@5   | 0.9062     |
+| cosine_accuracy@10  | 0.9463     |
+| cosine_precision@1  | 0.7628     |
+| cosine_precision@3  | 0.29       |
+| cosine_precision@5  | 0.1812     |
+| cosine_precision@10 | 0.0946     |
+| cosine_recall@1     | 0.7628     |
+| cosine_recall@3     | 0.87       |
+| cosine_recall@5     | 0.9062     |
+| cosine_recall@10    | 0.9463     |
+| cosine_ndcg@10      | 0.853      |
+| cosine_mrr@10       | 0.8232     |
+| **cosine_map@100**  | **0.8254** |
+
+#### 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   | 0.7628    |
+| cosine_accuracy@3   | 0.8684    |
+| cosine_accuracy@5   | 0.9016    |
+| cosine_accuracy@10  | 0.9419    |
+| cosine_precision@1  | 0.7628    |
+| cosine_precision@3  | 0.2895    |
+| cosine_precision@5  | 0.1803    |
+| cosine_precision@10 | 0.0942    |
+| cosine_recall@1     | 0.7628    |
+| cosine_recall@3     | 0.8684    |
+| cosine_recall@5     | 0.9016    |
+| cosine_recall@10    | 0.9419    |
+| cosine_ndcg@10      | 0.8507    |
+| cosine_mrr@10       | 0.8216    |
+| **cosine_map@100**  | **0.824** |
+
+#### 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   | 0.7573     |
+| cosine_accuracy@3   | 0.8634     |
+| cosine_accuracy@5   | 0.8953     |
+| cosine_accuracy@10  | 0.9347     |
+| cosine_precision@1  | 0.7573     |
+| cosine_precision@3  | 0.2878     |
+| cosine_precision@5  | 0.1791     |
+| cosine_precision@10 | 0.0935     |
+| cosine_recall@1     | 0.7573     |
+| cosine_recall@3     | 0.8634     |
+| cosine_recall@5     | 0.8953     |
+| cosine_recall@10    | 0.9347     |
+| cosine_ndcg@10      | 0.8445     |
+| cosine_mrr@10       | 0.8157     |
+| **cosine_map@100**  | **0.8184** |
+
+#### 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   | 0.742      |
+| cosine_accuracy@3   | 0.853      |
+| cosine_accuracy@5   | 0.8859     |
+| cosine_accuracy@10  | 0.9284     |
+| cosine_precision@1  | 0.742      |
+| cosine_precision@3  | 0.2843     |
+| cosine_precision@5  | 0.1772     |
+| cosine_precision@10 | 0.0928     |
+| cosine_recall@1     | 0.742      |
+| cosine_recall@3     | 0.853      |
+| cosine_recall@5     | 0.8859     |
+| cosine_recall@10    | 0.9284     |
+| cosine_ndcg@10      | 0.8335     |
+| cosine_mrr@10       | 0.8032     |
+| **cosine_map@100**  | **0.8057** |
+
+<!--
+## 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: 32,833 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: 3 tokens</li><li>mean: 34.54 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 16.78 tokens</li><li>max: 77 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                    | anchor                                                                                                           |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------|
+  | <code>The author saw taking risks as a necessary part of the creative process, and was willing to take risks in order to explore new ideas and themes.</code>                                                               | <code>What was the author's perspective on the importance of taking risks in creative work?</code>               |
+  | <code>Recognizing that older users are less likely to invite new users led to a strategic focus on younger demographics, prompting a shift in development efforts toward creating products that resonate with teens.</code> | <code>How did the realization about user engagement influence the app development strategy?</code>               |
+  | <code>The phrase emphasizes the fragility of Earth and our collective responsibility to protect it and ensure sustainable resource management for future generations.</code>                                                | <code>What is the significance of the phrase 'pale blue dot' in relation to environmental responsibility?</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`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 0.0002
+- `num_train_epochs`: 5
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `load_best_model_at_end`: True
+- `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`: 32
+- `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
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 0.0002
+- `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`: 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
+- `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
+- `eval_on_start`: False
+- `eval_use_gather_object`: 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 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.1558     | 10     | 0.7195        | -                      | -                      | -                      | -                     | -                      |
+| 0.3116     | 20     | 0.324         | -                      | -                      | -                      | -                     | -                      |
+| 0.4674     | 30     | 0.238         | -                      | -                      | -                      | -                     | -                      |
+| 0.6232     | 40     | 0.2265        | -                      | -                      | -                      | -                     | -                      |
+| 0.7790     | 50     | 0.1825        | -                      | -                      | -                      | -                     | -                      |
+| 0.9348     | 60     | 0.1938        | -                      | -                      | -                      | -                     | -                      |
+| **0.9971** | **64** | **-**         | **0.8054**             | **0.8198**             | **0.8276**             | **0.7796**            | **0.8329**             |
+| 1.0906     | 70     | 0.1397        | -                      | -                      | -                      | -                     | -                      |
+| 1.2463     | 80     | 0.0611        | -                      | -                      | -                      | -                     | -                      |
+| 1.4021     | 90     | 0.0506        | -                      | -                      | -                      | -                     | -                      |
+| 1.5579     | 100    | 0.047         | -                      | -                      | -                      | -                     | -                      |
+| 1.7137     | 110    | 0.0327        | -                      | -                      | -                      | -                     | -                      |
+| 1.8695     | 120    | 0.034         | -                      | -                      | -                      | -                     | -                      |
+| 1.9942     | 128    | -             | 0.8036                 | 0.8135                 | 0.8187                 | 0.7861                | 0.8243                 |
+| 2.0253     | 130    | 0.0319        | -                      | -                      | -                      | -                     | -                      |
+| 2.1811     | 140    | 0.0347        | -                      | -                      | -                      | -                     | -                      |
+| 2.3369     | 150    | 0.021         | -                      | -                      | -                      | -                     | -                      |
+| 2.4927     | 160    | 0.0169        | -                      | -                      | -                      | -                     | -                      |
+| 2.6485     | 170    | 0.0135        | -                      | -                      | -                      | -                     | -                      |
+| 2.8043     | 180    | 0.0123        | -                      | -                      | -                      | -                     | -                      |
+| 2.9601     | 190    | 0.0111        | -                      | -                      | -                      | -                     | -                      |
+| 2.9912     | 192    | -             | 0.8109                 | 0.8179                 | 0.8213                 | 0.7973                | 0.8264                 |
+| 3.1159     | 200    | 0.0083        | -                      | -                      | -                      | -                     | -                      |
+| 3.2717     | 210    | 0.0088        | -                      | -                      | -                      | -                     | -                      |
+| 3.4275     | 220    | 0.005         | -                      | -                      | -                      | -                     | -                      |
+| 3.5833     | 230    | 0.005         | -                      | -                      | -                      | -                     | -                      |
+| 3.7390     | 240    | 0.0043        | -                      | -                      | -                      | -                     | -                      |
+| 3.8948     | 250    | 0.0058        | -                      | -                      | -                      | -                     | -                      |
+| 3.9883     | 256    | -             | 0.8163                 | 0.8244                 | 0.8260                 | 0.8045                | 0.8287                 |
+| 4.0506     | 260    | 0.0057        | -                      | -                      | -                      | -                     | -                      |
+| 4.2064     | 270    | 0.0035        | -                      | -                      | -                      | -                     | -                      |
+| 4.3622     | 280    | 0.0033        | -                      | -                      | -                      | -                     | -                      |
+| 4.5180     | 290    | 0.0032        | -                      | -                      | -                      | -                     | -                      |
+| 4.6738     | 300    | 0.0031        | -                      | -                      | -                      | -                     | -                      |
+| 4.8296     | 310    | 0.0038        | -                      | -                      | -                      | -                     | -                      |
+| 4.9854     | 320    | 0.0042        | 0.8184                 | 0.8240                 | 0.8254                 | 0.8057                | 0.8302                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.5
+- Sentence Transformers: 3.0.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.0
+- Accelerate: 0.33.0
+- Datasets: 2.21.0
+- 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 +1,44 @@
+{
+  "_name_or_path": "Alibaba-NLP/gte-base-en-v1.5",
+  "architectures": [
+    "NewModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "rope",
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "ntk"
+  },
+  "rope_theta": 500000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 0,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 30528
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.44.2",
+    "pytorch": "2.4.0"
+  },
+  "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:aa8280e8c799e0e3acd77f0263ef9df6449c601d630fdd734bf422c5f5352daf
+size 547119128

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": 8192,
+  "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": 8192,
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93f7b36897bd6605d5c5db5bd2469f5e524cc3d49234bbcc23e781c26404414
+size 5496