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 +1,739 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:6300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: nomic-ai/nomic-embed-text-v1.5
+widget:
+- source_sentence: What contributed to the increase in accounts receivable in 2023
+    compared to the previous year?
+  sentences:
+  - At December 31, 2023, Caterpillar’s consolidated net worth was $19.55 billion,
+    which was above the $9.00 billion required under the Credit Facility.
+  - Accounts receivable increased to $3,154 million at October 29, 2023 from $2,958
+    million at October 30, 2022, primarily due to revenue linearity, offset in part
+    by additional receivables sold through factoring arrangements.
+  - The EU adopted the Carbon Border Adjustment Mechanism (CBAM), which subjects certain
+    imported materials such as iron, steel, and aluminum, to a carbon levy linked
+    to the carbon price payable on domestic goods under the European Trading Scheme.
+    The CBAM could increase costs of importing such materials and/or limit the ability
+    to import lower cost materials from non-EU countries.
+- source_sentence: What primarily constituted marketing expenses for the year ended
+    December 31, 2025?
+  sentences:
+  - This is the world’s first liquefied natural gas (LNG) plant supplied with associated
+    gas, where the natural gas is a byproduct of crude oil production.
+  - Marketing expenses consist primarily of advertising expenses and certain payments
+    made to our marketing and advertising sales partners.
+  - In January 2024, the CFPB proposed a rule that could significantly restrict bank
+    overdraft fees.
+- source_sentence: What is the total cash flow from operating activities for Airbnb,
+    Inc. in 2023?
+  sentences:
+  - Net cash provided by operating activities | 2,313 | | 3,430 | | 3,884
+  - Under ASO contracts, self-funded employers generally retain the risk of financing
+    the costs of health benefits, with large group customers retaining a greater share
+    and small group customers a smaller share of the cost of health benefits.
+  - Of the $2.2 billion in revenue that we generated in 2023, 55% came from customers
+    in the government segment, and 45% came from customers in the commercial segment.
+- source_sentence: What major legislative act mentioned in the text was enacted by
+    the U.S. government on August 16, 2022?
+  sentences:
+  - In July 2022, the borrowing capacity under the back-up facilities expanded from
+    $3.0 billion to $5.0 billion.
+  - The Company manages its investment portfolio to limit its exposure to any one
+    issuer or market sector, and largely limits its investments to investmententious
+    grade quality.
+  - On August 16, 2022, the U.S. government enacted the Inflation Reduction Act of
+    2022.
+- source_sentence: What is the maximum duration for patent term restoration for pharmaceutical
+    products in the U.S.?
+  sentences:
+  - Patent term restoration for a single patent for a pharmaceutical product is provided
+    to U.S. patent holders to compensate for a portion of the time invested in clinical
+    trials and the U.S. Food and Drug Administration (FDA). There is a five-year cap
+    on any restoration, and no patent's expiration date may be extended beyond 14
+    years from FDA approval.
+  - Using AI technologies, our Tax Advisor offering leverages information generated
+    from our ProConnect Tax Online and Lacerte offerings to enable year-round tax
+    planning services and communicate tax savings strategies to clients.
+  - In 2023, catastrophe losses were primarily due to U.S. flooding, hail, tornadoes,
+    and wind events.
+pipeline_tag: sentence-similarity
+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
+model-index:
+- name: nomic 1.5 base Financial Matryoshka
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7285714285714285
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8514285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8885714285714286
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.92
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7285714285714285
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28380952380952384
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17771428571428569
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09199999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7285714285714285
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8514285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8885714285714286
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.92
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.82688931465871
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7967777777777774
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8005981271078951
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7142857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8414285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8857142857142857
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9214285714285714
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7142857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2804761904761905
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17714285714285713
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09214285714285714
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7142857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8414285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8857142857142857
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9214285714285714
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8200375337187854
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7872664399092969
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7910342395417198
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7014285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8385714285714285
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.88
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9242857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7014285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2795238095238095
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.176
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09242857142857142
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7014285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8385714285714285
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.88
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9242857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8144449051665447
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7791428571428568
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7827133843260672
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7071428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8342857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8742857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9242857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7071428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2780952380952381
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17485714285714282
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09242857142857142
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7071428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8342857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8742857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9242857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8164938269316206
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.78222052154195
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7855606408045326
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.67
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8085714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8514285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8985714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.67
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26952380952380955
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17028571428571426
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08985714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.67
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8085714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8514285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8985714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7841742147445607
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7477647392290245
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7519306451620806
+      name: Cosine Map@100
+---
+
+# nomic 1.5 base Financial Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) on the json 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:** [nomic-ai/nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) <!-- at revision ac6fcd72429d86ff25c17895e47a9bfcfc50c1b2 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **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: NomicBertModel 
+  (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("CatSchroedinger/nomic-v1.5-financial-matryoshka")
+# Run inference
+sentences = [
+    'What is the maximum duration for patent term restoration for pharmaceutical products in the U.S.?',
+    "Patent term restoration for a single patent for a pharmaceutical product is provided to U.S. patent holders to compensate for a portion of the time invested in clinical trials and the U.S. Food and Drug Administration (FDA). There is a five-year cap on any restoration, and no patent's expiration date may be extended beyond 14 years from FDA approval.",
+    'Using AI technologies, our Tax Advisor offering leverages information generated from our ProConnect Tax Online and Lacerte offerings to enable year-round tax planning services and communicate tax savings strategies to clients.',
+]
+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
+
+* Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | dim_768    | dim_512  | dim_256    | dim_128    | dim_64     |
+|:--------------------|:-----------|:---------|:-----------|:-----------|:-----------|
+| cosine_accuracy@1   | 0.7286     | 0.7143   | 0.7014     | 0.7071     | 0.67       |
+| cosine_accuracy@3   | 0.8514     | 0.8414   | 0.8386     | 0.8343     | 0.8086     |
+| cosine_accuracy@5   | 0.8886     | 0.8857   | 0.88       | 0.8743     | 0.8514     |
+| cosine_accuracy@10  | 0.92       | 0.9214   | 0.9243     | 0.9243     | 0.8986     |
+| cosine_precision@1  | 0.7286     | 0.7143   | 0.7014     | 0.7071     | 0.67       |
+| cosine_precision@3  | 0.2838     | 0.2805   | 0.2795     | 0.2781     | 0.2695     |
+| cosine_precision@5  | 0.1777     | 0.1771   | 0.176      | 0.1749     | 0.1703     |
+| cosine_precision@10 | 0.092      | 0.0921   | 0.0924     | 0.0924     | 0.0899     |
+| cosine_recall@1     | 0.7286     | 0.7143   | 0.7014     | 0.7071     | 0.67       |
+| cosine_recall@3     | 0.8514     | 0.8414   | 0.8386     | 0.8343     | 0.8086     |
+| cosine_recall@5     | 0.8886     | 0.8857   | 0.88       | 0.8743     | 0.8514     |
+| cosine_recall@10    | 0.92       | 0.9214   | 0.9243     | 0.9243     | 0.8986     |
+| **cosine_ndcg@10**  | **0.8269** | **0.82** | **0.8144** | **0.8165** | **0.7842** |
+| cosine_mrr@10       | 0.7968     | 0.7873   | 0.7791     | 0.7822     | 0.7478     |
+| cosine_map@100      | 0.8006     | 0.791    | 0.7827     | 0.7856     | 0.7519     |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 6,300 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                           |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 20.49 tokens</li><li>max: 51 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 45.72 tokens</li><li>max: 687 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                               | positive                                                                                                                                                                                 |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>What limitations are associated with using non-GAAP financial measures such as contribution margin and adjusted income from operations?</code> | <code>Further, these metrics have certain limitations, as they do not include the impact of certain expenses that are reflected in our consolidated statements of operations.</code>     |
+  | <code>What type of firm is PricewaterhouseCoopers LLP as mentioned in the financial statements?</code>                                               | <code>PricewaterhouseCoopers LLP, mentioned as the independent registered public accounting firm with PCAOB ID 238, prepared the report on the consolidated financial statements.</code> |
+  | <code>What pages contain the financial Statements and Supplementary Data in IBM's 2023 Annual Report?</code>                                         | <code>The Financial Statements and Supplementary Data for IBM's 2023 Annual Report are found on pages 44 through 121.</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`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 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`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `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`: False
+- `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`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch   | Step   | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.8122  | 10     | 11.5729       | -                      | -                      | -                      | -                      | -                     |
+| 1.0     | 13     | -             | 0.7995                 | 0.7976                 | 0.7929                 | 0.7889                 | 0.7646                |
+| 1.5685  | 20     | 3.4999        | -                      | -                      | -                      | -                      | -                     |
+| 2.0     | 26     | -             | 0.8207                 | 0.8189                 | 0.8099                 | 0.8090                 | 0.7825                |
+| 2.3249  | 30     | 2.8578        | -                      | -                      | -                      | -                      | -                     |
+| **3.0** | **39** | **-**         | **0.8267**             | **0.8218**             | **0.8151**             | **0.8168**             | **0.7826**            |
+| 3.0812  | 40     | 2.0904        | -                      | -                      | -                      | -                      | -                     |
+| 3.7310  | 48     | -             | 0.8269                 | 0.8200                 | 0.8144                 | 0.8165                 | 0.7842                |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.5
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.2
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.3.0
+- Datasets: 2.19.1
+- Tokenizers: 0.21.0
+
+## 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 +1,58 @@
+{
+  "_name_or_path": "nomic-ai/nomic-embed-text-v1.5",
+  "activation_function": "swiglu",
+  "architectures": [
+    "NomicBertModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "nomic-ai/nomic-bert-2048--configuration_hf_nomic_bert.NomicBertConfig",
+    "AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
+    "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining"
+  },
+  "bos_token_id": null,
+  "causal": false,
+  "dense_seq_output": true,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "fused_bias_fc": true,
+  "fused_dropout_add_ln": true,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-12,
+  "max_trained_positions": 2048,
+  "mlp_fc1_bias": false,
+  "mlp_fc2_bias": false,
+  "model_type": "nomic_bert",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 8192,
+  "pad_vocab_size_multiple": 64,
+  "parallel_block": false,
+  "parallel_block_tied_norm": false,
+  "prenorm": false,
+  "qkv_proj_bias": false,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_emb_base": 1000,
+  "rotary_emb_fraction": 1.0,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "rotary_scaling_factor": null,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "use_flash_attn": true,
+  "use_rms_norm": false,
+  "use_xentropy": true,
+  "vocab_size": 30528
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.2",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60eaf75516b03cdf9ef97bf657225afe452d61200008b00e6293171db4af4aa1
+size 546938168

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 +1,56 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}