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 +1,692 @@
+---
+language:
+- en
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:557850
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: microsoft/mpnet-base
+widget:
+- source_sentence: A man is jumping unto his filthy bed.
+  sentences:
+  - A young male is looking at a newspaper while 2 females walks past him.
+  - The bed is dirty.
+  - The man is on the moon.
+- source_sentence: A carefully balanced male stands on one foot near a clean ocean
+    beach area.
+  sentences:
+  - A man is ouside near the beach.
+  - Three policemen patrol the streets on bikes
+  - A man is sitting on his couch.
+- source_sentence: The man is wearing a blue shirt.
+  sentences:
+  - Near the trashcan the man stood and smoked
+  - A man in a blue shirt leans on a wall beside a road with a blue van and red car
+    with water in the background.
+  - A man in a black shirt is playing a guitar.
+- source_sentence: The girls are outdoors.
+  sentences:
+  - Two girls riding on an amusement part ride.
+  - a guy laughs while doing laundry
+  - Three girls are standing together in a room, one is listening, one is writing
+    on a wall and the third is talking to them.
+- source_sentence: A construction worker peeking out of a manhole while his coworker
+    sits on the sidewalk smiling.
+  sentences:
+  - A worker is looking out of a manhole.
+  - A man is giving a presentation.
+  - The workers are both inside the manhole.
+datasets:
+- sentence-transformers/all-nli
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+co2_eq_emissions:
+  emissions: 205.739032893975
+  energy_consumed: 0.5292975927419334
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
+  ram_total_size: 31.777088165283203
+  hours_used: 2.452
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: SentenceTransformer based on microsoft/mpnet-base
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 768
+      type: sts-dev-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8427806843466507
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8508672705970183
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 512
+      type: sts-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8402650019702758
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8492501196021981
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 256
+      type: sts-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8346871892249894
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8462852114011874
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 128
+      type: sts-dev-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8258126981506843
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8396442287070809
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev 64
+      type: sts-dev-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.8133510090549183
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8314093123007742
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 768
+      type: sts-test-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8189065344720828
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8358553875433253
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 512
+      type: sts-test-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8185683063331012
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8361687236813662
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 256
+      type: sts-test-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8129602938883278
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8332021961323041
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 128
+      type: sts-test-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8030325360463209
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.826154869627039
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test 64
+      type: sts-test-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.7903762214352186
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8193971659006509
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on microsoft/mpnet-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [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:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [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: MPNetModel 
+  (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("tomaarsen/mpnet-base-nli-matryoshka-reproduced")
+# Run inference
+sentences = [
+    'A construction worker peeking out of a manhole while his coworker sits on the sidewalk smiling.',
+    'A worker is looking out of a manhole.',
+    'The workers are both inside the manhole.',
+]
+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
+
+* Datasets: `sts-dev-768` and `sts-test-768`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | sts-dev-768 | sts-test-768 |
+|:--------------------|:------------|:-------------|
+| pearson_cosine      | 0.8428      | 0.8189       |
+| **spearman_cosine** | **0.8509**  | **0.8359**   |
+
+#### Semantic Similarity
+
+* Datasets: `sts-dev-512` and `sts-test-512`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 512
+  }
+  ```
+
+| Metric              | sts-dev-512 | sts-test-512 |
+|:--------------------|:------------|:-------------|
+| pearson_cosine      | 0.8403      | 0.8186       |
+| **spearman_cosine** | **0.8493**  | **0.8362**   |
+
+#### Semantic Similarity
+
+* Datasets: `sts-dev-256` and `sts-test-256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 256
+  }
+  ```
+
+| Metric              | sts-dev-256 | sts-test-256 |
+|:--------------------|:------------|:-------------|
+| pearson_cosine      | 0.8347      | 0.813        |
+| **spearman_cosine** | **0.8463**  | **0.8332**   |
+
+#### Semantic Similarity
+
+* Datasets: `sts-dev-128` and `sts-test-128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 128
+  }
+  ```
+
+| Metric              | sts-dev-128 | sts-test-128 |
+|:--------------------|:------------|:-------------|
+| pearson_cosine      | 0.8258      | 0.803        |
+| **spearman_cosine** | **0.8396**  | **0.8262**   |
+
+#### Semantic Similarity
+
+* Datasets: `sts-dev-64` and `sts-test-64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 64
+  }
+  ```
+
+| Metric              | sts-dev-64 | sts-test-64 |
+|:--------------------|:-----------|:------------|
+| pearson_cosine      | 0.8134     | 0.7904      |
+| **spearman_cosine** | **0.8314** | **0.8194**  |
+
+<!--
+## 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
+
+#### all-nli
+
+* Dataset: [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: 10.46 tokens</li><li>max: 46 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.81 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 5 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
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### all-nli
+
+* Dataset: [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: 17.95 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.78 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.35 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
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_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}
+- `tp_size`: 0
+- `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`: 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
+- `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 | Validation Loss | sts-dev-768_spearman_cosine | sts-dev-512_spearman_cosine | sts-dev-256_spearman_cosine | sts-dev-128_spearman_cosine | sts-dev-64_spearman_cosine | sts-test-768_spearman_cosine | sts-test-512_spearman_cosine | sts-test-256_spearman_cosine | sts-test-128_spearman_cosine | sts-test-64_spearman_cosine |
+|:------:|:-----:|:-------------:|:---------------:|:---------------------------:|:---------------------------:|:---------------------------:|:---------------------------:|:--------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|
+| 0.0459 | 1600  | 4.3243        | 1.5267          | 0.8525                      | 0.8475                      | 0.8438                      | 0.8356                      | 0.8155                     | -                            | -                            | -                            | -                            | -                           |
+| 0.0918 | 3200  | 2.4538        | 1.4448          | 0.8479                      | 0.8439                      | 0.8403                      | 0.8346                      | 0.8249                     | -                            | -                            | -                            | -                            | -                           |
+| 0.1377 | 4800  | 2.2829        | 1.5117          | 0.8507                      | 0.8481                      | 0.8429                      | 0.8348                      | 0.8203                     | -                            | -                            | -                            | -                            | -                           |
+| 0.1836 | 6400  | 2.0446        | 1.2684          | 0.8574                      | 0.8541                      | 0.8498                      | 0.8413                      | 0.8302                     | -                            | -                            | -                            | -                            | -                           |
+| 0.2294 | 8000  | 1.8867        | 1.3107          | 0.8452                      | 0.8423                      | 0.8400                      | 0.8352                      | 0.8255                     | -                            | -                            | -                            | -                            | -                           |
+| 0.2753 | 9600  | 1.747         | 1.1663          | 0.8456                      | 0.8420                      | 0.8384                      | 0.8292                      | 0.8229                     | -                            | -                            | -                            | -                            | -                           |
+| 0.3212 | 11200 | 1.6297        | 1.0809          | 0.8420                      | 0.8388                      | 0.8360                      | 0.8294                      | 0.8205                     | -                            | -                            | -                            | -                            | -                           |
+| 0.3671 | 12800 | 1.5974        | 1.0853          | 0.8374                      | 0.8352                      | 0.8310                      | 0.8264                      | 0.8184                     | -                            | -                            | -                            | -                            | -                           |
+| 0.4130 | 14400 | 1.5227        | 1.0440          | 0.8479                      | 0.8457                      | 0.8434                      | 0.8380                      | 0.8266                     | -                            | -                            | -                            | -                            | -                           |
+| 0.4589 | 16000 | 1.3835        | 1.0718          | 0.8365                      | 0.8341                      | 0.8310                      | 0.8258                      | 0.8172                     | -                            | -                            | -                            | -                            | -                           |
+| 0.5048 | 17600 | 1.3893        | 1.0140          | 0.8384                      | 0.8363                      | 0.8339                      | 0.8275                      | 0.8178                     | -                            | -                            | -                            | -                            | -                           |
+| 0.5507 | 19200 | 1.3203        | 1.0048          | 0.8418                      | 0.8400                      | 0.8364                      | 0.8292                      | 0.8204                     | -                            | -                            | -                            | -                            | -                           |
+| 0.5966 | 20800 | 1.2396        | 0.9407          | 0.8458                      | 0.8439                      | 0.8404                      | 0.8353                      | 0.8274                     | -                            | -                            | -                            | -                            | -                           |
+| 0.6425 | 22400 | 1.1842        | 0.9541          | 0.8435                      | 0.8404                      | 0.8384                      | 0.8335                      | 0.8257                     | -                            | -                            | -                            | -                            | -                           |
+| 0.6883 | 24000 | 1.1217        | 0.9000          | 0.8534                      | 0.8512                      | 0.8478                      | 0.8408                      | 0.8297                     | -                            | -                            | -                            | -                            | -                           |
+| 0.7342 | 25600 | 1.093         | 0.8731          | 0.8525                      | 0.8503                      | 0.8467                      | 0.8406                      | 0.8313                     | -                            | -                            | -                            | -                            | -                           |
+| 0.7801 | 27200 | 1.0609        | 0.8238          | 0.8528                      | 0.8510                      | 0.8469                      | 0.8399                      | 0.8312                     | -                            | -                            | -                            | -                            | -                           |
+| 0.8260 | 28800 | 0.9807        | 0.8264          | 0.8497                      | 0.8478                      | 0.8448                      | 0.8384                      | 0.8295                     | -                            | -                            | -                            | -                            | -                           |
+| 0.8719 | 30400 | 1.0061        | 0.8135          | 0.8455                      | 0.8439                      | 0.8405                      | 0.8338                      | 0.8256                     | -                            | -                            | -                            | -                            | -                           |
+| 0.9178 | 32000 | 0.9724        | 0.7965          | 0.8517                      | 0.8499                      | 0.8465                      | 0.8401                      | 0.8319                     | -                            | -                            | -                            | -                            | -                           |
+| 0.9637 | 33600 | 0.9057        | 0.7841          | 0.8509                      | 0.8493                      | 0.8463                      | 0.8396                      | 0.8314                     | -                            | -                            | -                            | -                            | -                           |
+| -1     | -1    | -             | -               | -                           | -                           | -                           | -                           | -                          | 0.8359                       | 0.8362                       | 0.8332                       | 0.8262                       | 0.8194                      |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.529 kWh
+- **Carbon Emitted**: 0.206 kg of CO2
+- **Hours Used**: 2.452 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
+- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
+- **RAM Size**: 31.78 GB
+
+### Framework Versions
+- Python: 3.11.6
+- Sentence Transformers: 4.1.0.dev0
+- Transformers: 4.51.1
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.5.1
+- Datasets: 3.3.2
+- Tokenizers: 0.21.1
+
+## 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 +1,23 @@
+{
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "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": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0.dev0",
+    "transformers": "4.51.1",
+    "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 sha256:6f9ae885f211bb899aba131650508fc53fa73eed9c2d92a72be690d0279d73fc
+size 437967672

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": false,
+    "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": false,
+    "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": false,
+    "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": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
+}