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 +1,615 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:360886
+- loss:CoSENTLoss
+base_model: sentence-transformers/all-mpnet-base-v2
+widget:
+- source_sentence: '|Immunosuppressant drug therapy (procedure)| : { |Method (attribute)|
+    = |Administration - action (qualifier value)|, |Direct substance (attribute)|
+    = |Auranofin (substance)| }, { |Has intent (attribute)| = |Therapeutic intent
+    (qualifier value)| }'
+  sentences:
+  - Tofacitinib therapy (procedure)
+  - Mural thrombus of right ventricle following acute myocardial infarction (disorder)
+  - Neonatal botulism (disorder)
+- source_sentence: '|Injury of finger of left hand (disorder)| + |Traumatic blister
+    of index finger (disorder)| + |Traumatic blister of left hand (disorder)| : {
+    |Finding site (attribute)| = |Skin structure of left index finger (body structure)|,
+    |Associated morphology (attribute)| = |Blister (morphologic abnormality)| }, {
+    |Due to (attribute)| = |Traumatic event (event)| }'
+  sentences:
+  - Cardiovascular system closure (procedure)
+  - Entire skin of lower eyelid and periocular area (body structure)
+  - Avulsion of nail unit of left little finger (disorder)
+- source_sentence: '|Evaluation finding (finding)| : { |Interprets (attribute)| =
+    |Interferon gamma assay (procedure)|, |Has interpretation (attribute)| = |Positive
+    (qualifier value)| }'
+  sentences:
+  - Gleason pattern (observable entity)
+  - Interferon gamma assay positive (finding)
+  - Intentional melphalan overdose (disorder)
+- source_sentence: '|Finding of specific antibody level (finding)| : { |Interprets
+    (attribute)| = |Measurement of viral antibody (procedure)| }'
+  sentences:
+  - Lyme detected by immunoblot (finding)
+  - Primary malignant neoplasm of accessory sinus (disorder)
+  - Perfusion of lymphatics with hyperthermia (procedure)
+- source_sentence: '|Neoplasm of anterior wall of nasopharynx (disorder)| + |Neoplasm
+    of uncertain behavior of nasopharynx (disorder)| : { |Finding site (attribute)|
+    = |Structure of anterior wall of nasopharynx (body structure)|, |Associated morphology
+    (attribute)| = |Neoplasm of uncertain behavior (morphologic abnormality)| }'
+  sentences:
+  - Secondary angle-closure glaucoma - synechial (disorder)
+  - Neoplasm of uncertain behavior of lateral wall of nasopharynx (disorder)
+  - Product containing precisely cefamandole (as cefamandole nafate) 1 gram/1 vial
+    powder for conventional release solution for injection (clinical drug)
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.9048593944190657
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8556279874385214
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on the csv 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:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 9a3225965996d404b775526de6dbfe85d3368642 -->
+- **Maximum Sequence Length:** 384 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - csv
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 384, '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})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("yyzheng00/all-mpnet-base-v2_snomed_expression")
+# Run inference
+sentences = [
+    '|Neoplasm of anterior wall of nasopharynx (disorder)| + |Neoplasm of uncertain behavior of nasopharynx (disorder)| : { |Finding site (attribute)| = |Structure of anterior wall of nasopharynx (body structure)|, |Associated morphology (attribute)| = |Neoplasm of uncertain behavior (morphologic abnormality)| }',
+    'Neoplasm of uncertain behavior of lateral wall of nasopharynx (disorder)',
+    'Secondary angle-closure glaucoma - synechial (disorder)',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Dataset: `sts-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.9049     |
+| **spearman_cosine** | **0.8556** |
+
+<!--
+## 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
+
+#### csv
+
+* Dataset: csv
+* Size: 360,886 training samples
+* Columns: <code>text_a</code>, <code>text_b</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text_a                                                                               | text_b                                                                            | label                                           |
+  |:--------|:-------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                               | string                                                                            | int                                             |
+  | details | <ul><li>min: 28 tokens</li><li>mean: 101.13 tokens</li><li>max: 357 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 15.29 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>0: ~51.40%</li><li>1: ~48.60%</li></ul> |
+* Samples:
+  | text_a                                                                                                                                                                                                                                                                                                                                                                        | text_b                                                                      | label          |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------|:---------------|
+  | <code>|Risk assessment (procedure)| : { |Method (attribute)| = |Evaluation - action (qualifier value)| }, { |Has focus (attribute)| = |At increased risk of ineffective tissue perfusion (finding)| }</code>                                                                                                                                                                  | <code>Assessment of risk of ineffective tissue perfusion (procedure)</code> | <code>1</code> |
+  | <code>|Chronic inflammatory disorder (disorder)| + |Chronic nervous system disorder (disorder)| + |Meningitis (disorder)| : { |Finding site (attribute)| = |Meninges structure (body structure)|, |Associated morphology (attribute)| = |Chronic inflammatory morphology (morphologic abnormality)| }, { |Clinical course (attribute)| = |Chronic (qualifier value)| }</code> | <code>Chronic meningitis (disorder)</code>                                  | <code>1</code> |
+  | <code>|Imaging of head (procedure)| + |Ultrasound procedure on topographic region (procedure)| : { |Method (attribute)| = |Ultrasound imaging - action (qualifier value)|, |Procedure site - Direct (attribute)| = |Head structure (body structure)| }</code>                                                                                                                 | <code>Imaging of brain (procedure)</code>                                   | <code>0</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### csv
+
+* Dataset: csv
+* Size: 360,886 evaluation samples
+* Columns: <code>text_a</code>, <code>text_b</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text_a                                                                               | text_b                                                                            | label                                           |
+  |:--------|:-------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                               | string                                                                            | int                                             |
+  | details | <ul><li>min: 25 tokens</li><li>mean: 101.18 tokens</li><li>max: 366 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 15.21 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>0: ~51.30%</li><li>1: ~48.70%</li></ul> |
+* Samples:
+  | text_a                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | text_b                                                                                           | label          |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:---------------|
+  | <code>|Disorder of fetal abdominal region (disorder)| + |Fetal genitourinary abnormality (disorder)| + |Kidney disease (disorder)| : { |Occurrence (attribute)| = |Fetal period (qualifier value)|, |Finding site (attribute)| = |Kidney structure (body structure)|, |Associated morphology (attribute)| = |Morphologically abnormal structure (morphologic abnormality)|, |Pathological process (attribute)| = |Pathological developmental process (qualifier value)| }</code>                                                                                                                                                                                                                                                                                                                                          | <code>Early urethral obstruction sequence (disorder)</code>                                      | <code>0</code> |
+  | <code>|Computed tomography of pelvis for brachytherapy planning (procedure)| + |Computed tomography of prostate for radiotherapy planning (procedure)| : { |Has focus (attribute)| = |Treatment planning for brachytherapy (procedure)| }, { |Method (attribute)| = |Computed tomography imaging - action (qualifier value)|, |Procedure site - Direct (attribute)| = |Prostatic structure (body structure)| }</code>                                                                                                                                                                                                                                                                                                                                                                                                     | <code>Computed tomography of prostate with contrast for radiotherapy planning (procedure)</code> | <code>0</code> |
+  | <code>|Product containing only hydroxyzine in oral dose form (medicinal product form)| : |Has manufactured dose form (attribute)| = |Conventional release oral capsule (dose form)|, |Has unit of presentation (attribute)| = |Capsule (unit of presentation)|, |Count of base of active ingredient (attribute)| = #1, { |Has precise active ingredient (attribute)| = |Hydroxyzine pamoate (substance)|, |Has basis of strength substance (attribute)| = |Hydroxyzine pamoate (substance)|, |Has presentation strength numerator value (attribute)| = #100, |Has presentation strength numerator unit (attribute)| = |milligram (qualifier value)|, |Has presentation strength denominator value (attribute)| = #1, |Has presentation strength denominator unit (attribute)| = |Capsule (unit of presentation)| }</code> | <code>Hydroxyzine pamoate 100mg capsule (product)</code>                                         | <code>1</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### 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}
+- `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
+- `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
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step  | Training Loss | Validation Loss | sts-dev_spearman_cosine |
+|:------:|:-----:|:-------------:|:---------------:|:-----------------------:|
+| 0.0055 | 100   | 5.2922        | 3.9427          | 0.6159                  |
+| 0.0111 | 200   | 3.2766        | 2.8638          | 0.7437                  |
+| 0.0166 | 300   | 2.8445        | 2.4816          | 0.7833                  |
+| 0.0222 | 400   | 2.5209        | 2.2995          | 0.7974                  |
+| 0.0277 | 500   | 2.5298        | 2.1033          | 0.8072                  |
+| 0.0333 | 600   | 2.0427        | 2.1055          | 0.8114                  |
+| 0.0388 | 700   | 2.1367        | 2.0634          | 0.8121                  |
+| 0.0443 | 800   | 2.2486        | 1.7848          | 0.8210                  |
+| 0.0499 | 900   | 1.921         | 1.9666          | 0.8190                  |
+| 0.0554 | 1000  | 1.9962        | 1.9688          | 0.8180                  |
+| 0.0610 | 1100  | 1.5203        | 2.0695          | 0.8187                  |
+| 0.0665 | 1200  | 2.0616        | 1.7060          | 0.8223                  |
+| 0.0720 | 1300  | 2.0793        | 1.8158          | 0.8254                  |
+| 0.0776 | 1400  | 2.0766        | 1.8549          | 0.8213                  |
+| 0.0831 | 1500  | 1.5608        | 1.8045          | 0.8241                  |
+| 0.0887 | 1600  | 1.7671        | 1.9724          | 0.8196                  |
+| 0.0942 | 1700  | 2.1665        | 2.2623          | 0.8033                  |
+| 0.0998 | 1800  | 1.9596        | 1.8070          | 0.8224                  |
+| 0.1053 | 1900  | 1.5704        | 1.8142          | 0.8265                  |
+| 0.1108 | 2000  | 2.0749        | 2.0596          | 0.8205                  |
+| 0.1164 | 2100  | 1.9445        | 1.7458          | 0.8279                  |
+| 0.1219 | 2200  | 1.6043        | 2.0309          | 0.8242                  |
+| 0.1275 | 2300  | 1.5723        | 1.7440          | 0.8286                  |
+| 0.1330 | 2400  | 1.7905        | 1.5584          | 0.8319                  |
+| 0.1385 | 2500  | 2.0777        | 1.7437          | 0.8254                  |
+| 0.1441 | 2600  | 1.7563        | 1.6852          | 0.8322                  |
+| 0.1496 | 2700  | 1.6565        | 1.8196          | 0.8268                  |
+| 0.1552 | 2800  | 1.5064        | 1.6763          | 0.8302                  |
+| 0.1607 | 2900  | 1.9221        | 1.7317          | 0.8279                  |
+| 0.1663 | 3000  | 1.7803        | 1.8330          | 0.8225                  |
+| 0.1718 | 3100  | 1.3559        | 1.9419          | 0.8278                  |
+| 0.1773 | 3200  | 1.5309        | 1.5263          | 0.8345                  |
+| 0.1829 | 3300  | 1.6429        | 1.7952          | 0.8290                  |
+| 0.1884 | 3400  | 1.4676        | 1.8284          | 0.8270                  |
+| 0.1940 | 3500  | 1.5167        | 1.6084          | 0.8295                  |
+| 0.1995 | 3600  | 1.7605        | 1.6362          | 0.8334                  |
+| 0.2050 | 3700  | 1.6812        | 1.4205          | 0.8348                  |
+| 0.2106 | 3800  | 1.4537        | 1.6432          | 0.8341                  |
+| 0.2161 | 3900  | 1.6718        | 1.2594          | 0.8382                  |
+| 0.2217 | 4000  | 1.3892        | 1.4798          | 0.8351                  |
+| 0.2272 | 4100  | 1.7261        | 1.3948          | 0.8354                  |
+| 0.2328 | 4200  | 1.6611        | 1.4519          | 0.8368                  |
+| 0.2383 | 4300  | 1.3181        | 1.2844          | 0.8389                  |
+| 0.2438 | 4400  | 1.4356        | 1.3015          | 0.8392                  |
+| 0.2494 | 4500  | 1.4077        | 1.3217          | 0.8381                  |
+| 0.2549 | 4600  | 1.2534        | 1.5767          | 0.8340                  |
+| 0.2605 | 4700  | 1.6881        | 1.2737          | 0.8398                  |
+| 0.2660 | 4800  | 1.4572        | 1.2570          | 0.8408                  |
+| 0.2715 | 4900  | 1.2339        | 1.1919          | 0.8423                  |
+| 0.2771 | 5000  | 1.2871        | 1.3166          | 0.8398                  |
+| 0.2826 | 5100  | 1.3532        | 1.4045          | 0.8360                  |
+| 0.2882 | 5200  | 1.2731        | 1.4843          | 0.8384                  |
+| 0.2937 | 5300  | 1.3776        | 1.1347          | 0.8423                  |
+| 0.2993 | 5400  | 1.2179        | 1.5040          | 0.8373                  |
+| 0.3048 | 5500  | 1.41          | 1.2401          | 0.8418                  |
+| 0.3103 | 5600  | 1.3901        | 1.1494          | 0.8416                  |
+| 0.3159 | 5700  | 1.4007        | 1.2487          | 0.8414                  |
+| 0.3214 | 5800  | 1.3444        | 1.4062          | 0.8397                  |
+| 0.3270 | 5900  | 1.3671        | 1.3194          | 0.8410                  |
+| 0.3325 | 6000  | 1.2401        | 1.2642          | 0.8411                  |
+| 0.3380 | 6100  | 1.4102        | 1.3317          | 0.8392                  |
+| 0.3436 | 6200  | 1.1672        | 1.0846          | 0.8438                  |
+| 0.3491 | 6300  | 1.3595        | 1.2747          | 0.8387                  |
+| 0.3547 | 6400  | 1.0956        | 1.4071          | 0.8392                  |
+| 0.3602 | 6500  | 1.539         | 1.2683          | 0.8413                  |
+| 0.3658 | 6600  | 1.3078        | 1.2173          | 0.8430                  |
+| 0.3713 | 6700  | 1.3562        | 1.0733          | 0.8447                  |
+| 0.3768 | 6800  | 1.3009        | 1.3561          | 0.8408                  |
+| 0.3824 | 6900  | 1.4319        | 1.1958          | 0.8432                  |
+| 0.3879 | 7000  | 1.0702        | 1.1325          | 0.8437                  |
+| 0.3935 | 7100  | 1.2339        | 0.9852          | 0.8465                  |
+| 0.3990 | 7200  | 0.8772        | 1.2658          | 0.8419                  |
+| 0.4045 | 7300  | 1.3411        | 1.1585          | 0.8438                  |
+| 0.4101 | 7400  | 1.1518        | 1.1572          | 0.8439                  |
+| 0.4156 | 7500  | 1.0287        | 0.9960          | 0.8456                  |
+| 0.4212 | 7600  | 1.2913        | 1.1595          | 0.8437                  |
+| 0.4267 | 7700  | 1.1006        | 1.1575          | 0.8437                  |
+| 0.4323 | 7800  | 1.3463        | 1.0478          | 0.8459                  |
+| 0.4378 | 7900  | 1.0428        | 1.0495          | 0.8461                  |
+| 0.4433 | 8000  | 1.0657        | 1.0442          | 0.8465                  |
+| 0.4489 | 8100  | 1.1002        | 1.0223          | 0.8475                  |
+| 0.4544 | 8200  | 1.1596        | 1.0066          | 0.8474                  |
+| 0.4600 | 8300  | 1.3218        | 1.0403          | 0.8460                  |
+| 0.4655 | 8400  | 1.1482        | 1.1177          | 0.8457                  |
+| 0.4710 | 8500  | 1.0033        | 1.1743          | 0.8448                  |
+| 0.4766 | 8600  | 1.0772        | 1.1071          | 0.8464                  |
+| 0.4821 | 8700  | 0.775         | 1.2731          | 0.8438                  |
+| 0.4877 | 8800  | 0.8859        | 0.9293          | 0.8491                  |
+| 0.4932 | 8900  | 0.7837        | 1.0760          | 0.8462                  |
+| 0.4988 | 9000  | 0.7768        | 1.0135          | 0.8470                  |
+| 0.5043 | 9100  | 1.0103        | 0.9691          | 0.8477                  |
+| 0.5098 | 9200  | 1.0219        | 1.2059          | 0.8441                  |
+| 0.5154 | 9300  | 0.9093        | 1.0895          | 0.8461                  |
+| 0.5209 | 9400  | 1.0176        | 0.9229          | 0.8489                  |
+| 0.5265 | 9500  | 1.3811        | 0.9470          | 0.8483                  |
+| 0.5320 | 9600  | 0.8338        | 1.0048          | 0.8477                  |
+| 0.5375 | 9700  | 0.7105        | 1.0591          | 0.8464                  |
+| 0.5431 | 9800  | 1.0313        | 0.9789          | 0.8482                  |
+| 0.5486 | 9900  | 1.0308        | 0.8741          | 0.8499                  |
+| 0.5542 | 10000 | 0.7353        | 0.9419          | 0.8482                  |
+| 0.5597 | 10100 | 0.7683        | 1.0695          | 0.8473                  |
+| 0.5653 | 10200 | 1.1728        | 0.9705          | 0.8494                  |
+| 0.5708 | 10300 | 0.8578        | 0.9633          | 0.8493                  |
+| 0.5763 | 10400 | 1.0095        | 0.7799          | 0.8514                  |
+| 0.5819 | 10500 | 1.0157        | 1.0333          | 0.8485                  |
+| 0.5874 | 10600 | 0.8164        | 0.8596          | 0.8509                  |
+| 0.5930 | 10700 | 0.9278        | 0.8256          | 0.8516                  |
+| 0.5985 | 10800 | 0.5919        | 1.0104          | 0.8493                  |
+| 0.6040 | 10900 | 0.6931        | 0.9957          | 0.8492                  |
+| 0.6096 | 11000 | 1.1545        | 0.9758          | 0.8494                  |
+| 0.6151 | 11100 | 1.1061        | 1.0360          | 0.8493                  |
+| 0.6207 | 11200 | 0.7954        | 0.9362          | 0.8509                  |
+| 0.6262 | 11300 | 0.6365        | 0.9504          | 0.8511                  |
+| 0.6318 | 11400 | 0.992         | 0.8553          | 0.8521                  |
+| 0.6373 | 11500 | 0.6971        | 0.8763          | 0.8520                  |
+| 0.6428 | 11600 | 0.8162        | 0.9527          | 0.8504                  |
+| 0.6484 | 11700 | 0.8973        | 0.8722          | 0.8519                  |
+| 0.6539 | 11800 | 0.7652        | 0.9417          | 0.8510                  |
+| 0.6595 | 11900 | 0.7305        | 0.8955          | 0.8519                  |
+| 0.6650 | 12000 | 0.8555        | 0.9007          | 0.8510                  |
+| 0.6705 | 12100 | 0.7165        | 0.7924          | 0.8530                  |
+| 0.6761 | 12200 | 0.7939        | 0.8607          | 0.8516                  |
+| 0.6816 | 12300 | 0.9873        | 0.7780          | 0.8533                  |
+| 0.6872 | 12400 | 0.7197        | 0.9380          | 0.8508                  |
+| 0.6927 | 12500 | 1.076         | 0.8041          | 0.8531                  |
+| 0.6983 | 12600 | 0.6853        | 0.8800          | 0.8517                  |
+| 0.7038 | 12700 | 0.9403        | 0.8181          | 0.8527                  |
+| 0.7093 | 12800 | 0.8598        | 0.7641          | 0.8536                  |
+| 0.7149 | 12900 | 0.628         | 0.7479          | 0.8540                  |
+| 0.7204 | 13000 | 1.0517        | 0.7611          | 0.8536                  |
+| 0.7260 | 13100 | 0.5099        | 0.8426          | 0.8521                  |
+| 0.7315 | 13200 | 0.751         | 0.8133          | 0.8526                  |
+| 0.7370 | 13300 | 0.572         | 0.8344          | 0.8524                  |
+| 0.7426 | 13400 | 0.8213        | 0.7869          | 0.8528                  |
+| 0.7481 | 13500 | 0.6046        | 0.7810          | 0.8528                  |
+| 0.7537 | 13600 | 0.7211        | 0.7502          | 0.8537                  |
+| 0.7592 | 13700 | 0.7443        | 0.7398          | 0.8538                  |
+| 0.7648 | 13800 | 0.6644        | 0.8257          | 0.8529                  |
+| 0.7703 | 13900 | 0.8948        | 0.7271          | 0.8536                  |
+| 0.7758 | 14000 | 0.6886        | 0.7607          | 0.8531                  |
+| 0.7814 | 14100 | 0.8322        | 0.7143          | 0.8540                  |
+| 0.7869 | 14200 | 0.6965        | 0.7270          | 0.8540                  |
+| 0.7925 | 14300 | 0.6478        | 0.7368          | 0.8541                  |
+| 0.7980 | 14400 | 0.6877        | 0.7690          | 0.8532                  |
+| 0.8035 | 14500 | 0.6289        | 0.7316          | 0.8538                  |
+| 0.8091 | 14600 | 0.9058        | 0.6514          | 0.8548                  |
+| 0.8146 | 14700 | 0.5971        | 0.6980          | 0.8542                  |
+| 0.8202 | 14800 | 0.5774        | 0.7124          | 0.8539                  |
+| 0.8257 | 14900 | 0.6134        | 0.7480          | 0.8534                  |
+| 0.8313 | 15000 | 0.6962        | 0.6284          | 0.8551                  |
+| 0.8368 | 15100 | 0.5934        | 0.7099          | 0.8540                  |
+| 0.8423 | 15200 | 0.7791        | 0.6925          | 0.8542                  |
+| 0.8479 | 15300 | 0.5418        | 0.6774          | 0.8544                  |
+| 0.8534 | 15400 | 0.7526        | 0.6380          | 0.8552                  |
+| 0.8590 | 15500 | 0.694         | 0.6967          | 0.8543                  |
+| 0.8645 | 15600 | 0.5813        | 0.6864          | 0.8543                  |
+| 0.8700 | 15700 | 0.726         | 0.6325          | 0.8552                  |
+| 0.8756 | 15800 | 0.5094        | 0.6491          | 0.8549                  |
+| 0.8811 | 15900 | 0.5728        | 0.6549          | 0.8549                  |
+| 0.8867 | 16000 | 0.5272        | 0.6723          | 0.8548                  |
+| 0.8922 | 16100 | 0.6896        | 0.6786          | 0.8546                  |
+| 0.8978 | 16200 | 0.5666        | 0.6629          | 0.8550                  |
+| 0.9033 | 16300 | 0.7312        | 0.6801          | 0.8549                  |
+| 0.9088 | 16400 | 0.6451        | 0.6779          | 0.8549                  |
+| 0.9144 | 16500 | 0.6572        | 0.6374          | 0.8556                  |
+| 0.9199 | 16600 | 0.5052        | 0.6672          | 0.8551                  |
+| 0.9255 | 16700 | 0.5395        | 0.6686          | 0.8550                  |
+| 0.9310 | 16800 | 0.4715        | 0.6840          | 0.8547                  |
+| 0.9365 | 16900 | 0.7149        | 0.6576          | 0.8552                  |
+| 0.9421 | 17000 | 0.5066        | 0.6533          | 0.8553                  |
+| 0.9476 | 17100 | 0.6382        | 0.6509          | 0.8552                  |
+| 0.9532 | 17200 | 0.5585        | 0.6729          | 0.8550                  |
+| 0.9587 | 17300 | 0.5953        | 0.6505          | 0.8554                  |
+| 0.9643 | 17400 | 0.3545        | 0.6487          | 0.8555                  |
+| 0.9698 | 17500 | 0.8031        | 0.6451          | 0.8555                  |
+| 0.9753 | 17600 | 0.8531        | 0.6366          | 0.8557                  |
+| 0.9809 | 17700 | 0.7154        | 0.6365          | 0.8557                  |
+| 0.9864 | 17800 | 0.3339        | 0.6339          | 0.8557                  |
+| 0.9920 | 17900 | 0.5858        | 0.6410          | 0.8556                  |
+| 0.9975 | 18000 | 0.7509        | 0.6400          | 0.8556                  |
+
+</details>
+
+### Framework Versions
+- Python: 3.11.1
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.0
+- PyTorch: 2.1.1+cu121
+- Accelerate: 1.2.0
+- Datasets: 2.18.0
+- 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",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## 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 +1,24 @@
+{
+  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "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": "4.47.0",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.0",
+    "pytorch": "2.1.1+cu121"
+  },
+  "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:f7e306368f641be132de2af2261e2931594e13f7131198d9e7fbffcb28d3fb0f
+size 437967672

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 384,
+  "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": false,
+    "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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "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>",
+  "max_length": 128,
+  "model_max_length": 384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}