Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 384,
+    "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 +1,658 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:21470
+- loss:MultipleNegativesRankingLoss
+base_model: thenlper/gte-small
+widget:
+- source_sentence: This positive resistance model is a different way of analyzing
+    feedback oscillator operation.
+  sentences:
+  - This positive resistance model is a different way of analyzing feedback oscillator
+    operation.
+  - This negative resistance model is an alternate way of analyzing feedback oscillator
+    operation.
+  - I am BE 8th sem. CSE student. Which path should I choose as a career or which
+    course I should do to get a good job in future within my country?
+- source_sentence: Danny Danny Kortchmar played guitar , Charles Larkey played bass
+    and Gordon played drums producing with Lou Adler .
+  sentences:
+  - What is the main reason for all the problems within India?
+  - Gordon played guitar , Danny Kortchmar played bass and Lou Adler played drums
+    with Charles Larkey producing .
+  - Danny Danny Kortchmar played guitar , Charles Larkey played bass and Gordon played
+    drums producing with Lou Adler .
+- source_sentence: The Ngage isn't still lacking in earbuds.
+  sentences:
+  - What is Queen's University's acceptance rate for international students on campus?
+  - The Ngage is still lacking in earbuds.
+  - The Ngage isn't still lacking in earbuds.
+- source_sentence: Previously reported figures were consistently revised down.
+  sentences:
+  - Previously reported figures were consistently revised down.
+  - What are the side effects for using Proactiv on the face? How are the side effects
+    treated?
+  - Previously reported numbers were infrequently revised down.
+- source_sentence: What is the fastest way to get a PAN card within India?
+  sentences:
+  - He has also used the OpenMusic software (designed at IRCAM ) to create computer-generated
+    music.
+  - What is the fastest way to get a PAN card outside India?
+  - What is the fastest way to get a PAN card within India?
+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: SentenceTransformer based on thenlper/gte-small
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: NanoMSMARCO
+      type: NanoMSMARCO
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.28
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.48
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.52
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.58
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.28
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.15999999999999998
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.10400000000000001
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.057999999999999996
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.28
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.48
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.52
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.58
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.4281391945817123
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.3795238095238095
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.39018847344323304
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: NanoNQ
+      type: NanoNQ
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.32
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.6
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.66
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.74
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.32
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.132
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07400000000000001
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.3
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.55
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.61
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.68
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5108521344166539
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.4791904761904762
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.452598225251627
+      name: Cosine Map@100
+  - task:
+      type: nano-beir
+      name: Nano BEIR
+    dataset:
+      name: NanoBEIR mean
+      type: NanoBEIR_mean
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.30000000000000004
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.54
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.5900000000000001
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.6599999999999999
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.30000000000000004
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.18
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.11800000000000001
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.066
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.29000000000000004
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.515
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.565
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.63
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.4694956644991831
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.4293571428571429
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.42139334934743
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on thenlper/gte-small
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [thenlper/gte-small](https://huggingface.co/thenlper/gte-small). It maps sentences & paragraphs to a 384-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:** [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) <!-- at revision 17e1f347d17fe144873b1201da91788898c639cd -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/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': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (1): Pooling({'word_embedding_dimension': 384, '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("redis/unified-negatives")
+# Run inference
+sentences = [
+    'What is the fastest way to get a PAN card within India?',
+    'What is the fastest way to get a PAN card within India?',
+    'What is the fastest way to get a PAN card outside India?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 1.0000, 0.2943],
+#         [1.0000, 1.0000, 0.2943],
+#         [0.2943, 0.2943, 1.0000]])
+```
+
+<!--
+### 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: `NanoMSMARCO` and `NanoNQ`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | NanoMSMARCO | NanoNQ     |
+|:--------------------|:------------|:-----------|
+| cosine_accuracy@1   | 0.28        | 0.32       |
+| cosine_accuracy@3   | 0.48        | 0.6        |
+| cosine_accuracy@5   | 0.52        | 0.66       |
+| cosine_accuracy@10  | 0.58        | 0.74       |
+| cosine_precision@1  | 0.28        | 0.32       |
+| cosine_precision@3  | 0.16        | 0.2        |
+| cosine_precision@5  | 0.104       | 0.132      |
+| cosine_precision@10 | 0.058       | 0.074      |
+| cosine_recall@1     | 0.28        | 0.3        |
+| cosine_recall@3     | 0.48        | 0.55       |
+| cosine_recall@5     | 0.52        | 0.61       |
+| cosine_recall@10    | 0.58        | 0.68       |
+| **cosine_ndcg@10**  | **0.4281**  | **0.5109** |
+| cosine_mrr@10       | 0.3795      | 0.4792     |
+| cosine_map@100      | 0.3902      | 0.4526     |
+
+#### Nano BEIR
+
+* Dataset: `NanoBEIR_mean`
+* Evaluated with [<code>NanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.NanoBEIREvaluator) with these parameters:
+  ```json
+  {
+      "dataset_names": [
+          "msmarco",
+          "nq"
+      ],
+      "dataset_id": "lightonai/NanoBEIR-en"
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.3        |
+| cosine_accuracy@3   | 0.54       |
+| cosine_accuracy@5   | 0.59       |
+| cosine_accuracy@10  | 0.66       |
+| cosine_precision@1  | 0.3        |
+| cosine_precision@3  | 0.18       |
+| cosine_precision@5  | 0.118      |
+| cosine_precision@10 | 0.066      |
+| cosine_recall@1     | 0.29       |
+| cosine_recall@3     | 0.515      |
+| cosine_recall@5     | 0.565      |
+| cosine_recall@10    | 0.63       |
+| **cosine_ndcg@10**  | **0.4695** |
+| cosine_mrr@10       | 0.4294     |
+| cosine_map@100      | 0.4214     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 21,470 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: 5 tokens</li><li>mean: 19.91 tokens</li><li>max: 101 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.91 tokens</li><li>max: 101 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 19.91 tokens</li><li>max: 101 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                     | positive                                                                                                                   | negative                                                                                                                           |
+  |:---------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------|
+  | <code>The pale coloration provides camouflage for the beetle on the light sand.</code>                                     | <code>The pale coloration provides camouflage for the beetle on the light sand.</code>                                     | <code>The pale coloration helps the beetle stand out on the light sand.</code>                                                     |
+  | <code>It is found from Fennoscandinavia to the Pyrenees , Italy and Greece and from Britain to Russia and Ukraine .</code> | <code>It is found from Fennoscandinavia to the Pyrenees , Italy and Greece and from Britain to Russia and Ukraine .</code> | <code>It is located from Fennoscandinavia to the Pyrenees , Great Britain and Greece and from Italy to Russia and Ukraine .</code> |
+  | <code>Is Swami Vivekananda's speech at parliament of world's religions, Chicago overrated in Chicago?</code>               | <code>Is Swami Vivekananda's speech at parliament of world's religions, Chicago overrated in Chicago?</code>               | <code>Is Swami Vivekananda's speech at parliament of world's religions, Chicago overrated outside Chicago?</code>                  |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 7.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,386 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: 19.42 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.42 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.41 tokens</li><li>max: 74 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                         | positive                                                                                                       | negative                                                                                                       |
+  |:---------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------|
+  | <code>He died at Fort Edward on August 18 , 1861 , and was buried at the Union Cemetery in Sandy Hill .</code> | <code>He died at Fort Edward on August 18 , 1861 , and was buried at the Union Cemetery in Sandy Hill .</code> | <code>He died at Sandy Hill on August 18 , 1861 , and was buried at the Union Cemetery in Fort Edward .</code> |
+  | <code>It was this cooperation which led to the development of the satellite AIS system.</code>                 | <code>It was this cooperation which led to the development of the satellite AIS system.</code>                 | <code>It was this cooperation which led to the halting of development of the satellite AIS system.</code>      |
+  | <code>What is the best field of engineering on campus?</code>                                                  | <code>What is the best field of engineering on campus?</code>                                                  | <code>What is the best field of engineering off campus?</code>                                                 |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 7.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `learning_rate`: 1e-06
+- `weight_decay`: 0.001
+- `max_steps`: 3000
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `dataloader_drop_last`: True
+- `dataloader_num_workers`: 1
+- `dataloader_prefetch_factor`: 1
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch
+- `ddp_find_unused_parameters`: False
+- `push_to_hub`: True
+- `hub_model_id`: redis/unified-negatives
+- `eval_on_start`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 1e-06
+- `weight_decay`: 0.001
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 3.0
+- `max_steps`: 3000
+- `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
+- `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`: True
+- `dataloader_num_workers`: 1
+- `dataloader_prefetch_factor`: 1
+- `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}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `ddp_find_unused_parameters`: False
+- `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`: True
+- `resume_from_checkpoint`: None
+- `hub_model_id`: redis/unified-negatives
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `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`: no
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: True
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: True
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch   | Step | Training Loss | Validation Loss | NanoMSMARCO_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
+|:-------:|:----:|:-------------:|:---------------:|:--------------------------:|:---------------------:|:----------------------------:|
+| 0       | 0    | -             | 3.6734          | 0.6259                     | 0.6583                | 0.6421                       |
+| 1.4970  | 250  | 3.8677        | 3.3900          | 0.6334                     | 0.6510                | 0.6422                       |
+| 2.9940  | 500  | 3.188         | 1.8654          | 0.5772                     | 0.6252                | 0.6012                       |
+| 4.4910  | 750  | 1.4714        | 0.6890          | 0.4032                     | 0.5437                | 0.4735                       |
+| 5.9880  | 1000 | 0.8535        | 0.5511          | 0.3617                     | 0.5197                | 0.4407                       |
+| 7.4850  | 1250 | 0.7547        | 0.5268          | 0.3469                     | 0.5346                | 0.4407                       |
+| 8.9820  | 1500 | 0.716         | 0.5123          | 0.3684                     | 0.5223                | 0.4454                       |
+| 10.4790 | 1750 | 0.6939        | 0.5039          | 0.3846                     | 0.5179                | 0.4512                       |
+| 11.9760 | 2000 | 0.6789        | 0.4986          | 0.4120                     | 0.5280                | 0.4700                       |
+| 13.4731 | 2250 | 0.6681        | 0.4953          | 0.4148                     | 0.5189                | 0.4669                       |
+| 14.9701 | 2500 | 0.662         | 0.4918          | 0.4224                     | 0.5109                | 0.4666                       |
+| 16.4671 | 2750 | 0.6575        | 0.4905          | 0.4224                     | 0.5109                | 0.4666                       |
+| 17.9641 | 3000 | 0.6555        | 0.4900          | 0.4281                     | 0.5109                | 0.4695                       |
+
+
+### Framework Versions
+- Python: 3.10.18
+- Sentence Transformers: 5.2.0
+- Transformers: 4.57.3
+- PyTorch: 2.9.1+cu128
+- Accelerate: 1.12.0
+- Datasets: 2.21.0
+- Tokenizers: 0.22.1
+
+## 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",
+}
+```
+
+#### 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_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.57.3",
+    "pytorch": "2.9.1+cu128"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

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": 128,
+    "do_lower_case": false
+}