Add new SentenceTransformer model.

README.md

@@ -1,201 +1,568 @@
 ---
 base_model: sentence-transformers/all-MiniLM-L6-v2
-language: en
-license: apache-2.0
-model_name: LeoChiuu/all-MiniLM-L6-v2-arc
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:965
+- loss:OnlineContrastiveLoss
+widget:
+- source_sentence: Do it by yourself
+  sentences:
+  - What magic can he use?
+  - Let's go outside
+  - Why do I have to do that?
+- source_sentence: What is that on the tree?
+  sentences:
+  - I have not
+  - Oblivion
+  - Is that a cloth on the tree?
+- source_sentence: Which one?
+  sentences:
+  - Bed
+  - I found lillies.
+  - The plush is the flower
+- source_sentence: Who are you?
+  sentences:
+  - You are beautiful
+  - What's analyze mode?
+  - Let's go outside
+- source_sentence: 'Someone who uses magic that turns something into something. '
+  sentences:
+  - Where am I?
+  - 'Mage who can use magic to change the object. '
+  - what's the mystery?
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: custom arc semantics data en
+      type: custom-arc-semantics-data-en
+    metrics:
+    - type: cosine_accuracy
+      value: 0.8911917098445595
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.8555419445037842
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9041095890410958
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.8399168252944946
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9252336448598131
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8839285714285714
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9448087103322457
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.8911917098445595
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 0.8555418252944946
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.9041095890410958
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 0.8399168252944946
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.9252336448598131
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.8839285714285714
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9448087103322457
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.8911917098445595
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 8.42230224609375
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.9041095890410958
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 8.718589782714844
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.9252336448598131
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.8839285714285714
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.9451459110925178
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.8911917098445595
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 0.5375091433525085
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.9041095890410958
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 0.5658255219459534
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.9252336448598131
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.8839285714285714
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.9448087103322457
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.8911917098445595
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 8.42230224609375
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.9041095890410958
+      name: Max F1
+    - type: max_f1_threshold
+      value: 8.718589782714844
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.9252336448598131
+      name: Max Precision
+    - type: max_recall
+      value: 0.8839285714285714
+      name: Max Recall
+    - type: max_ap
+      value: 0.9451459110925178
+      name: Max Ap
 ---
 
-# Model Card for LeoChiuu/all-MiniLM-L6-v2-arc
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
 
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the csv dataset. 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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision 8b3219a92973c328a8e22fadcfa821b5dc75636a -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - csv
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
 
-<!-- Provide a longer summary of what this model is. -->
-
-Generates similarity embeddings
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** en
-- **License:** apache-2.0
-- **Finetuned from model [optional]:** sentence-transformers/all-MiniLM-L6-v2
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### Model Sources
 
-### Direct Use
+- **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)
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+### Full Model Architecture
 
-[More Information Needed]
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: 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()
+)
+```
 
-### Downstream Use [optional]
+## Usage
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+### Direct Usage (Sentence Transformers)
 
-[More Information Needed]
+First install the Sentence Transformers library:
 
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+```bash
+pip install -U sentence-transformers
+```
 
-## Bias, Risks, and Limitations
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+# Download from the 🤗 Hub
+model = SentenceTransformer("LeoChiuu/all-MiniLM-L6-v2-arc")
+# Run inference
+sentences = [
+    'Someone who uses magic that turns something into something. ',
+    'Mage who can use magic to change the object. ',
+    "what's the mystery?",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
 
-[More Information Needed]
-
-### Recommendations
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+<!--
+### Direct Usage (Transformers)
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+<details><summary>Click to see the direct usage in Transformers</summary>
 
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
+</details>
+-->
 
-### Training Data
+<!--
+### Downstream Usage (Sentence Transformers)
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+You can finetune this model on your own dataset.
 
-[More Information Needed]
+<details><summary>Click to expand</summary>
 
-### Training Procedure
+</details>
+-->
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+<!--
+### Out-of-Scope Use
 
-[More Information Needed]
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
+### Metrics
+
+#### Binary Classification
+* Dataset: `custom-arc-semantics-data-en`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.8912     |
+| cosine_accuracy_threshold    | 0.8555     |
+| cosine_f1                    | 0.9041     |
+| cosine_f1_threshold          | 0.8399     |
+| cosine_precision             | 0.9252     |
+| cosine_recall                | 0.8839     |
+| cosine_ap                    | 0.9448     |
+| dot_accuracy                 | 0.8912     |
+| dot_accuracy_threshold       | 0.8555     |
+| dot_f1                       | 0.9041     |
+| dot_f1_threshold             | 0.8399     |
+| dot_precision                | 0.9252     |
+| dot_recall                   | 0.8839     |
+| dot_ap                       | 0.9448     |
+| manhattan_accuracy           | 0.8912     |
+| manhattan_accuracy_threshold | 8.4223     |
+| manhattan_f1                 | 0.9041     |
+| manhattan_f1_threshold       | 8.7186     |
+| manhattan_precision          | 0.9252     |
+| manhattan_recall             | 0.8839     |
+| manhattan_ap                 | 0.9451     |
+| euclidean_accuracy           | 0.8912     |
+| euclidean_accuracy_threshold | 0.5375     |
+| euclidean_f1                 | 0.9041     |
+| euclidean_f1_threshold       | 0.5658     |
+| euclidean_precision          | 0.9252     |
+| euclidean_recall             | 0.8839     |
+| euclidean_ap                 | 0.9448     |
+| max_accuracy                 | 0.8912     |
+| max_accuracy_threshold       | 8.4223     |
+| max_f1                       | 0.9041     |
+| max_f1_threshold             | 8.7186     |
+| max_precision                | 0.9252     |
+| max_recall                   | 0.8839     |
+| **max_ap**                   | **0.9451** |
+
+<!--
+## 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
 
-## Model Card Authors [optional]
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
 
-[More Information Needed]
+## Training Details
 
+### Training Dataset
+
+#### csv
+
+* Dataset: csv
+* Size: 965 training samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 965 samples:
+  |         | text1                                                                            | text2                                                                            | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | int                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.23 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.08 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>0: ~42.88%</li><li>1: ~57.12%</li></ul> |
+* Samples:
+  | text1                                   | text2                                  | label          |
+  |:----------------------------------------|:---------------------------------------|:---------------|
+  | <code>This storybook is related.</code> | <code>Do you know this book?</code>    | <code>1</code> |
+  | <code>Who gave it to you?</code>        | <code>Is it the one I gave you?</code> | <code>1</code> |
+  | <code>Why rosemary?</code>              | <code>Thank you!</code>                | <code>0</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Evaluation Dataset
+
+#### csv
+
+* Dataset: csv
+* Size: 965 evaluation samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
+* Approximate statistics based on the first 965 samples:
+  |         | text1                                                                           | text2                                                                            | label                                           |
+  |:--------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                          | string                                                                           | int                                             |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.4 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.34 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>0: ~41.97%</li><li>1: ~58.03%</li></ul> |
+* Samples:
+  | text1                                  | text2                                  | label          |
+  |:---------------------------------------|:---------------------------------------|:---------------|
+  | <code>Where?</code>                    | <code>Which one should I chose?</code> | <code>1</code> |
+  | <code>Was the window left open?</code> | <code>Did you open the window?</code>  | <code>0</code> |
+  | <code>I don't need any</code>          | <code>Inside</code>                    | <code>0</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 13
+- `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`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 8
+- `per_device_eval_batch_size`: 8
+- `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`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 13
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | Training Loss | loss   | custom-arc-semantics-data-en_max_ap |
+|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
+| None  | 0    | -             | -      | 0.9204                              |
+| 1.0   | 97   | 0.4216        | 0.1880 | 0.9318                              |
+| 2.0   | 194  | 0.1234        | 0.1109 | 0.9388                              |
+| 3.0   | 291  | 0.0588        | 0.1065 | 0.9360                              |
+| 4.0   | 388  | 0.041         | 0.0964 | 0.9472                              |
+| 5.0   | 485  | 0.031         | 0.0962 | 0.9471                              |
+| 6.0   | 582  | 0.0202        | 0.1032 | 0.9444                              |
+| 7.0   | 679  | 0.0214        | 0.0922 | 0.9452                              |
+| 8.0   | 776  | 0.0232        | 0.0857 | 0.9454                              |
+| 9.0   | 873  | 0.0135        | 0.0873 | 0.9474                              |
+| 10.0  | 970  | 0.0136        | 0.0870 | 0.9444                              |
+| 11.0  | 1067 | 0.0131        | 0.0903 | 0.9452                              |
+| 12.0  | 1164 | 0.0135        | 0.0903 | 0.9450                              |
+| 13.0  | 1261 | 0.0082        | 0.0902 | 0.9451                              |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.1.0
+- Transformers: 4.44.2
+- PyTorch: 2.4.1+cu121
+- Accelerate: 0.34.2
+- Datasets: 2.20.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+<!--
+## 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
 
-[More Information Needed]
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d69507d61c4dad8a4b2276b36338d6e9e97f7dbc11623f392dc2d0f64f31a75
+oid sha256:a7fefe0ef583c2760d11ac99d99c8344222316fea40286e6ca9556955ab311af
 size 90864192