Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "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 +1,547 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:156387
+- loss:ContrastiveLoss
+base_model: FacebookAI/xlm-roberta-large
+widget:
+- source_sentence: the latter is useful for modifying information about some or all
+    forms of a word , hence reducing the work required to improve <t>dictionary</t>
+    contents .
+  sentences:
+  - conchita nagged at the younger children , attempting without <t>success</t> to
+    keep her thoughts off tom brannon .
+  - another girl from a relatively large midwestern city described herself as `` the
+    only orthodox girl in <t>town</t> '' .
+  - entries are summarized only when by doing so the amount of information retained
+    in the <t>dictionary</t> is reduced and the time required for dictionary operations
+    is decreased .
+- source_sentence: the kind of religious experience that most moderns seek not only
+    provides , clarifies , and relates human yearnings , values , ideals , and purposes
+    ; it also provides facilities and incitements for the <t>development</t> of personality
+    , sociality , and creativeness .
+  sentences:
+  - the artistic interest , then , lies in what the encounter may be made to represent
+    , in the power of some <t>central</t> significance to draw the details into relevance
+    and meaningfulness .
+  - more than 25 carefully selected cities were visited , <t>including</t> new york
+    , brooklyn , long island city , newark , elizabeth , stamford , waterbury , new
+    haven , bridgeport , boston , cambridge , worcester , and waltham .
+  - the liberals , smelling blood , were faced with the necessity of <t>winning</t>
+    three big votes - in the democratic committee on committees , in the full party
+    caucus , and on the floor of the house - before they could oust colmer .
+- source_sentence: 'another yankee became so disgusted as to state : `` i wish to
+    god one half of our <t>officers</t> were knocked in the head by slinging them
+    against [ the other half ] '''' .'
+  sentences:
+  - we 'd seen his handiwork out in the back yard , and the little his tenants had
+    told us of him did make him sound a little <t>special</t> .
+  - 'private george gray hunter of pennsylvania wrote : `` i am well convinced in
+    my own mind that had it not been for <t>officers</t> this war would have ended
+    long ago '''' .'
+  - until this hunter-killer operation can be performed by spacecraft , manned aircraft
+    <t>appear</t> to be the only means available to us .
+- source_sentence: there was a man 's jacket on the chair and a straw hat on the <t>table</t>
+    .
+  sentences:
+  - this section shall not apply to corporations purchasing such stock solely for
+    investment and not using the same by voting or otherwise to bring about , or in
+    <t>attempting</t> to bring about , the substantial lessening of competition ``
+    .
+  - if your principal place of abode for the tax <t>year</t> is outside the united
+    states ( including alaska and hawaii ) , puerto rico , or the virgin islands and
+    you have no legal residence or principal place of business in any internal revenue
+    district in the united states , you should file your return with the office of
+    international operations , internal revenue service , washington 25 , d. c. .
+  - both , of course , were remarkable feats and further embossed the fact that <t>baseball</t>
+    rightfully is the national pastime .
+- source_sentence: a. e. sharp , in vowel-length and syllabicity in kikuyu , examines
+    one set of related orthographic questions and its phonologic <t>background</t>
+    in detail .
+  sentences:
+  - sensing the unseen presence of the other men in the patrol , he felt mutely united
+    to these nine <t>near</t> strangers sharing this pinpoint of being with him .
+  - this subsection shall not be so construed as to deprive the owner of any <t>background</t>
+    patent relating thereto of such rights as he may have thereunder .
+  - government itself was based upon contract ; business organization - the corporation
+    - was analyzed in contractual terms ; trade was based on freedom of contract ,
+    and money was lent and borrowed on contractual terms ; even marriage and the family
+    was seen as a contractual <t>arrangement</t> .
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+model-index:
+- name: SentenceTransformer based on FacebookAI/xlm-roberta-large
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: cale eval
+      type: cale-eval
+    metrics:
+    - type: cosine_accuracy
+      value: 0.7822948920719075
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.6373387575149536
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.7738327068520447
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.5533720254898071
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.661133681563165
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9328492657094503
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.7420096616621343
+      name: Cosine Ap
+---
+
+# SentenceTransformer based on FacebookAI/xlm-roberta-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large). It maps sentences & paragraphs to a 1024-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:** [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) <!-- at revision c23d21b0620b635a76227c604d44e43a9f0ee389 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 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/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("gabrielloiseau/CALE-XLM-R")
+# Run inference
+sentences = [
+    'a. e. sharp , in vowel-length and syllabicity in kikuyu , examines one set of related orthographic questions and its phonologic <t>background</t> in detail .',
+    'this subsection shall not be so construed as to deprive the owner of any <t>background</t> patent relating thereto of such rights as he may have thereunder .',
+    'sensing the unseen presence of the other men in the patrol , he felt mutely united to these nine <t>near</t> strangers sharing this pinpoint of being with him .',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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
+
+#### Binary Classification
+
+* Dataset: `cale-eval`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value     |
+|:--------------------------|:----------|
+| cosine_accuracy           | 0.7823    |
+| cosine_accuracy_threshold | 0.6373    |
+| cosine_f1                 | 0.7738    |
+| cosine_f1_threshold       | 0.5534    |
+| cosine_precision          | 0.6611    |
+| cosine_recall             | 0.9328    |
+| **cosine_ap**             | **0.742** |
+
+<!--
+## 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: 156,387 training samples
+* Columns: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | label                                           | sentence1                                                                           | sentence2                                                                           |
+  |:--------|:------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | int                                             | string                                                                              | string                                                                              |
+  | details | <ul><li>0: ~60.70%</li><li>1: ~39.30%</li></ul> | <ul><li>min: 23 tokens</li><li>mean: 56.47 tokens</li><li>max: 134 tokens</li></ul> | <ul><li>min: 23 tokens</li><li>mean: 57.06 tokens</li><li>max: 135 tokens</li></ul> |
+* Samples:
+  | label          | sentence1                                                                                                                                                  | sentence2                                                                                                                                                                                                                                                                                                                                                                                                                       |
+  |:---------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>1</code> | <code>as a result , although we still make use of this distinction , there is much confusion as to the meaning of the <t>basic</t> terms employed .</code> | <code>but he takes his bearings from the great guidelines of policy , well established precedents , the commitments of the united states under international charters and treaties , <t>basic</t> statutes , and well understood notions of the american people about how we are to conduct ourselves , in policy literature such as country papers and national security council papers accumulated in the department .</code> |
+  | <code>0</code> | <code>as a result , although we still make use of this distinction , there is much confusion as to the meaning of the <t>basic</t> terms employed .</code> | <code>if adjectival meanings show relatively low retentiveness of stems , as i am confident will prove to be the case in most languages of the world , why should our <t>basic</t> lists include 15 per cent of these unstable forms , but only 8 per cent of animals and plants which replace much more slowly ?</code>                                                                                                        |
+  | <code>0</code> | <code>as a result , although we still make use of this distinction , there is much confusion as to the meaning of the <t>basic</t> terms employed .</code> | <code>in 1927 his father 's business collapsed , and , rather than go bankrupt , mercer senior turned his firm over to a <t>bank</t> for liquidation .</code>                                                                                                                                                                                                                                                                   |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.7,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 44,891 evaluation samples
+* Columns: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | label                                           | sentence1                                                                           | sentence2                                                                           |
+  |:--------|:------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | int                                             | string                                                                              | string                                                                              |
+  | details | <ul><li>0: ~60.60%</li><li>1: ~39.40%</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 53.29 tokens</li><li>max: 151 tokens</li></ul> | <ul><li>min: 21 tokens</li><li>mean: 54.72 tokens</li><li>max: 149 tokens</li></ul> |
+* Samples:
+  | label          | sentence1                                                                                              | sentence2                                                                                                                                                                                                                                                 |
+  |:---------------|:-------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>1</code> | <code>drop both hands to the floor and at the same time kick the right <t>foot</t> up in back .</code> | <code>place a suitably loaded barbell across them ; grasp the bar ( which will rest against the back of your neck ) ; extend your <t>feet</t> forward and backward until you are in a deep leg split .</code>                                             |
+  | <code>0</code> | <code>drop both hands to the floor and at the same time kick the right <t>foot</t> up in back .</code> | <code>a scant half mile away shelley and mary were doubtless sitting on their diminutive terrace , the air about them scented with stock , and listening to the nightingale who had nested in the big lime tree at the <t>foot</t> of the garden .</code> |
+  | <code>0</code> | <code>drop both hands to the floor and at the same time kick the right <t>foot</t> up in back .</code> | <code>in preparing the state guide plan , particular attention will be given means of <t>strengthening</t> the economy of the state through the development of industry and recreation .</code>                                                           |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.7,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 13
+- `per_device_eval_batch_size`: 13
+- `gradient_accumulation_steps`: 2
+- `learning_rate`: 4.46438e-06
+- `weight_decay`: 0.0388
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.2995
+- `fp16`: True
+- `gradient_checkpointing`: 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`: 13
+- `per_device_eval_batch_size`: 13
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 4.46438e-06
+- `weight_decay`: 0.0388
+- `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`: 0.2995
+- `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`: True
+- `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`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | cale-eval_cosine_ap |
+|:------:|:----:|:-------------:|:---------------:|:-------------------:|
+| 0      | 0    | -             | -               | 0.5131              |
+| 0.0166 | 100  | 0.2826        | -               | -                   |
+| 0.0333 | 200  | 0.2505        | -               | -                   |
+| 0.0499 | 300  | 0.1684        | -               | -                   |
+| 0.0665 | 400  | 0.1539        | -               | -                   |
+| 0.0831 | 500  | 0.1297        | 0.0598          | 0.5317              |
+| 0.0998 | 600  | 0.1237        | -               | -                   |
+| 0.1164 | 700  | 0.1141        | -               | -                   |
+| 0.1330 | 800  | 0.114         | -               | -                   |
+| 0.1496 | 900  | 0.1161        | -               | -                   |
+| 0.1663 | 1000 | 0.111         | 0.0561          | 0.5799              |
+| 0.1829 | 1100 | 0.1066        | -               | -                   |
+| 0.1995 | 1200 | 0.1012        | -               | -                   |
+| 0.2161 | 1300 | 0.0951        | -               | -                   |
+| 0.2328 | 1400 | 0.0885        | -               | -                   |
+| 0.2494 | 1500 | 0.0844        | 0.0410          | 0.7014              |
+| 0.2660 | 1600 | 0.0827        | -               | -                   |
+| 0.2826 | 1700 | 0.0807        | -               | -                   |
+| 0.2993 | 1800 | 0.0833        | -               | -                   |
+| 0.3159 | 1900 | 0.079         | -               | -                   |
+| 0.3325 | 2000 | 0.0778        | 0.0393          | 0.7209              |
+| 0.3491 | 2100 | 0.0756        | -               | -                   |
+| 0.3658 | 2200 | 0.0798        | -               | -                   |
+| 0.3824 | 2300 | 0.0756        | -               | -                   |
+| 0.3990 | 2400 | 0.0715        | -               | -                   |
+| 0.4156 | 2500 | 0.0723        | 0.0374          | 0.7374              |
+| 0.4323 | 2600 | 0.0728        | -               | -                   |
+| 0.4489 | 2700 | 0.0719        | -               | -                   |
+| 0.4655 | 2800 | 0.0724        | -               | -                   |
+| 0.4821 | 2900 | 0.0674        | -               | -                   |
+| 0.4988 | 3000 | 0.0683        | 0.0377          | 0.7344              |
+| 0.5154 | 3100 | 0.0673        | -               | -                   |
+| 0.5320 | 3200 | 0.0684        | -               | -                   |
+| 0.5486 | 3300 | 0.0649        | -               | -                   |
+| 0.5653 | 3400 | 0.067         | -               | -                   |
+| 0.5819 | 3500 | 0.0673        | 0.0373          | 0.7382              |
+| 0.5985 | 3600 | 0.0701        | -               | -                   |
+| 0.6151 | 3700 | 0.0648        | -               | -                   |
+| 0.6318 | 3800 | 0.0641        | -               | -                   |
+| 0.6484 | 3900 | 0.0653        | -               | -                   |
+| 0.6650 | 4000 | 0.0658        | 0.0367          | 0.7428              |
+| 0.6816 | 4100 | 0.0628        | -               | -                   |
+| 0.6983 | 4200 | 0.0671        | -               | -                   |
+| 0.7149 | 4300 | 0.0626        | -               | -                   |
+| 0.7315 | 4400 | 0.0638        | -               | -                   |
+| 0.7481 | 4500 | 0.0655        | 0.0370          | 0.7383              |
+| 0.7648 | 4600 | 0.0608        | -               | -                   |
+| 0.7814 | 4700 | 0.062         | -               | -                   |
+| 0.7980 | 4800 | 0.0625        | -               | -                   |
+| 0.8146 | 4900 | 0.0629        | -               | -                   |
+| 0.8313 | 5000 | 0.0631        | 0.0368          | 0.7409              |
+| 0.8479 | 5100 | 0.0619        | -               | -                   |
+| 0.8645 | 5200 | 0.0623        | -               | -                   |
+| 0.8811 | 5300 | 0.0623        | -               | -                   |
+| 0.8978 | 5400 | 0.0631        | -               | -                   |
+| 0.9144 | 5500 | 0.0588        | 0.0367          | 0.7409              |
+| 0.9310 | 5600 | 0.0618        | -               | -                   |
+| 0.9476 | 5700 | 0.0588        | -               | -                   |
+| 0.9643 | 5800 | 0.0605        | -               | -                   |
+| 0.9809 | 5900 | 0.061         | -               | -                   |
+| 0.9975 | 6000 | 0.0587        | 0.0367          | 0.7420              |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.48.1
+- PyTorch: 2.5.1
+- Accelerate: 1.2.1
+- Datasets: 3.2.0
+- 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.0.0",
+    "transformers": "4.55.0",
+    "pytorch": "2.7.1+cu126"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine",
+  "model_type": "SentenceTransformer"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24059aa5f0d8e613409e17e7e0450db5412616bd665f16150b69bcfe8bf5bdce
+size 2239607176

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": 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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}