Update README.md

README.md

@@ -1,547 +1,59 @@
 ---
+license: apache-2.0
 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
+datasets:
+- gabrielloiseau/CALE-SPCD
 ---
 
-# SentenceTransformer based on FacebookAI/xlm-roberta-large
+# CALE-XLM-R
 
-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.
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps occurences of a word to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
-## 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
+## Usage (Sentence-Transformers)
 
-- **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.
+Then you can use the model like this:
+
 ```python
 from sentence_transformers import SentenceTransformer
 
-# Download from the 🤗 Hub
+# 1. Load CALE model
 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 .',
+    "the boy could easily <t>distinguish</t> the different note values",
+    "he patient’s ability to <t>recognize</t> forms and shapes",
+    "the government had refused to <t>recognize</t> their autonomy and existence as a state",
 ]
+
+# 2. Calculate embeddings
 embeddings = model.encode(sentences)
 print(embeddings.shape)
 # [3, 1024]
 
-# Get the similarity scores for the embeddings
+# 3. Calculate the embedding similarities
 similarities = model.similarity(embeddings, embeddings)
-print(similarities.shape)
-# [3, 3]
+print(similarities)
+# tensor([[1.0000, 0.9332, 0.5331],
+#        [0.9332, 1.0000, 0.5619],
+#        [0.5331, 0.5619, 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
-
-#### 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",
-}
+## Full Model Architecture
 ```
-
-#### 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.*
--->
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': '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})
+)
+```