Upload 12 files

.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": 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

@@ -1,3 +1,535 @@
----
-license: apache-2.0
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:909469
+- loss:CosineSimilarityLoss
+base_model: intfloat/multilingual-e5-small
+widget:
+- source_sentence: esperto in formazione e motivazione del personale
+  sentences:
+  - linguistic informatics
+  - multi state oversight
+  - esperto in formazione e motivazione del personale
+- source_sentence: drilling horizontal
+  sentences:
+  - gcp, bigquery, service accounts, cloud foundation
+  - visite guidate di libri
+  - introduction to rooms division management
+- source_sentence: deploy de sistemas (centosos, cpanel)
+  sentences:
+  - nvq 2 automotive technician
+  - التحاور الشفهي بالبنجابية
+  - reader oriented-mind
+- source_sentence: json処理
+  sentences:
+  - उच्च सटीकता वाले हाथ के औजारों का उपयोग
+  - owasp zapプロキシ
+  - manipulação de json
+- source_sentence: digas audioproduktion
+  sentences:
+  - commitment to patient safety
+  - soziale arbeit und beratung
+  - formation strategies
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on intfloat/multilingual-e5-small
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.9577111210471887
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8786537702630683
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.9570133219075257
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8800070052053953
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on intfloat/multilingual-e5-small
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-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:** [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) <!-- at revision c007d7ef6fd86656326059b28395a7a03a7c5846 -->
+- **Maximum Sequence Length:** 30 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/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': 30, '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()
+)
+```
+
+## 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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'digas audioproduktion',
+    'formation strategies',
+    'commitment to patient safety',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Datasets: `sts-dev` and `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | sts-dev    | sts-test |
+|:--------------------|:-----------|:---------|
+| pearson_cosine      | 0.9577     | 0.957    |
+| **spearman_cosine** | **0.8787** | **0.88** |
+
+<!--
+## 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: 909,469 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | score                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.05 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.62 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                           | sentence2                                                                  | score            |
+  |:------------------------------------------------------------------------------------|:---------------------------------------------------------------------------|:-----------------|
+  | <code>デジタルデータプロセッシング</code>                                                         | <code>数字数据处理</code>                                                        | <code>1.0</code> |
+  | <code>maintenance des équipements électriques, électroniques et de précision</code> | <code>maintenance of electronic, electrical and precision equipment</code> | <code>1.0</code> |
+  | <code>application frameworks</code>                                                 | <code>ソフトウェアフレームワーク</code>                                                 | <code>1.0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 113,683 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | score                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 8.97 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.85 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.56</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                              | sentence2                          | score             |
+  |:-------------------------------------------------------|:-----------------------------------|:------------------|
+  | <code>verstehen von geschriebenem portugiesisch</code> | <code>लिखित पुर्तगाली समझें</code> | <code>1.0</code>  |
+  | <code>backbox pen test</code>                          | <code>backbox ペネトレーションテスト</code>   | <code>1.0</code>  |
+  | <code>ing. industrial en produccion y calidad</code>   | <code>national speaking</code>     | <code>0.19</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `learning_rate`: 1e-05
+- `num_train_epochs`: 4
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### 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`: 32
+- `per_device_eval_batch_size`: 32
+- `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-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`: 4
+- `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}
+- `tp_size`: 0
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `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
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step  | Training Loss | Validation Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
+|:------:|:-----:|:-------------:|:---------------:|:-----------------------:|:------------------------:|
+| 0.0352 | 500   | 0.2006        | -               | -                       | -                        |
+| 0.0704 | 1000  | 0.0519        | -               | -                       | -                        |
+| 0.1056 | 1500  | 0.0361        | -               | -                       | -                        |
+| 0.1407 | 2000  | 0.0325        | -               | -                       | -                        |
+| 0.1759 | 2500  | 0.0299        | -               | -                       | -                        |
+| 0.2111 | 3000  | 0.0289        | -               | -                       | -                        |
+| 0.2463 | 3500  | 0.0274        | -               | -                       | -                        |
+| 0.2815 | 4000  | 0.0261        | -               | -                       | -                        |
+| 0.3167 | 4500  | 0.0254        | -               | -                       | -                        |
+| 0.3518 | 5000  | 0.0249        | -               | -                       | -                        |
+| 0.3870 | 5500  | 0.0243        | -               | -                       | -                        |
+| 0.4222 | 6000  | 0.0236        | -               | -                       | -                        |
+| 0.4574 | 6500  | 0.0232        | -               | -                       | -                        |
+| 0.4926 | 7000  | 0.0227        | -               | -                       | -                        |
+| 0.5278 | 7500  | 0.0219        | -               | -                       | -                        |
+| 0.5629 | 8000  | 0.0222        | -               | -                       | -                        |
+| 0.5981 | 8500  | 0.0217        | -               | -                       | -                        |
+| 0.6333 | 9000  | 0.0212        | -               | -                       | -                        |
+| 0.6685 | 9500  | 0.0205        | -               | -                       | -                        |
+| 0.7037 | 10000 | 0.0206        | -               | -                       | -                        |
+| 0.7389 | 10500 | 0.0207        | -               | -                       | -                        |
+| 0.7740 | 11000 | 0.02          | -               | -                       | -                        |
+| 0.8092 | 11500 | 0.0198        | -               | -                       | -                        |
+| 0.8444 | 12000 | 0.0199        | -               | -                       | -                        |
+| 0.8796 | 12500 | 0.0196        | -               | -                       | -                        |
+| 0.9148 | 13000 | 0.0192        | -               | -                       | -                        |
+| 0.9500 | 13500 | 0.019         | -               | -                       | -                        |
+| 0.9852 | 14000 | 0.0191        | -               | -                       | -                        |
+| 1.0    | 14211 | -             | 0.0169          | 0.8695                  | -                        |
+| 1.0203 | 14500 | 0.0187        | -               | -                       | -                        |
+| 1.0555 | 15000 | 0.0179        | -               | -                       | -                        |
+| 1.0907 | 15500 | 0.0178        | -               | -                       | -                        |
+| 1.1259 | 16000 | 0.0173        | -               | -                       | -                        |
+| 1.1611 | 16500 | 0.018         | -               | -                       | -                        |
+| 1.1963 | 17000 | 0.0176        | -               | -                       | -                        |
+| 1.2314 | 17500 | 0.0173        | -               | -                       | -                        |
+| 1.2666 | 18000 | 0.0174        | -               | -                       | -                        |
+| 1.3018 | 18500 | 0.0173        | -               | -                       | -                        |
+| 1.3370 | 19000 | 0.0174        | -               | -                       | -                        |
+| 1.3722 | 19500 | 0.0173        | -               | -                       | -                        |
+| 1.4074 | 20000 | 0.0175        | -               | -                       | -                        |
+| 1.4425 | 20500 | 0.0179        | -               | -                       | -                        |
+| 1.4777 | 21000 | 0.017         | -               | -                       | -                        |
+| 1.5129 | 21500 | 0.0167        | -               | -                       | -                        |
+| 1.5481 | 22000 | 0.0174        | -               | -                       | -                        |
+| 1.5833 | 22500 | 0.017         | -               | -                       | -                        |
+| 1.6185 | 23000 | 0.0166        | -               | -                       | -                        |
+| 1.6536 | 23500 | 0.0165        | -               | -                       | -                        |
+| 1.6888 | 24000 | 0.0166        | -               | -                       | -                        |
+| 1.7240 | 24500 | 0.017         | -               | -                       | -                        |
+| 1.7592 | 25000 | 0.0167        | -               | -                       | -                        |
+| 1.7944 | 25500 | 0.0163        | -               | -                       | -                        |
+| 1.8296 | 26000 | 0.0167        | -               | -                       | -                        |
+| 1.8648 | 26500 | 0.0165        | -               | -                       | -                        |
+| 1.8999 | 27000 | 0.0165        | -               | -                       | -                        |
+| 1.9351 | 27500 | 0.0167        | -               | -                       | -                        |
+| 1.9703 | 28000 | 0.0162        | -               | -                       | -                        |
+| 2.0    | 28422 | -             | 0.0155          | 0.8751                  | -                        |
+| 2.0055 | 28500 | 0.0161        | -               | -                       | -                        |
+| 2.0407 | 29000 | 0.0157        | -               | -                       | -                        |
+| 2.0759 | 29500 | 0.0156        | -               | -                       | -                        |
+| 2.1110 | 30000 | 0.015         | -               | -                       | -                        |
+| 2.1462 | 30500 | 0.0155        | -               | -                       | -                        |
+| 2.1814 | 31000 | 0.0152        | -               | -                       | -                        |
+| 2.2166 | 31500 | 0.0153        | -               | -                       | -                        |
+| 2.2518 | 32000 | 0.0154        | -               | -                       | -                        |
+| 2.2870 | 32500 | 0.0154        | -               | -                       | -                        |
+| 2.3221 | 33000 | 0.0152        | -               | -                       | -                        |
+| 2.3573 | 33500 | 0.0154        | -               | -                       | -                        |
+| 2.3925 | 34000 | 0.015         | -               | -                       | -                        |
+| 2.4277 | 34500 | 0.015         | -               | -                       | -                        |
+| 2.4629 | 35000 | 0.0148        | -               | -                       | -                        |
+| 2.4981 | 35500 | 0.0148        | -               | -                       | -                        |
+| 2.5332 | 36000 | 0.0151        | -               | -                       | -                        |
+| 2.5684 | 36500 | 0.0155        | -               | -                       | -                        |
+| 2.6036 | 37000 | 0.0152        | -               | -                       | -                        |
+| 2.6388 | 37500 | 0.0155        | -               | -                       | -                        |
+| 2.6740 | 38000 | 0.0149        | -               | -                       | -                        |
+| 2.7092 | 38500 | 0.0148        | -               | -                       | -                        |
+| 2.7444 | 39000 | 0.0151        | -               | -                       | -                        |
+| 2.7795 | 39500 | 0.0147        | -               | -                       | -                        |
+| 2.8147 | 40000 | 0.015         | -               | -                       | -                        |
+| 2.8499 | 40500 | 0.0147        | -               | -                       | -                        |
+| 2.8851 | 41000 | 0.0147        | -               | -                       | -                        |
+| 2.9203 | 41500 | 0.0151        | -               | -                       | -                        |
+| 2.9555 | 42000 | 0.0144        | -               | -                       | -                        |
+| 2.9906 | 42500 | 0.0146        | -               | -                       | -                        |
+| 3.0    | 42633 | -             | 0.0148          | 0.8771                  | -                        |
+| 3.0258 | 43000 | 0.0144        | -               | -                       | -                        |
+| 3.0610 | 43500 | 0.0141        | -               | -                       | -                        |
+| 3.0962 | 44000 | 0.0146        | -               | -                       | -                        |
+| 3.1314 | 44500 | 0.0136        | -               | -                       | -                        |
+| 3.1666 | 45000 | 0.0143        | -               | -                       | -                        |
+| 3.2017 | 45500 | 0.0142        | -               | -                       | -                        |
+| 3.2369 | 46000 | 0.0146        | -               | -                       | -                        |
+| 3.2721 | 46500 | 0.0144        | -               | -                       | -                        |
+| 3.3073 | 47000 | 0.0142        | -               | -                       | -                        |
+| 3.3425 | 47500 | 0.0142        | -               | -                       | -                        |
+| 3.3777 | 48000 | 0.0138        | -               | -                       | -                        |
+| 3.4128 | 48500 | 0.0141        | -               | -                       | -                        |
+| 3.4480 | 49000 | 0.0141        | -               | -                       | -                        |
+| 3.4832 | 49500 | 0.0142        | -               | -                       | -                        |
+| 3.5184 | 50000 | 0.0142        | -               | -                       | -                        |
+| 3.5536 | 50500 | 0.0141        | -               | -                       | -                        |
+| 3.5888 | 51000 | 0.0141        | -               | -                       | -                        |
+| 3.6240 | 51500 | 0.014         | -               | -                       | -                        |
+| 3.6591 | 52000 | 0.0143        | -               | -                       | -                        |
+| 3.6943 | 52500 | 0.0136        | -               | -                       | -                        |
+| 3.7295 | 53000 | 0.0139        | -               | -                       | -                        |
+| 3.7647 | 53500 | 0.0141        | -               | -                       | -                        |
+| 3.7999 | 54000 | 0.0139        | -               | -                       | -                        |
+| 3.8351 | 54500 | 0.0141        | -               | -                       | -                        |
+| 3.8702 | 55000 | 0.014         | -               | -                       | -                        |
+| 3.9054 | 55500 | 0.0142        | -               | -                       | -                        |
+| 3.9406 | 56000 | 0.0142        | -               | -                       | -                        |
+| 3.9758 | 56500 | 0.014         | -               | -                       | -                        |
+| 4.0    | 56844 | -             | 0.0147          | 0.8787                  | -                        |
+| -1     | -1    | -             | -               | -                       | 0.8800                   |
+
+</details>
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.5.2
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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
+
+*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 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model card.txt

@@ -0,0 +1,22 @@
+Training dataset: 
+	File: skills_matching_training_v1
+	Origin: gpt_dataset_acronyms, gpt_dataset_related, gpt_dataset_translations, gpt_dataset_generator, gpt_dataset_variant_generator
+	Characteristics: LOWER CASE
+	Length: 1.136.837 rows
+
+Base Model: intfloat/multilingual-e5-small
+
+Token Length = 30
+
+Training Data:
+	Train 0.8, Val 0.1, Test 0.1
+	train_batch_size = 32
+	num_epochs = 4
+	warmup_ratio=0.1
+
+Training Results: 
+Epoch	Training Loss	Validation Loss	Sts-dev Pearson Cosine	Sts-dev Spearman Cosine
+1	0.019100	0.016896	0.951701	0.869526
+2	0.016200	0.015457	0.955264	0.875107
+3	0.014600	0.014808	0.957285	0.877118
+4	0.014000	0.014653	0.957711	0.878654

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18aa4869ded36bc812734d4067cffa320cb0251f1ac7762be48c8bc527401ca2
+size 470637416

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": 30,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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": false,
+    "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 sha256:329a8078cc04736e6c69645980ec6e76a17c2a2068e48038596ef0ce143acc67
+size 17083052

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 30,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}