---
base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
language:
- en
- ar
- pt
- es
- de
- th
library_name: sentence-transformers
license: apache-2.0
metrics:
- pearson_cosine
- spearman_cosine
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:178008
- loss:CosineSimilarityLoss
widget:
- source_sentence: 'PHOTOS: Giant human skeleton found in cave by Khao Khanap Nam
A unique discovery of the giant skeleton. Giant possibly killed by a snake. Important
discovery made by paleontologists. Group of scientists unearthing remains of a
human skeleton of gigantic proportions. Do we finally have irrefutable proof that
human giants existed?'
sentences:
- The skeleton that appears in the photographs belongs to a giant human. It is an
important discovery made by paleontologists.
- تم بعون الله شراء خصله شعر رسول الله واودعت اخيرا في دبي بعد شراءها من متحف قرطبة
بأسبانيا صلو على رسول الله
- Photo shows a 2015 visit by then-US president Barack Obama, infectious diseases
expert Dr. Anthony Fauci and philanthropist Melinda Gates to a laboratory in China’s
Wuhan
- source_sentence: iris o preventable ALL OR PATRIC emergency operations center medical
PH manual wennilindered J -Phansuk c
sentences:
- Bolivianos cruzan frontera para votar en legislativas nacionales argentinas
- Note that the pH of the coronavirus ranges from 5.5 to 8.5. So, all we have to
do, to eliminate the virus, is consume more alkaline foods, above the acid level
of the virus. Such as; Bananas, Lime → 9.9 pH, Yellow Lemon → 8.2 pH, Avocado
- 15.6 pH, Garlic - 13.2 pH, Mango - 8.7 pH, Tangerine - 8.5 pH, Pineapple - 12.7
pH, Watercress - 22.7 pH, oranges - 9.2 pH
- El aseo bucal extremo cura y previene el covid-19
- source_sentence: 'ACCORDING TO THE PENDLES 4/22/240 FROM TV AND POLLERS -CASTLE
- KEY KO - FAILED - DOES NOT KNOW THE 4.1% 26% fifteen%. 18% HANDLING CASTLE:
41%. KEYKO: 26 + 15 +18 = 59% AST MANIPULATE AND PREPARE THE FRAUD AND THE DECEIT.'
sentences:
- A Spanish scientist declares that soccer players like Messi and Ronaldo earn 1
million euros per month and researchers who fight against COVID-19 1,800 euros
per month
- White and flawed votes join Keiko Fujimori in the survey
- The Oxford and Sinovac Biotech vaccines were tested only on animals before being
applied to Brazilians.
- source_sentence: Imagina que naciste en Una familia pobre. C HONDURAS
sentences:
- Doria's guinea pig who took the Chinese vaccine against the new coronavirus.
- This is a promo for a new Netflix series "Narcos Honduras"
- Demônio subindo no teto de igreja na Itália ou Espanha
- source_sentence: So Let's - Circle Back - to how YOU got your JOB - Jen Psaki
sentences:
- Jokowi Demonstrated in Germany
- NAIA reverts to MIA, its old name
- Jen Psaki said, 'If you don’t buy anything, you won’t experience inflation’
model-index:
- name: Multilingual mPNet finetuned for cross-lingual similarity
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: eval similarity
type: eval-similarity
metrics:
- type: pearson_cosine
value: 0.9494257373936542
name: Pearson Cosine
- type: spearman_cosine
value: 0.8549322905323449
name: Spearman Cosine
---
# Multilingual mPNet finetuned for cross-lingual similarity
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2)
- **Maximum Sequence Length:** 128 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Languages:** en, ar, pt, es, de, th
- **License:** apache-2.0
### 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': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 768, '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("aryasuneesh/paraphrase-multilingual-mpnet-base-v2-7")
# Run inference
sentences = [
"So Let's - Circle Back - to how YOU got your JOB - Jen Psaki",
"Jen Psaki said, 'If you don’t buy anything, you won’t experience inflation’",
'NAIA reverts to MIA, its old name',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
## Evaluation
### Metrics
#### Semantic Similarity
* Dataset: `eval-similarity`
* Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.9494 |
| **spearman_cosine** | **0.8549** |
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 178,008 training samples
* Columns: text1, text2, and label
* Approximate statistics based on the first 1000 samples:
| | text1 | text2 | label |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details | - min: 5 tokens
- mean: 65.05 tokens
- max: 128 tokens
| - min: 4 tokens
- mean: 21.88 tokens
- max: 128 tokens
| - min: 0.0
- mean: 0.46
- max: 1.0
|
* Samples:
| text1 | text2 | label |
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:-----------------|
| CONFIRM THAT THE UNITED STATES CARRIED CARRIED OUT A MILITARY ATTACK ON KABUL | صورة لانفجار عبوة ناسفة استهدفت سيارة عسكرية جنوب غربي مدينة الرقة السوريّة. | 0.0 |
| Lisboa grita Fora Bolsonaro durante show de Gustavo Lima De arrepiarl [USER] LISBOA, PORTUGAL | Lisbon screams Fora Bolsonaro during concert by Gustavo Lima | 0.0 |
| Singapore stops the vaccination after 48 people died The Telegraph Singapore halts use of flu vaccines after 48 die in South Korea [USER].06flatearth | Singapore halts the rollout of influenza vaccination due to deaths in South Korea | 1.0 |
* Loss: [CosineSimilarityLoss](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: 44,503 evaluation samples
* Columns: text1, text2, and label
* Approximate statistics based on the first 1000 samples:
| | text1 | text2 | label |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details | - min: 7 tokens
- mean: 66.12 tokens
- max: 128 tokens
| - min: 4 tokens
- mean: 22.01 tokens
- max: 128 tokens
| - min: 0.0
- mean: 0.48
- max: 1.0
|
* Samples:
| text1 | text2 | label |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------|:-----------------|
| 141 UN PUEBLO QUE ELIGE A CORRUPTOS, LADRONES Y TRAIDORES NO ES VÍCTIMA, ES COMPLICE. GEORGE ORWELL or [USER] periodismo • poder para la gente | “A people who elect corrupts, imposters, thieves and traitors, are not victims. You are an accomplice!” | 0.0 |
| Watch Full Video [URL] Nasir Chenyoti, the one who spread smiles on people's faces, is fighting a life and death battle today. | Pakistani comic Nasir Chinyoti burned in an accident | 1.0 |
| at des Bezirkec Potsdam Abt. Veterinarsenen 1500 Heinrich-enn-Allee 107 III-15-01-Br 25. Juli 1985 04.07.1985 Information zum Infektionszeitpunkt und zur Übertragung der Coronavirueinfektion in Krein Brandenburg Ier 03.07.1985 gibt es in Kreis 7 staatliche ban. genossenschaftliche und 24 individuelle Coronavirus infektions-Bestunde (siehe Anlage). - Fia Fratinfektion hat vermutlich in der FA wollin stattgefunden (Blutentnahme v. 22.5.85, Feststellung 30.5.85). Von Galten der Betriebsleitung wird eine Einschleppung tiber 1KVE-Fahrzeuge der TVB Conthin vermutet. | Dieses Dokument beweist, dass das Corona-Virus schon in der DDR existierte | 1.0 |
* Loss: [CosineSimilarityLoss](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`: steps
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `learning_rate`: 2e-05
- `weight_decay`: 0.01
- `num_train_epochs`: 5
- `lr_scheduler_type`: cosine
- `warmup_ratio`: 0.1
- `fp16`: True
- `fp16_full_eval`: True
- `dataloader_num_workers`: 4
- `load_best_model_at_end`: True
#### All Hyperparameters
Click to expand
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.01
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 5
- `max_steps`: -1
- `lr_scheduler_type`: cosine
- `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`: True
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 4
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: False
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `eval_use_gather_object`: False
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional