Add new SentenceTransformer model.

7a3dff5 verified 5 months ago

21.9 kB

	---
	language:
	- en
	- ca
	license: apache-2.0
	library_name: sentence-transformers
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- dataset_size:1K<n<10K
	- loss:CoSENTLoss
	base_model: microsoft/mpnet-base
	metrics:
	- pearson_cosine
	- spearman_cosine
	- pearson_manhattan
	- spearman_manhattan
	- pearson_euclidean
	- spearman_euclidean
	- pearson_dot
	- spearman_dot
	- pearson_max
	- spearman_max
	widget:
	- source_sentence: Dia Internacional del Nen Prematur
	sentences:
	- Premiats a les comarques de Barcelona
	- Les concordances són adjectiu / substantiu o verb / substantiu.
	- Els Mossos en busquen un altre, que va aconseguir fugir en ser enxampats 'in fraganti'
	- source_sentence: Vulneració del dret a la llibertat
	sentences:
	- Vulneració del dret a un jutge imparcial
	- Detenen un home a Malgrat de Mar per apallissar un escombriaire
	- La víctima ha rebut un cop de puny i ha caigut a terra inconscient
	- source_sentence: Agafem un taxi i ens plantem allà.
	sentences:
	- És una activitat gratuïta oberta al públic general.
	- El líder del PSC, Miquel Iceta, serà el nou president del Senat
	- El PSOE ja no descarta l’aplicació de l’article 155 de la Constitució a Catalunya
	- source_sentence: No ho entenc, però és el que hi ha.
	sentences:
	- és dels plats que a casa ens encanten!
	- El Punt d'Informació Juvenil és el servei més actiu del centre.
	- Puigdemont reunirà dimecres a Bèlgica els diputats de JxCat
	- source_sentence: Però que hi ha de cert en tot això?
	sentences:
	- Però, què hi ha de veritat en tot això?
	- Els camioners dissolen la marxa lenta a les rondes de Barcelona
	- El 112 atén 747.730 trucades durant el primer semestre, un 9,6% més que l'any
	passat
	pipeline_tag: sentence-similarity
	model-index:
	- name: MPNet base trained on semantic text similarity
	results:
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: Unknown
	type: unknown
	metrics:
	- type: pearson_cosine
	value: 0.9369799393019737
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.991833254558149
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.9582116235734125
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.9876060961452328
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.9594231143506534
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.9887559900790531
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.9469313911363318
	name: Pearson Dot
	- type: spearman_dot
	value: 0.9834282009396937
	name: Spearman Dot
	- type: pearson_max
	value: 0.9594231143506534
	name: Pearson Max
	- type: spearman_max
	value: 0.991833254558149
	name: Spearman Max
	- type: pearson_cosine
	value: 0.5855972037779524
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.5854785473306573
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.5881281979560977
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.578667646485271
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.5851079475768374
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.5754637407144132
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.5612927132777441
	name: Pearson Dot
	- type: spearman_dot
	value: 0.5630862098985
	name: Spearman Dot
	- type: pearson_max
	value: 0.5881281979560977
	name: Pearson Max
	- type: spearman_max
	value: 0.5854785473306573
	name: Spearman Max
	- type: pearson_cosine
	value: 0.6501162382185041
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.6819594226888658
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.6517756634326819
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.6701084565797553
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.6553647425414415
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.675292747578234
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.6350099608995957
	name: Pearson Dot
	- type: spearman_dot
	value: 0.6458150666120989
	name: Spearman Dot
	- type: pearson_max
	value: 0.6553647425414415
	name: Pearson Max
	- type: spearman_max
	value: 0.6819594226888658
	name: Spearman Max
	---

	# MPNet base trained on semantic text similarity

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [projecte-aina/sts-ca](https://huggingface.co/datasets/projecte-aina/sts-ca) dataset. 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: [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 768 tokens
	- Similarity Function: Cosine Similarity
	- Training Dataset:
	- [projecte-aina/sts-ca](https://huggingface.co/datasets/projecte-aina/sts-ca)
	- Languages: en, ca
	- 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': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
	(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("pauhidalgoo/finetuned-sts-ca-mpnet-base")
	# Run inference
	sentences = [
	'Però que hi ha de cert en tot això?',
	'Però, què hi ha de veritat en tot això?',
	'Els camioners dissolen la marxa lenta a les rondes de Barcelona',
	]
	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]
	```

	<!--
	### 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

	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.937 \|
	\| spearman_cosine \| 0.9918 \|
	\| pearson_manhattan \| 0.9582 \|
	\| spearman_manhattan \| 0.9876 \|
	\| pearson_euclidean \| 0.9594 \|
	\| spearman_euclidean \| 0.9888 \|
	\| pearson_dot \| 0.9469 \|
	\| spearman_dot \| 0.9834 \|
	\| pearson_max \| 0.9594 \|
	\| spearman_max \| 0.9918 \|

	#### Semantic Similarity

	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.5856 \|
	\| spearman_cosine \| 0.5855 \|
	\| pearson_manhattan \| 0.5881 \|
	\| spearman_manhattan \| 0.5787 \|
	\| pearson_euclidean \| 0.5851 \|
	\| spearman_euclidean \| 0.5755 \|
	\| pearson_dot \| 0.5613 \|
	\| spearman_dot \| 0.5631 \|
	\| pearson_max \| 0.5881 \|
	\| spearman_max \| 0.5855 \|

	#### Semantic Similarity

	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:----------\|
	\| pearson_cosine \| 0.6501 \|
	\| spearman_cosine \| 0.682 \|
	\| pearson_manhattan \| 0.6518 \|
	\| spearman_manhattan \| 0.6701 \|
	\| pearson_euclidean \| 0.6554 \|
	\| spearman_euclidean \| 0.6753 \|
	\| pearson_dot \| 0.635 \|
	\| spearman_dot \| 0.6458 \|
	\| pearson_max \| 0.6554 \|
	\| spearman_max \| 0.682 \|

	<!--
	## 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

	#### projecte-aina/sts-ca

	* Dataset: [projecte-aina/sts-ca](https://huggingface.co/datasets/projecte-aina/sts-ca)
	* Size: 2,073 training samples
	* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \| label \|
	\|:--------\|:-----------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------\|:---------------------------------------------------------------\|
	\| type \| string \| string \| float \|
	\| details \| <ul><li>min: 10 tokens</li><li>mean: 32.36 tokens</li><li>max: 82 tokens</li></ul> \| <ul><li>min: 11 tokens</li><li>mean: 30.57 tokens</li><li>max: 68 tokens</li></ul> \| <ul><li>min: 0.0</li><li>mean: 2.56</li><li>max: 5.0</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| label \|
	\|:-------------------------------------------------------------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:--------------------------------\|
	\| <code>Atorga per primer cop les mencions Encarna Sanahuja a la inclusió de la perspectiva de gènere en docència Universitària</code> \| <code>Creen la menció M. Encarna Sanahuja a la inclusió de la perspectiva de gènere en docència universitària</code> \| <code>3.5</code> \|
	\| <code>Finalment, afegiu-hi els bolets que haureu saltat en una paella amb oli i deixeu-ho coure tot junt durant 5 minuts.</code> \| <code>Finalment, poseu-hi les minipastanagues tallades a dauets, els pèsols, rectifiqueu-ho de sal i deixeu-ho coure tot junt durant un parell de minuts més.</code> \| <code>1.25</code> \|
	\| <code>El TC suspèn el pla d'acció exterior i de relacions amb la UE de la Generalitat</code> \| <code>El Constitucional manté la suspensió del pla estratègic d'acció exterior i relacions amb la UE</code> \| <code>3.6700000762939453</code> \|
	* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "pairwise_cos_sim"
	}
	```

	### Evaluation Dataset

	#### projecte-aina/sts-ca

	* Dataset: [projecte-aina/sts-ca](https://huggingface.co/datasets/projecte-aina/sts-ca)
	* Size: 500 evaluation samples
	* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \| label \|
	\|:--------\|:-----------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------\|:---------------------------------------------------------------\|
	\| type \| string \| string \| float \|
	\| details \| <ul><li>min: 10 tokens</li><li>mean: 32.94 tokens</li><li>max: 68 tokens</li></ul> \| <ul><li>min: 12 tokens</li><li>mean: 31.42 tokens</li><li>max: 69 tokens</li></ul> \| <ul><li>min: 0.0</li><li>mean: 2.58</li><li>max: 5.0</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| label \|
	\|:---------------------------------------------------------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------------------------------------\|:--------------------------------\|
	\| <code>L'euríbor puja una centèsima fins el -0,189% al gener després de setze mesos de caigudes</code> \| <code>La morositat de bancs i caixes repunta moderadament fins el 9,44%, després d'onze mesos de caigudes</code> \| <code>1.6699999570846558</code> \|
	\| <code>Demanen 3 anys de presó a l'ex treballador d'una farmàcia de Lleida per robar més de 550 unitats de Viagra i Cialis</code> \| <code>L'extreballador d'una farmàcia de Lleida accepta sis mesos de presó per robar més de 500 unitats de Viagra i Cialis</code> \| <code>2.0</code> \|
	\| <code>Es tracta d'un jove de 20 anys que ha estat denunciat als Mossos d'Esquadra</code> \| <code>Es tracta d'un jove de 21 anys que ha estat denunciat penalment pels Mossos</code> \| <code>3.0</code> \|
	* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "pairwise_cos_sim"
	}
	```

	### Training Hyperparameters
	#### Non-Default Hyperparameters

	- `per_device_train_batch_size`: 16
	- `per_device_eval_batch_size`: 16
	- `num_train_epochs`: 40
	- `warmup_ratio`: 0.1
	- `fp16`: True

	#### All Hyperparameters
	<details><summary>Click to expand</summary>

	- `overwrite_output_dir`: False
	- `do_predict`: False
	- `eval_strategy`: no
	- `prediction_loss_only`: True
	- `per_device_train_batch_size`: 16
	- `per_device_eval_batch_size`: 16
	- `per_gpu_train_batch_size`: None
	- `per_gpu_eval_batch_size`: None
	- `gradient_accumulation_steps`: 1
	- `eval_accumulation_steps`: None
	- `learning_rate`: 5e-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`: 40
	- `max_steps`: -1
	- `lr_scheduler_type`: linear
	- `lr_scheduler_kwargs`: {}
	- `warmup_ratio`: 0.1
	- `warmup_steps`: 0
	- `log_level`: passive
	- `log_level_replica`: warning
	- `log_on_each_node`: True
	- `logging_nan_inf_filter`: True
	- `save_safetensors`: True
	- `save_on_each_node`: False
	- `save_only_model`: False
	- `restore_callback_states_from_checkpoint`: False
	- `no_cuda`: False
	- `use_cpu`: False
	- `use_mps_device`: False
	- `seed`: 42
	- `data_seed`: None
	- `jit_mode_eval`: False
	- `use_ipex`: False
	- `bf16`: False
	- `fp16`: True
	- `fp16_opt_level`: O1
	- `half_precision_backend`: auto
	- `bf16_full_eval`: False
	- `fp16_full_eval`: False
	- `tf32`: None
	- `local_rank`: 0
	- `ddp_backend`: None
	- `tpu_num_cores`: None
	- `tpu_metrics_debug`: False
	- `debug`: []
	- `dataloader_drop_last`: False
	- `dataloader_num_workers`: 0
	- `dataloader_prefetch_factor`: None
	- `past_index`: -1
	- `disable_tqdm`: False
	- `remove_unused_columns`: True
	- `label_names`: None
	- `load_best_model_at_end`: False
	- `ignore_data_skip`: False
	- `fsdp`: []
	- `fsdp_min_num_params`: 0
	- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
	- `fsdp_transformer_layer_cls_to_wrap`: None
	- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
	- `deepspeed`: None
	- `label_smoothing_factor`: 0.0
	- `optim`: adamw_torch
	- `optim_args`: None
	- `adafactor`: False
	- `group_by_length`: False
	- `length_column_name`: length
	- `ddp_find_unused_parameters`: None
	- `ddp_bucket_cap_mb`: None
	- `ddp_broadcast_buffers`: False
	- `dataloader_pin_memory`: True
	- `dataloader_persistent_workers`: False
	- `skip_memory_metrics`: True
	- `use_legacy_prediction_loop`: False
	- `push_to_hub`: False
	- `resume_from_checkpoint`: None
	- `hub_model_id`: None
	- `hub_strategy`: every_save
	- `hub_private_repo`: False
	- `hub_always_push`: False
	- `gradient_checkpointing`: False
	- `gradient_checkpointing_kwargs`: None
	- `include_inputs_for_metrics`: False
	- `eval_do_concat_batches`: True
	- `fp16_backend`: auto
	- `push_to_hub_model_id`: None
	- `push_to_hub_organization`: None
	- `mp_parameters`:
	- `auto_find_batch_size`: False
	- `full_determinism`: False
	- `torchdynamo`: None
	- `ray_scope`: last
	- `ddp_timeout`: 1800
	- `torch_compile`: False
	- `torch_compile_backend`: None
	- `torch_compile_mode`: None
	- `dispatch_batches`: None
	- `split_batches`: None
	- `include_tokens_per_second`: False
	- `include_num_input_tokens_seen`: False
	- `neftune_noise_alpha`: None
	- `optim_target_modules`: None
	- `batch_eval_metrics`: False
	- `batch_sampler`: batch_sampler
	- `multi_dataset_batch_sampler`: proportional

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| spearman_cosine \|
	\|:-------:\|:----:\|:-------------:\|:---------------:\|
	\| 3.8462 \| 500 \| 4.5209 \| - \|
	\| 7.6923 \| 1000 \| 4.1445 \| - \|
	\| 11.5385 \| 1500 \| 3.9291 \| - \|
	\| 15.3846 \| 2000 \| 3.6952 \| - \|
	\| 19.2308 \| 2500 \| 3.5393 \| - \|
	\| 23.0769 \| 3000 \| 3.3778 \| - \|
	\| 26.9231 \| 3500 \| 3.1712 \| - \|
	\| 30.7692 \| 4000 \| 2.8265 \| - \|
	\| 34.6154 \| 4500 \| 2.6265 \| - \|
	\| 38.4615 \| 5000 \| 2.3259 \| - \|
	\| 40.0 \| 5200 \| - \| 0.6820 \|


	### Framework Versions
	- Python: 3.10.12
	- Sentence Transformers: 3.0.0
	- Transformers: 4.41.1
	- PyTorch: 2.3.0+cu121
	- Accelerate: 0.30.1
	- Datasets: 2.19.2
	- Tokenizers: 0.19.1

	## Citation

	### BibTeX

	#### Sentence Transformers
	```bibtex
	@inproceedings{reimers-2019-sentence-bert,
	title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
	author = "Reimers, Nils and Gurevych, Iryna",
	booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
	month = "11",
	year = "2019",
	publisher = "Association for Computational Linguistics",
	url = "https://arxiv.org/abs/1908.10084",
	}
	```

	#### CoSENTLoss
	```bibtex
	@online{kexuefm-8847,
	title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
	author={Su Jianlin},
	year={2022},
	month={Jan},
	url={https://kexue.fm/archives/8847},
	}
	```

	<!--
	## 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.
	-->