Add new SentenceTransformer model.

594a251 verified 2 months ago

19 kB

	---
	language: []
	library_name: sentence-transformers
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- generated_from_trainer
	- dataset_size:665
	- loss:CoSENTLoss
	base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
	datasets: []
	metrics:
	- pearson_cosine
	- spearman_cosine
	- pearson_manhattan
	- spearman_manhattan
	- pearson_euclidean
	- spearman_euclidean
	- pearson_dot
	- spearman_dot
	- pearson_max
	- spearman_max
	widget:
	- source_sentence: Is there a free return policy?
	sentences:
	- general query
	- faq query
	- product query
	- source_sentence: Quiero reservar un vuelo a Madrid
	sentences:
	- faq query
	- general query
	- product query
	- source_sentence: Bestell mir einen Bluetooth-Lautsprecher
	sentences:
	- faq query
	- general query
	- general query
	- source_sentence: Kann ich meinen Account auf Premium upgraden?
	sentences:
	- faq query
	- product query
	- faq query
	- source_sentence: Was kostet der Versand nach Kanada?
	sentences:
	- product query
	- faq query
	- faq query
	pipeline_tag: sentence-similarity
	model-index:
	- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
	results:
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: MiniLM dev
	type: MiniLM-dev
	metrics:
	- type: pearson_cosine
	value: 0.7060858093148971
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.7122657953703283
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.5850353380261794
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.6010204119883696
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.5997691394008732
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.6079117189235353
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.7251159526734934
	name: Pearson Dot
	- type: spearman_dot
	value: 0.732939716175825
	name: Spearman Dot
	- type: pearson_max
	value: 0.7251159526734934
	name: Pearson Max
	- type: spearman_max
	value: 0.732939716175825
	name: Spearman Max
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: MiniLM test
	type: MiniLM-test
	metrics:
	- type: pearson_cosine
	value: 0.8232712880664017
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.822196399839697
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7831863345453927
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8000293400400974
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.792921493930252
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.80506730817637
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.8011854727667188
	name: Pearson Dot
	- type: spearman_dot
	value: 0.8151432444489153
	name: Spearman Dot
	- type: pearson_max
	value: 0.8232712880664017
	name: Pearson Max
	- type: spearman_max
	value: 0.822196399839697
	name: Spearman Max
	---

	# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). 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: [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
	- Maximum Sequence Length: 128 tokens
	- Output Dimensionality: 384 tokens
	- 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': 128, '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})
	)
	```

	## 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("philipp-zettl/MiniLM-similarity-small")
	# Run inference
	sentences = [
	'Was kostet der Versand nach Kanada?',
	'faq query',
	'product query',
	]
	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
	* Dataset: `MiniLM-dev`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.7061 \|
	\| spearman_cosine \| 0.7123 \|
	\| pearson_manhattan \| 0.585 \|
	\| spearman_manhattan \| 0.601 \|
	\| pearson_euclidean \| 0.5998 \|
	\| spearman_euclidean \| 0.6079 \|
	\| pearson_dot \| 0.7251 \|
	\| spearman_dot \| 0.7329 \|
	\| pearson_max \| 0.7251 \|
	\| spearman_max \| 0.7329 \|

	#### Semantic Similarity
	* Dataset: `MiniLM-test`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.8233 \|
	\| spearman_cosine \| 0.8222 \|
	\| pearson_manhattan \| 0.7832 \|
	\| spearman_manhattan \| 0.8 \|
	\| pearson_euclidean \| 0.7929 \|
	\| spearman_euclidean \| 0.8051 \|
	\| pearson_dot \| 0.8012 \|
	\| spearman_dot \| 0.8151 \|
	\| pearson_max \| 0.8233 \|
	\| spearman_max \| 0.8222 \|

	<!--
	## 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: 665 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: 7 tokens</li><li>mean: 11.29 tokens</li><li>max: 19 tokens</li></ul> \| <ul><li>min: 5 tokens</li><li>mean: 5.31 tokens</li><li>max: 6 tokens</li></ul> \| <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| score \|
	\|:---------------------------------------------------------------------\|:---------------------------\|:-----------------\|
	\| <code>Send me deals on gaming accessories</code> \| <code>product query</code> \| <code>1.0</code> \|
	\| <code>Aidez-moi à synchroniser mes contacts sur mon téléphone</code> \| <code>faq query</code> \| <code>0.0</code> \|
	\| <code>Какие у вас есть предложения по ноутбукам?</code> \| <code>faq query</code> \| <code>0.0</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"
	}
	```

	### Evaluation Dataset

	#### Unnamed Dataset


	* Size: 84 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: 7 tokens</li><li>mean: 11.32 tokens</li><li>max: 17 tokens</li></ul> \| <ul><li>min: 5 tokens</li><li>mean: 5.42 tokens</li><li>max: 6 tokens</li></ul> \| <ul><li>min: 0.0</li><li>mean: 0.46</li><li>max: 1.0</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| score \|
	\|:-----------------------------------------------------------------------------\|:---------------------------\|:-----------------\|
	\| <code>كيف يمكنني تتبع شحنتي؟</code> \| <code>support query</code> \| <code>0.0</code> \|
	\| <code>Aidez-moi à configurer une nouvelle adresse e-mail</code> \| <code>support query</code> \| <code>1.0</code> \|
	\| <code>Envoyez-moi les dernières promotions sur les montres connectées</code> \| <code>product query</code> \| <code>1.0</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

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 32
	- `per_device_eval_batch_size`: 32
	- `learning_rate`: 2e-05
	- `num_train_epochs`: 8
	- `warmup_ratio`: 0.1
	- `fp16`: True
	- `batch_sampler`: no_duplicates

	#### 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`: 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
	- `learning_rate`: 2e-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`: 8
	- `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`: no_duplicates
	- `multi_dataset_batch_sampler`: proportional

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| loss \| MiniLM-dev_spearman_cosine \| MiniLM-test_spearman_cosine \|
	\|:------:\|:----:\|:-------------:\|:------:\|:--------------------------:\|:---------------------------:\|
	\| 0.4762 \| 10 \| 1.3639 \| 0.8946 \| 0.0665 \| - \|
	\| 0.9524 \| 20 \| 0.8488 \| 0.7608 \| 0.2318 \| - \|
	\| 1.4286 \| 30 \| 0.6629 \| 1.0463 \| 0.3736 \| - \|
	\| 1.9048 \| 40 \| 1.1413 \| 1.1547 \| 0.4159 \| - \|
	\| 2.3810 \| 50 \| 1.8156 \| 1.2059 \| 0.4760 \| - \|
	\| 2.8571 \| 60 \| 2.0179 \| 0.8129 \| 0.5794 \| - \|
	\| 3.3333 \| 70 \| 0.3202 \| 0.6236 \| 0.6217 \| - \|
	\| 3.8095 \| 80 \| 0.1437 \| 0.6061 \| 0.6404 \| - \|
	\| 4.2857 \| 90 \| 1.1623 \| 0.7312 \| 0.6424 \| - \|
	\| 4.7619 \| 100 \| 0.4376 \| 0.5987 \| 0.6621 \| - \|
	\| 5.2381 \| 110 \| 0.5832 \| 0.4848 \| 0.6837 \| - \|
	\| 5.7143 \| 120 \| 0.1749 \| 0.3367 \| 0.6896 \| - \|
	\| 6.1905 \| 130 \| 0.0192 \| 0.2607 \| 0.6936 \| - \|
	\| 6.6667 \| 140 \| 0.2047 \| 0.2564 \| 0.6995 \| - \|
	\| 7.1429 \| 150 \| 0.404 \| 0.2747 \| 0.7103 \| - \|
	\| 7.6190 \| 160 \| 0.0008 \| 0.2764 \| 0.7123 \| - \|
	\| 8.0 \| 168 \| - \| - \| - \| 0.8222 \|


	### Framework Versions
	- Python: 3.10.14
	- Sentence Transformers: 3.0.1
	- Transformers: 4.41.2
	- PyTorch: 2.3.1+cu121
	- Accelerate: 0.33.0
	- Datasets: 2.21.0
	- 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.
	-->