SentenceTransformer based on bowphs/LaBerta

This is a sentence-transformers model finetuned from bowphs/LaBerta. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: bowphs/LaBerta
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'RobertaModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("TdelaSelle/PatriLaRS")
# Run inference
queries = [
    'et mirati sunt super hoc ueraces: uel quare potestas data sit inpiis in ecclesia, uel quare ab inpiis euangelium agnitum non sit.',
]
documents = [
    'stupebunt iusti super hoc et innocens contra hypocritam suscitabitur',
    'stupebunt iusti super hoc et innocens contra hypocritam suscitabitur',
    'stupebunt iusti super hoc et innocens contra hypocritam suscitabitur',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.4673, 0.4673, 0.4673]])

Evaluation

Metrics

Information Retrieval

• Dataset: laberta-mpmnrl-closed
• Evaluated with InformationRetrievalEvaluator

Training Details

Training Dataset

Unnamed Dataset

• Size: 78,988 training samples
• Columns: anchor, positive_1, positive_2, positive_3, negative_1, negative_2, negative_3, negative_4, negative_5, negative_6, negative_7, negative_8, negative_9, and negative_10
• Approximate statistics based on the first 100 samples:

  	anchor	positive_1	positive_2	positive_3	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7	negative_8	negative_9	negative_10
  type	string	string	string	string	string	string	string	string	string	string	string	string	string	string
  modality	text	text	text	text	text	text	text	text	text	text	text	text	text	text
  details	min: 11 tokensmean: 35.41 tokensmax: 69 tokens	min: 9 tokensmean: 20.08 tokensmax: 41 tokens	min: 9 tokensmean: 19.9 tokensmax: 41 tokens	min: 9 tokensmean: 20.05 tokensmax: 41 tokens	min: 7 tokensmean: 19.58 tokensmax: 40 tokens	min: 8 tokensmean: 19.42 tokensmax: 48 tokens	min: 7 tokensmean: 19.02 tokensmax: 49 tokens	min: 5 tokensmean: 19.86 tokensmax: 38 tokens	min: 9 tokensmean: 19.44 tokensmax: 44 tokens	min: 8 tokensmean: 19.11 tokensmax: 42 tokens	min: 8 tokensmean: 21.0 tokensmax: 40 tokens	min: 10 tokensmean: 20.42 tokensmax: 40 tokens	min: 8 tokensmean: 19.84 tokensmax: 43 tokens	min: 10 tokensmean: 21.13 tokensmax: 42 tokens

• Samples:

  anchor	positive_1	positive_2	positive_3	negative_1	negative_2	negative_3	negative_4	negative_5	negative_6	negative_7	negative_8	negative_9	negative_10
  nam mihi credite, uel potius illi credite, qui ait: quaerite et inuenietis, nec cognitionem desperandam esse et manifestiorem futuram, quam sunt illi numeri.	petite et dabitur vobis quaerite et invenietis pulsate et aperietur vobis	petite et dabitur vobis quaerite et invenietis pulsate et aperietur vobis	petite et dabitur vobis quaerite et invenietis pulsate et aperietur vobis	omnis enim qui petit accipit et qui quaerit invenit et pulsanti aperietur	dixit custos venit mane et nox si quaeritis quaerite convertimini venite	quaerite Dominum dum inveniri potest invocate eum dum prope est	surgam et circuibo civitatem per vicos et plateas quaeram quem diligit anima mea quaesivi illum et non inveni	quaeretis me et invenietis cum quaesieritis me in toto corde vestro	quaerite Dominum et virtutem eius quaerite faciem eius semper	quaerite Dominum et confirmamini quaerite faciem eius semper	et ego vobis dico petite et dabitur vobis quaerite et invenietis pulsate et aperietur vobis	quia haec dicit Dominus domui Israhel quaerite me et vivetis	dicens iustus es Domine et omnia iudicia tua iusta sunt et omnes viae tuae misericordia et veritas et iudicium
  de eo quod scriptum est: in principio fecit deus caelum et terram usque ad id quod scriptum est: et factum est uespere et factum est mane dies una.	appelavitque lucem diem et tenebras noctem factumque est vespere et mane dies unus	in principio creavit Deus caelum et terram	appelavitque lucem diem et tenebras noctem factumque est vespere et mane dies unus	istae generationes caeli et terrae quando creatae sunt in die quo fecit Dominus Deus caelum et terram	qui dixit fiat terra et facta est fiat caelum et factum est	et dixi o Domine loquens locutus es ab initio creaturae in primo die dicens fiat caelum et terra et tuum verbum opus perfecit	sex enim diebus fecit Dominus caelum et terram et mare et omnia quae in eis sunt et requievit in die septimo idcirco benedixit Dominus diei sabbati et sanctificavit eum	dixitque Deus fiat lux et facta est lux	factumque est vespere et mane dies tertius	vocavitque Deus firmamentum caelum et factum est vespere et mane dies secundus	et factum est vespere et mane dies quintus	terminum circumdedit aquis usque dum finiantur lux et tenebrae	et factum est vespere et mane dies quartus
  hoc capitulum legis aduersum esse euangelio stultissimi manichaei arbitrantur dicentes in genesi scriptum esse, quod deus per se ipsum fecerit caelum et terram et lucem, in euangelio autem scriptum esse per dominum nostrum iesum christum fabricatum esse mundum, ubi dictum est: et mundus factus est per ipsum, et mundus illum non cognouit.	in mundo erat et mundus per ipsum factus est et mundus eum non cognovit	in mundo erat et mundus per ipsum factus est et mundus eum non cognovit	in mundo erat et mundus per ipsum factus est et mundus eum non cognovit	in principio creavit Deus caelum et terram	tu fecisti caelum et terram et quicquid caeli ambitu continetur	omnia per ipsum facta sunt et sine ipso factum est nihil quod factum est	et ipse est ante omnes et omnia in ipso constant	deus qui fecit mundum et omnia quae in eo sunt hic caeli et terrae cum sit Dominus non in manufactis templis inhabitat	nam quia in Dei sapientia non cognovit mundus per sapientiam Deum placuit Deo per stultitiam praedicationis salvos facere credentes	invisibilia enim ipsius a creatura mundi per ea quae facta sunt intellecta conspiciuntur sempiterna quoque eius virtus et divinitas ut sint inexcusabiles	et nos vidimus et testificamur quoniam Pater misit Filium salvatorem mundi	igitur perfecti sunt caeli et terra et omnis ornatus eorum	istae generationes caeli et terrae quando creatae sunt in die quo fecit Dominus Deus caelum et terram

• Loss: mpmnrl_loss.MultiplePositiveMultipleNegativeRankingLoss with these parameters:

  {
      "scale": 20.0,
      "n_positives": 3,
      "mini_batch_size": 128,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 256
• per_device_eval_batch_size: 64
• learning_rate: 2e-05
• warmup_ratio: 0.1
• bf16: True
• dataloader_drop_last: True

All Hyperparameters

• overwrite_output_dir: False
• do_predict: False
• prediction_loss_only: True
• per_device_train_batch_size: 256
• 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: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 3.0
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• 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
• bf16: True
• fp16: False
• 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: True
• 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}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• 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
• hub_revision: None
• 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: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Training Time

• Training: 29.4 minutes

Framework Versions

• Python: 3.10.20
• Sentence Transformers: 5.7.0
• Transformers: 4.57.6
• PyTorch: 2.11.0+cu128
• Accelerate: 1.14.0
• Datasets: 4.6.0
• Tokenizers: 0.22.2

Additional Resources

• Training and Finetuning Embedding Models with Sentence Transformers: the end-to-end guide for training or finetuning Sentence Transformer models.
• Introduction to Matryoshka Embedding Models: variable-size embeddings that can be truncated with minimal quality loss.
• Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval: post-training compression of embedding vectors.
• Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video models through the same API.
• Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: train multimodal embedding models, with a Visual Document Retrieval walkthrough.

Citation

BibTeX

Sentence Transformers

@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",
}