README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:2560698
  - loss:ModifiedMatryoshkaLoss
base_model: google-bert/bert-base-multilingual-cased
widget:
  - source_sentence: We got off the exit, we found a Shoney's restaurant.
    sentences:
      - >-
        Nos alejamos de la salida, comenzamos a buscar un -- encontramos un
        restaurante Shoney's.
      - >-
        Reduzcan sus emisiones de dióxido de carbono con todo el rango de
        opciones que tienen y luego compren o adquieran compensaciones para el
        resto que no han reducido completamente.
      - >-
        En el momento que nos invitaron a ir allí teníamos sede en San
        Francisco. Así que fuimos de un lado a otro durante el resto de 2009,
        pasando la mitad del tiempo en el condado de Bertie.
  - source_sentence: >-
      And in the audio world that's when the microphone gets too close to its
      sound source, and then it gets in this self-destructive loop that creates
      a very unpleasant sound.
    sentences:
      - >-
        Y, en el mundo del audio, es cuando el micrófono se acerca demasiado a
        su fuente de sonido, y entra en este bucle autodestructivo que crea un
        sonido muy desagradable.
      - >-
        Tiene que ayudarles a alcanzar un compromiso equitativo, y a asegurar
        que una amplia coalición de partidarios locales regionales e
        internacionales les ayuden a implementar el acuerdo.
      - >-
        Y es un renegado y visionario absoluto, y esa es la razón por la que
        ahora vivo y trabajo allí.
  - source_sentence: Figure out some of the other options that are much better.
    sentences:
      - >-
        Así que no sólo estamos reclutando a las multinacionales, les estamos
        dando las herramientas para entregar este bien público, el respeto por
        los Derechos Humanos, y lo estamos verificando.
      - Piensen en otras de las opciones que son mucho mejores.
      - Termina la propiedad comunal de las tierras de reserva.
  - source_sentence: >-
      He is 16 years old, loves hunting and fishing and being outside and doing
      anything with his hands, and so for him, Studio H means that he can stay
      interested in his education through that hands-on engagement.
    sentences:
      - >-
        Tiene 16 años, le encanta cazar, pescar y estar al aire libre y hacer
        tareas manuales. Para él Studio H representa el nexo educativo mediante
        esa motivación práctica.
      - >-
        Carbón capturado y secuestrado -- eso es lo que CCS significa -- es
        probable que se convierta en la aplicación determinante que nos
        posibilitará continuar utilizando combustibles fósiles en un modo que
        sea seguro.
      - El condado de Bertie no es la excepción.
  - source_sentence: There are thousands of these blue dots all over the county.
    sentences:
      - >-
        Me gusta crisis climática en vez de colapso climático, pero de nuevo,
        aquellos de ustedes que son buenos en diseño de marcas, necesito su
        ayuda en esto.
      - >-
        Si miran con cuidado, se ve que su cráneo ha sido sustituido por una
        cúpula transparente de plexiglás así que el funcionamiento de su cerebro
        se puede observar y controlar con luz.
      - Hay miles de estos puntos azules en todo el condado.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - negative_mse
model-index:
  - name: SentenceTransformer based on google-bert/bert-base-multilingual-cased
    results:
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en es
          type: MSE-val-en-es
        metrics:
          - type: negative_mse
            value: -31.070706248283386
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en pt
          type: MSE-val-en-pt
        metrics:
          - type: negative_mse
            value: -31.284737586975098
            name: Negative Mse
      - task:
          type: knowledge-distillation
          name: Knowledge Distillation
        dataset:
          name: MSE val en pt br
          type: MSE-val-en-pt-br
        metrics:
          - type: negative_mse
            value: -29.748335480690002
            name: Negative Mse

SentenceTransformer based on google-bert/bert-base-multilingual-cased

This is a sentence-transformers model finetuned from google-bert/bert-base-multilingual-cased. 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: google-bert/bert-base-multilingual-cased
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (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:

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("luanafelbarros/bert-en-es-pt-matryoshka_v1")
# Run inference
sentences = [
    'There are thousands of these blue dots all over the county.',
    'Hay miles de estos puntos azules en todo el condado.',
    'Me gusta crisis climática en vez de colapso climático, pero de nuevo, aquellos de ustedes que son buenos en diseño de marcas, necesito su ayuda en esto.',
]
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

Knowledge Distillation

• Datasets: MSE-val-en-es, MSE-val-en-pt and MSE-val-en-pt-br
• Evaluated with MSEEvaluator

Metric	MSE-val-en-es	MSE-val-en-pt	MSE-val-en-pt-br
negative_mse	-31.0707	-31.2847	-29.7483

Training Details

Training Dataset

Unnamed Dataset

• Size: 2,560,698 training samples
• Columns: english, non_english, and label
• Approximate statistics based on the first 1000 samples:

  	english	non_english	label
  type	string	string	list
  details	min: 4 tokens mean: 25.46 tokens max: 128 tokens	min: 4 tokens mean: 26.67 tokens max: 128 tokens	size: 768 elements

• Samples:

  english	non_english	label
  And then there are certain conceptual things that can also benefit from hand calculating, but I think they're relatively small in number.	Y luego hay ciertas aspectos conceptuales que pueden beneficiarse del cálculo a mano pero creo que son relativamente pocos.	[-0.015244179405272007, 0.04601434990763664, -0.052873335778713226, 0.03535117208957672, -0.039562877267599106, ...]
  One thing I often ask about is ancient Greek and how this relates.	Algo que pregunto a menudo es sobre el griego antiguo y cómo se relaciona.	[0.0012022971641272306, -0.009590390138328075, -0.032977133989334106, 0.017047710716724396, -0.0028919472824782133, ...]
  See, the thing we're doing right now is we're forcing people to learn mathematics.	Vean, lo que estamos haciendo ahora es forzar a la gente a aprender matemáticas.	[-0.01942082867026329, 0.1043599545955658, 0.009455358609557152, -0.02814248949289322, -0.017036128789186478, ...]

• Loss: main.ModifiedMatryoshkaLoss with these parameters:

  {
      "loss": "MSELoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 6,974 evaluation samples
• Columns: english, non_english, and label
• Approximate statistics based on the first 1000 samples:

  	english	non_english	label
  type	string	string	list
  details	min: 4 tokens mean: 25.68 tokens max: 128 tokens	min: 4 tokens mean: 27.31 tokens max: 128 tokens	size: 768 elements

• Samples:

  english	non_english	label
  Thank you so much, Chris.	Muchas gracias Chris.	[-0.0616779625415802, -0.04450426995754242, -0.03250579163432121, -0.06641441583633423, 0.003981655463576317, ...]
  And it's truly a great honor to have the opportunity to come to this stage twice; I'm extremely grateful.	Y es en verdad un gran honor tener la oportunidad de venir a este escenario por segunda vez. Estoy extremadamente agradecido.	[0.011398598551750183, -0.02500401996076107, -0.009884790517389774, 0.009336900897324085, 0.003082842566072941, ...]
  I have been blown away by this conference, and I want to thank all of you for the many nice comments about what I had to say the other night.	He quedado conmovido por esta conferencia, y deseo agradecer a todos ustedes sus amables comentarios acerca de lo que tenía que decir la otra noche.	[-0.03842132166028023, 0.03635749593377113, -0.02491452544927597, -0.0032229204662144184, 0.0003549510147422552, ...]

• Loss: main.ModifiedMatryoshkaLoss with these parameters:

  {
      "loss": "MSELoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 200
• per_device_eval_batch_size: 200
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True
• label_names: ['label']

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 200
• per_device_eval_batch_size: 200
• 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: 1
• 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: ['label']
• 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
• 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
• 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
• 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

Training Logs

Epoch	Step	Training Loss	Validation Loss	MSE-val-en-es_negative_mse	MSE-val-en-pt_negative_mse	MSE-val-en-pt-br_negative_mse
0.0781	1000	0.0252	0.0231	-24.4152	-24.3443	-25.3002
0.1562	2000	0.0222	0.0212	-25.3038	-25.3995	-24.8563
0.2343	3000	0.021	0.0204	-27.0894	-27.2195	-26.2906
0.3124	4000	0.0204	0.0198	-28.7895	-28.9815	-28.0121
0.3905	5000	0.02	0.0194	-29.1917	-29.3694	-28.0828
0.4686	6000	0.0196	0.0191	-30.0902	-30.2569	-28.9723
0.5467	7000	0.0194	0.0189	-30.3385	-30.5334	-29.1280
0.6248	8000	0.0192	0.0188	-30.6629	-30.8491	-29.4291
0.7029	9000	0.0191	0.0186	-30.6934	-30.8920	-29.4820
0.7810	10000	0.019	0.0185	-31.0134	-31.2205	-29.6545
0.8591	11000	0.0189	0.0185	-31.0993	-31.2950	-29.8062
0.9372	12000	0.0188	0.0184	-31.0707	-31.2847	-29.7483

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.3.1
• Transformers: 4.46.3
• PyTorch: 2.5.1+cu121
• Accelerate: 1.1.1
• Datasets: 3.1.0
• Tokenizers: 0.20.3

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",
}