luanafelbarros/bert-en-es-pt-matryoshka_v3

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_v3")
# Run inference
sentences = [
    'All the grayed-out species disappear.',
    'Van a desaparecer todas las especies en gris.',
    'Los diamantes: quizá todos hemos oído hablar de la película "Diamante de sangre".',
]
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	-33.7751	-34.0922	-32.0787

Training Details

Training Dataset

Unnamed Dataset

• Size: 3,560,698 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.	[-0.0616779662668705, -0.044504180550575256, -0.032505787909030914, -0.06641441583633423, 0.003981734160333872, ...]
  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: 2
• 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: 2
• 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
0.0562	1000	0.0283	0.0251	-22.4432	-22.0406	-25.1401
0.1123	2000	0.0241	0.0227	-24.1255	-23.9880	-24.7731
0.1685	3000	0.0224	0.0214	-25.3630	-25.2889	-25.4316
0.2247	4000	0.0214	0.0205	-27.9225	-28.0038	-27.3050
0.2808	5000	0.0206	0.0199	-29.4189	-29.5093	-28.8545
0.3370	6000	0.0202	0.0194	-30.3190	-30.4212	-29.4919
0.3932	7000	0.0198	0.0191	-31.3278	-31.4753	-30.3090
0.4493	8000	0.0195	0.0188	-31.4089	-31.6387	-30.3325
0.5055	9000	0.0193	0.0186	-32.0598	-32.2536	-30.9067
0.5617	10000	0.0191	0.0184	-32.0989	-32.2766	-31.0155
0.6178	11000	0.0189	0.0183	-32.2449	-32.4302	-30.9863
0.6740	12000	0.0187	0.0181	-32.5800	-32.8070	-31.2254
0.7302	13000	0.0186	0.0180	-32.9225	-33.1228	-31.5803
0.7863	14000	0.0185	0.0179	-32.9227	-33.1304	-31.5169
0.8425	15000	0.0184	0.0178	-33.0181	-33.2681	-31.5791
0.8987	16000	0.0183	0.0177	-33.1309	-33.3638	-31.6113
0.9548	17000	0.0182	0.0176	-33.1635	-33.4414	-31.6507
1.0110	18000	0.0181	0.0175	-33.3615	-33.6376	-31.8086
1.0672	19000	0.018	0.0175	-33.5781	-33.8775	-32.0611
1.1233	20000	0.0179	0.0174	-33.5645	-33.8531	-32.0438
1.1795	21000	0.0179	0.0173	-33.6646	-33.9817	-32.0500
1.2357	22000	0.0179	0.0173	-33.7056	-34.0088	-32.1065
1.2918	23000	0.0178	0.0173	-33.7397	-34.0153	-32.1810
1.3480	24000	0.0178	0.0172	-33.7863	-34.0887	-32.1103
1.4042	25000	0.0177	0.0172	-33.7981	-34.0863	-32.1683
1.4603	26000	0.0177	0.0171	-33.7458	-34.0451	-32.0611
1.5165	27000	0.0177	0.0171	-33.7650	-34.0652	-32.1565
1.5727	28000	0.0176	0.0171	-33.7347	-34.0446	-32.0698
1.6288	29000	0.0176	0.0171	-33.8011	-34.1169	-32.0683
1.6850	30000	0.0176	0.0170	-33.7949	-34.1010	-32.1128
1.7412	31000	0.0176	0.0170	-33.7713	-34.0857	-32.1020
1.7973	32000	0.0176	0.0170	-33.8393	-34.1676	-32.1371
1.8535	33000	0.0175	0.0170	-33.7687	-34.0887	-32.0748
1.9097	34000	0.0175	0.0170	-33.7614	-34.0854	-32.0550
1.9659	35000	0.0175	0.0170	-33.7751	-34.0922	-32.0787

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",
}