bert-base-multilingual-uncased-matryoshka-mkqa

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

This is a sentence-transformers model finetuned from google-bert/bert-base-multilingual-uncased. 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-uncased <!-- at revision 7cbf9a625e29989f6b9c6c2fa68234c304f7e38f -->
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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-base-multilingual-uncased-matryoshka-mkqa")
# Run inference
sentences = [
    'who wrote the song i shot the sheriff',
    'i shot the sheriff şarkısını kim besteledi',
    'tr',
]
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

Knowledge Distillation

• Datasets: MSE-val-en-to-ar, MSE-val-en-to-da, MSE-val-en-to-de, MSE-val-en-to-en, MSE-val-en-to-es, MSE-val-en-to-fi, MSE-val-en-to-fr, MSE-val-en-to-he, MSE-val-en-to-hu, MSE-val-en-to-it, MSE-val-en-to-ja, MSE-val-en-to-ko, MSE-val-en-to-km, MSE-val-en-to-ms, MSE-val-en-to-nl, MSE-val-en-to-no, MSE-val-en-to-pl, MSE-val-en-to-pt, MSE-val-en-to-ru, MSE-val-en-to-sv, MSE-val-en-to-th, MSE-val-en-to-tr, MSE-val-en-to-vi, MSE-val-en-to-zh_cn, MSE-val-en-to-zh_hk and MSE-val-en-to-zh_tw
• Evaluated with <code>MSEEvaluator</code>

<!-- ## 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: 234,000 training samples
• Columns: <code>english</code>, <code>non-english</code>, <code>target</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	english	non-english	target	label
  type	string	string	string	list
  details	<ul><li>min: 10 tokens</li><li>mean: 11.48 tokens</li><li>max: 16 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 13.27 tokens</li><li>max: 33 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 3.38 tokens</li><li>max: 7 tokens</li></ul>	<ul><li>size: 768 elements</li></ul>

• Samples:

  english	non-english	target	label
  <code>who plays hope on days of our lives</code>	<code>من الذي يلعب الأمل في أيام حياتنا</code>	<code>ar</code>	<code>[0.2171212136745453, 0.5138550996780396, 0.5517176389694214, -1.0655105113983154, 1.5853567123413086, ...]</code>
  <code>who plays hope on days of our lives</code>	<code>hvem spiller hope i Horton-sagaen</code>	<code>da</code>	<code>[0.2171212136745453, 0.5138550996780396, 0.5517176389694214, -1.0655105113983154, 1.5853567123413086, ...]</code>
  <code>who plays hope on days of our lives</code>	<code>Wer spielt die Hope in Zeit der Sehnsucht?</code>	<code>de</code>	<code>[0.2171212136745453, 0.5138550996780396, 0.5517176389694214, -1.0655105113983154, 1.5853567123413086, ...]</code>

• Loss: <code>MSELoss</code>

Evaluation Dataset

Unnamed Dataset

• Size: 13,000 evaluation samples
• Columns: <code>english</code>, <code>non-english</code>, <code>target</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	english	non-english	target	label
  type	string	string	string	list
  details	<ul><li>min: 10 tokens</li><li>mean: 11.53 tokens</li><li>max: 14 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 13.37 tokens</li><li>max: 50 tokens</li></ul>	<ul><li>min: 3 tokens</li><li>mean: 3.38 tokens</li><li>max: 7 tokens</li></ul>	<ul><li>size: 768 elements</li></ul>

• Samples:

  english	non-english	target	label
  <code>who played prudence on nanny and the professor</code>	<code>من لعب دور "prudence" فى "nanny and the professor"</code>	<code>ar</code>	<code>[-0.2837616801261902, -0.4943353235721588, 0.020107418298721313, 0.7796109318733215, -0.47365888953208923, ...]</code>
  <code>who played prudence on nanny and the professor</code>	<code>hvem spiller prudence på nanny and the professor</code>	<code>da</code>	<code>[-0.2837616801261902, -0.4943353235721588, 0.020107418298721313, 0.7796109318733215, -0.47365888953208923, ...]</code>
  <code>who played prudence on nanny and the professor</code>	<code>Wer spielte Prudence in Nanny and the Professor</code>	<code>de</code>	<code>[-0.2837616801261902, -0.4943353235721588, 0.020107418298721313, 0.7796109318733215, -0.47365888953208923, ...]</code>

• Loss: <code>MSELoss</code>

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• learning_rate: 1e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True

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: 64
• 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: 1e-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: 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
• 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

</details>

Training Logs

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",
}

MSELoss

@inproceedings{reimers-2020-multilingual-sentence-bert,
    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2020",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/2004.09813",
}

<!-- ## 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.* -->