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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("luanafelbarros/bert-en-es-pt-matryoshka_v2")
# 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	-32.0329	-32.2705	-30.5909

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: [object Object].ModifiedMatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MSELoss", 3 "matryoshka_dims": [ 4 768, 5 512, 6 256, 7 128, 8 64 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

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: [object Object].ModifiedMatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MSELoss", 3 "matryoshka_dims": [ 4 768, 5 512, 6 256, 7 128, 8 64 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

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
max_steps: 5000
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: 5000
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
0.0781	1000	0.0188	0.0184	-31.6211	-31.8237	-30.2854
0.1562	2000	0.0186	0.0182	-31.6994	-31.9203	-30.3186
0.2343	3000	0.0184	0.0181	-31.8023	-32.0229	-30.3928
0.3124	4000	0.0183	0.0180	-32.0537	-32.2930	-30.6803
0.3905	5000	0.0182	0.0179	-32.0329	-32.2705	-30.5909

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

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",
}

	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