SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This sentence-transformers model is a multilingual student model supporting English, Spanish, and Portuguese. For the student, an efficient MiniLM architecture was adopted, prized for its balance of performance and compact size (similar to the architecture used in models like sentence-transformers/all-MiniLM-L6-v2). This student was then trained by distilling knowledge from the high-performance BAAI/bge-small-en-v1.5 English embedding model, which served as the teacher. The resulting model maps sentences & paragraphs to a 384-dimensional dense vector space, suitable for tasks such as semantic textual similarity, semantic search, paraphrase mining, text classification, and clustering.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 128 tokens
Output Dimensionality: 384 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': 384, '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})
  (2): Normalize()
)

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("sentence_transformers_model_id")
# Run inference
sentences = [
    'The Social Security takes another 8.7 billion euros from the Backup Fund',
    'La Seguridad Social saca otros 8.700 millones del Fondo de Reserva',
    'Tiene unos 44.000 millones de barriles de reservas de petroleo, y 54 billones de pies cubicos de reservas de gas natural.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

Datasets: stsb_multi_mt-pt, stsb_multi_mt-en and stsb_multi_mt-es
Evaluated with EmbeddingSimilarityEvaluator

Metric	stsb_multi_mt-pt	stsb_multi_mt-en	stsb_multi_mt-es
pearson_cosine	0.8087	0.836	0.8209
spearman_cosine	0.8245	0.8542	0.8434

Training Details

Training Dataset

Unnamed Dataset

Size: 37,000,000 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: 3 tokens
mean: 21.97 tokens
max: 103 tokens

min: 3 tokens
mean: 23.91 tokens
max: 118 tokens

size: 384 elements

	english	non_english	label
type	string	string	list
details	min: 3 tokens mean: 21.97 tokens max: 103 tokens	min: 3 tokens mean: 23.91 tokens max: 118 tokens	size: 384 elements

Samples:

english	non_english	label
`It also calls on the UN Secretary-General, to present by 15 April to the Security Council “options” for the deployment of an international police force.`	`Asimismo, solicita al Secretario General de las Naciones Unidas que presente al Consejo de Seguridad, antes del 15 de abril, algunas "propuestas" para el despliegue de fuerzas de policía internacional.`	`[-0.04722730070352554, -0.025426536798477173, 0.04836353287100792, -0.04443460330367088, 0.06477425247430801, ...]`
`The Viacom Services governed by this privacy policy are generally not intended for use by children.`	`Los Servicios de Viacom que están regidos por esta política de privacidad, por lo general, no están destinados a menores de edad.`	`[0.0823400542140007, -0.004498262889683247, 0.023361222818493843, -0.07224256545305252, -0.0026566446758806705, ...]`
`- You gotta promise me, doc.`	`- Prometa-me, Doutor.`	`[-0.010264741256833076, 0.004426243249326944, 0.06644191592931747, -0.03601944074034691, 0.009492351673543453, ...]`

Loss: MSELoss

Evaluation Dataset

Unnamed Dataset

Size: 701,304 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: 22.86 tokens
max: 102 tokens

min: 5 tokens
mean: 24.97 tokens
max: 100 tokens

size: 384 elements

	english	non_english	label
type	string	string	list
details	min: 4 tokens mean: 22.86 tokens max: 102 tokens	min: 5 tokens mean: 24.97 tokens max: 100 tokens	size: 384 elements

Samples:

english	non_english	label
`Manufacturer: Rourke Educational Media`	`Gravadora: Rourke Meios Educativos`	`[0.016672328114509583, 0.025462372228503227, 0.024576706811785698, -0.01961815170943737, 0.014413068071007729, ...]`
`What in hells success if it isnt right there in your Stevenson sonnet, which outranks Henleys Apparition, in that Love-cycle, in those sea- poems?`	`¿Qué demonios es el éxito sino lo que hay en su soneto sobre Stevenson, superior a la Aparición de Henley, o en su Ciclo del amor y en sus Poemas del mar?`	`[0.0172938983887434, -0.04857725650072098, -0.05557125806808472, -0.012614483945071697, -0.014296879060566425, ...]`
`Everyone knows, and you know already that you are existing; there is no need, it is futile.`	`Todo mundo sabe, e você já sabe que está existindo; não há nenhuma necessidade disso, isso é fútil.`	`[-0.005980388727039099, -0.02314012683928013, 0.022277960553765297, -0.008318797685205936, -0.0034421393647789955, ...]`

Loss: MSELoss

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 512
per_device_eval_batch_size: 512
gradient_accumulation_steps: 2
learning_rate: 0.0003
num_train_epochs: 8
warmup_ratio: 0.15
bf16: True
dataloader_num_workers: 8

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 512
per_device_eval_batch_size: 512
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 2
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 0.0003
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 8
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.15
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: 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: False
dataloader_num_workers: 8
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}
tp_size: 0
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: None
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
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

Click to expand

Epoch	Step	Training Loss	Validation Loss	stsb_multi_mt-pt_spearman_cosine	stsb_multi_mt-en_spearman_cosine	stsb_multi_mt-es_spearman_cosine
0.0138	500	0.007	-	-	-	-
0.0277	1000	0.0048	-	-	-	-
0.0415	1500	0.0042	-	-	-	-
0.0554	2000	0.0038	-	-	-	-
0.0692	2500	0.0035	-	-	-	-
0.0830	3000	0.0034	-	-	-	-
0.0969	3500	0.0032	-	-	-	-
0.1107	4000	0.0031	-	-	-	-
0.1245	4500	0.003	-	-	-	-
0.1384	5000	0.0029	0.0014	0.3870	0.4251	0.4009
0.1522	5500	0.0027	-	-	-	-
0.1661	6000	0.0026	-	-	-	-
0.1799	6500	0.0025	-	-	-	-
0.1937	7000	0.0024	-	-	-	-
0.2076	7500	0.0024	-	-	-	-
0.2214	8000	0.0023	-	-	-	-
0.2352	8500	0.0022	-	-	-	-
0.2491	9000	0.0021	-	-	-	-
0.2629	9500	0.0021	-	-	-	-
0.2768	10000	0.002	0.0009	0.5930	0.6429	0.6127
0.2906	10500	0.0019	-	-	-	-
0.3044	11000	0.0019	-	-	-	-
0.3183	11500	0.0018	-	-	-	-
0.3321	12000	0.0018	-	-	-	-
0.3459	12500	0.0017	-	-	-	-
0.3598	13000	0.0017	-	-	-	-
0.3736	13500	0.0016	-	-	-	-
0.3875	14000	0.0016	-	-	-	-
0.4013	14500	0.0015	-	-	-	-
0.4151	15000	0.0015	0.0007	0.6874	0.7547	0.7104
0.4290	15500	0.0015	-	-	-	-
0.4428	16000	0.0014	-	-	-	-
0.4566	16500	0.0014	-	-	-	-
0.4705	17000	0.0014	-	-	-	-
0.4843	17500	0.0013	-	-	-	-
0.4982	18000	0.0013	-	-	-	-
0.5120	18500	0.0013	-	-	-	-
0.5258	19000	0.0013	-	-	-	-
0.5397	19500	0.0012	-	-	-	-
0.5535	20000	0.0012	0.0006	0.7185	0.7866	0.7445
0.5673	20500	0.0012	-	-	-	-
0.5812	21000	0.0012	-	-	-	-
0.5950	21500	0.0012	-	-	-	-
0.6089	22000	0.0012	-	-	-	-
0.6227	22500	0.0012	-	-	-	-
0.6365	23000	0.0011	-	-	-	-
0.6504	23500	0.0011	-	-	-	-
0.6642	24000	0.0011	-	-	-	-
0.6781	24500	0.0011	-	-	-	-
0.6919	25000	0.0011	0.0005	0.7381	0.8008	0.7642
0.7057	25500	0.0011	-	-	-	-
0.7196	26000	0.0011	-	-	-	-
0.7334	26500	0.0011	-	-	-	-
0.7472	27000	0.0011	-	-	-	-
0.7611	27500	0.001	-	-	-	-
0.7749	28000	0.001	-	-	-	-
0.7888	28500	0.001	-	-	-	-
0.8026	29000	0.001	-	-	-	-
0.8164	29500	0.001	-	-	-	-
0.8303	30000	0.001	0.0005	0.7555	0.8184	0.7799
0.8441	30500	0.001	-	-	-	-
0.8579	31000	0.001	-	-	-	-
0.8718	31500	0.001	-	-	-	-
0.8856	32000	0.001	-	-	-	-
0.8995	32500	0.001	-	-	-	-
0.9133	33000	0.001	-	-	-	-
0.9271	33500	0.001	-	-	-	-
0.9410	34000	0.001	-	-	-	-
0.9548	34500	0.001	-	-	-	-
0.9686	35000	0.001	0.0004	0.7628	0.8230	0.7883
0.9825	35500	0.001	-	-	-	-
0.9963	36000	0.0009	-	-	-	-
1.0102	36500	0.0009	-	-	-	-
1.0240	37000	0.0009	-	-	-	-
1.0378	37500	0.0009	-	-	-	-
1.0517	38000	0.0009	-	-	-	-
1.0655	38500	0.0009	-	-	-	-
1.0793	39000	0.0009	-	-	-	-
1.0932	39500	0.0009	-	-	-	-
1.1070	40000	0.0009	0.0004	0.7701	0.8313	0.7975
1.1209	40500	0.0009	-	-	-	-
1.1347	41000	0.0009	-	-	-	-
1.1485	41500	0.0009	-	-	-	-
1.1624	42000	0.0009	-	-	-	-
1.1762	42500	0.0009	-	-	-	-
1.1900	43000	0.0009	-	-	-	-
1.2039	43500	0.0009	-	-	-	-
1.2177	44000	0.0009	-	-	-	-
1.2316	44500	0.0009	-	-	-	-
1.2454	45000	0.0009	0.0004	0.7747	0.8344	0.7990
1.2592	45500	0.0009	-	-	-	-
1.2731	46000	0.0009	-	-	-	-
1.2869	46500	0.0009	-	-	-	-
1.3008	47000	0.0009	-	-	-	-
1.3146	47500	0.0009	-	-	-	-
1.3284	48000	0.0009	-	-	-	-
1.3423	48500	0.0009	-	-	-	-
1.3561	49000	0.0009	-	-	-	-
1.3699	49500	0.0009	-	-	-	-
1.3838	50000	0.0009	0.0004	0.7824	0.8372	0.8111
1.3976	50500	0.0009	-	-	-	-
1.4115	51000	0.0009	-	-	-	-
1.4253	51500	0.0009	-	-	-	-
1.4391	52000	0.0009	-	-	-	-
1.4530	52500	0.0009	-	-	-	-
1.4668	53000	0.0009	-	-	-	-
1.4806	53500	0.0009	-	-	-	-
1.4945	54000	0.0008	-	-	-	-
1.5083	54500	0.0008	-	-	-	-
1.5222	55000	0.0008	0.0004	0.7882	0.8426	0.8149
1.5360	55500	0.0008	-	-	-	-
1.5498	56000	0.0008	-	-	-	-
1.5637	56500	0.0008	-	-	-	-
1.5775	57000	0.0008	-	-	-	-
1.5913	57500	0.0008	-	-	-	-
1.6052	58000	0.0008	-	-	-	-
1.6190	58500	0.0008	-	-	-	-
1.6329	59000	0.0008	-	-	-	-
1.6467	59500	0.0008	-	-	-	-
1.6605	60000	0.0008	0.0004	0.7969	0.8453	0.8242
1.6744	60500	0.0008	-	-	-	-
1.6882	61000	0.0008	-	-	-	-
1.7020	61500	0.0008	-	-	-	-
1.7159	62000	0.0008	-	-	-	-
1.7297	62500	0.0008	-	-	-	-
1.7436	63000	0.0008	-	-	-	-
1.7574	63500	0.0008	-	-	-	-
1.7712	64000	0.0008	-	-	-	-
1.7851	64500	0.0008	-	-	-	-
1.7989	65000	0.0008	0.0004	0.7970	0.8473	0.8254
1.8127	65500	0.0008	-	-	-	-
1.8266	66000	0.0008	-	-	-	-
1.8404	66500	0.0008	-	-	-	-
1.8543	67000	0.0008	-	-	-	-
1.8681	67500	0.0008	-	-	-	-
1.8819	68000	0.0008	-	-	-	-
1.8958	68500	0.0008	-	-	-	-
1.9096	69000	0.0008	-	-	-	-
1.9234	69500	0.0008	-	-	-	-
1.9373	70000	0.0008	0.0004	0.7959	0.8459	0.8234
1.9511	70500	0.0008	-	-	-	-
1.9650	71000	0.0008	-	-	-	-
1.9788	71500	0.0008	-	-	-	-
1.9926	72000	0.0008	-	-	-	-
2.0065	72500	0.0008	-	-	-	-
2.0203	73000	0.0008	-	-	-	-
2.0342	73500	0.0008	-	-	-	-
2.0480	74000	0.0008	-	-	-	-
2.0618	74500	0.0008	-	-	-	-
2.0757	75000	0.0008	0.0004	0.7995	0.8489	0.8277
2.0895	75500	0.0008	-	-	-	-
2.1033	76000	0.0008	-	-	-	-
2.1172	76500	0.0008	-	-	-	-
2.1310	77000	0.0008	-	-	-	-
2.1449	77500	0.0008	-	-	-	-
2.1587	78000	0.0008	-	-	-	-
2.1725	78500	0.0008	-	-	-	-
2.1864	79000	0.0008	-	-	-	-
2.2002	79500	0.0008	-	-	-	-
2.2140	80000	0.0008	0.0004	0.7994	0.8462	0.8237
2.2279	80500	0.0008	-	-	-	-
2.2417	81000	0.0008	-	-	-	-
2.2556	81500	0.0008	-	-	-	-
2.2694	82000	0.0008	-	-	-	-
2.2832	82500	0.0008	-	-	-	-
2.2971	83000	0.0008	-	-	-	-
2.3109	83500	0.0008	-	-	-	-
2.3247	84000	0.0008	-	-	-	-
2.3386	84500	0.0008	-	-	-	-
2.3524	85000	0.0008	0.0004	0.8074	0.8499	0.8300
2.3663	85500	0.0008	-	-	-	-
2.3801	86000	0.0008	-	-	-	-
2.3939	86500	0.0008	-	-	-	-
2.4078	87000	0.0008	-	-	-	-
2.4216	87500	0.0008	-	-	-	-
2.4354	88000	0.0008	-	-	-	-
2.4493	88500	0.0008	-	-	-	-
2.4631	89000	0.0008	-	-	-	-
2.4770	89500	0.0008	-	-	-	-
2.4908	90000	0.0008	0.0003	0.8088	0.8506	0.8315
2.5046	90500	0.0008	-	-	-	-
2.5185	91000	0.0008	-	-	-	-
2.5323	91500	0.0008	-	-	-	-
2.5461	92000	0.0008	-	-	-	-
2.5600	92500	0.0008	-	-	-	-
2.5738	93000	0.0008	-	-	-	-
2.5877	93500	0.0008	-	-	-	-
2.6015	94000	0.0008	-	-	-	-
2.6153	94500	0.0008	-	-	-	-
2.6292	95000	0.0008	0.0003	0.8094	0.8518	0.8337
2.6430	95500	0.0008	-	-	-	-
2.6569	96000	0.0008	-	-	-	-
2.6707	96500	0.0008	-	-	-	-
2.6845	97000	0.0008	-	-	-	-
2.6984	97500	0.0008	-	-	-	-
2.7122	98000	0.0008	-	-	-	-
2.7260	98500	0.0008	-	-	-	-
2.7399	99000	0.0008	-	-	-	-
2.7537	99500	0.0008	-	-	-	-
2.7676	100000	0.0008	0.0003	0.8083	0.8514	0.8303
2.7814	100500	0.0008	-	-	-	-
2.7952	101000	0.0008	-	-	-	-
2.8091	101500	0.0008	-	-	-	-
2.8229	102000	0.0008	-	-	-	-
2.8367	102500	0.0008	-	-	-	-
2.8506	103000	0.0008	-	-	-	-
2.8644	103500	0.0008	-	-	-	-
2.8783	104000	0.0008	-	-	-	-
2.8921	104500	0.0008	-	-	-	-
2.9059	105000	0.0008	0.0003	0.8126	0.8521	0.8352
2.9198	105500	0.0008	-	-	-	-
2.9336	106000	0.0008	-	-	-	-
2.9474	106500	0.0008	-	-	-	-
2.9613	107000	0.0008	-	-	-	-
2.9751	107500	0.0008	-	-	-	-
2.9890	108000	0.0008	-	-	-	-
3.0028	108500	0.0008	-	-	-	-
3.0166	109000	0.0008	-	-	-	-
3.0305	109500	0.0008	-	-	-	-
3.0443	110000	0.0008	0.0003	0.8149	0.8515	0.8340
3.0581	110500	0.0008	-	-	-	-
3.0720	111000	0.0008	-	-	-	-
3.0858	111500	0.0008	-	-	-	-
3.0997	112000	0.0008	-	-	-	-
3.1135	112500	0.0008	-	-	-	-
3.1273	113000	0.0008	-	-	-	-
3.1412	113500	0.0008	-	-	-	-
3.1550	114000	0.0008	-	-	-	-
3.1688	114500	0.0008	-	-	-	-
3.1827	115000	0.0008	0.0003	0.8160	0.8527	0.8348
3.1965	115500	0.0008	-	-	-	-
3.2104	116000	0.0008	-	-	-	-
3.2242	116500	0.0008	-	-	-	-
3.2380	117000	0.0008	-	-	-	-
3.2519	117500	0.0008	-	-	-	-
3.2657	118000	0.0008	-	-	-	-
3.2796	118500	0.0008	-	-	-	-
3.2934	119000	0.0008	-	-	-	-
3.3072	119500	0.0008	-	-	-	-
3.3211	120000	0.0008	0.0003	0.8176	0.8524	0.8359
3.3349	120500	0.0008	-	-	-	-
3.3487	121000	0.0008	-	-	-	-
3.3626	121500	0.0008	-	-	-	-
3.3764	122000	0.0008	-	-	-	-
3.3903	122500	0.0008	-	-	-	-
3.4041	123000	0.0008	-	-	-	-
3.4179	123500	0.0008	-	-	-	-
3.4318	124000	0.0008	-	-	-	-
3.4456	124500	0.0008	-	-	-	-
3.4594	125000	0.0008	0.0003	0.8177	0.8541	0.8379
3.4733	125500	0.0008	-	-	-	-
3.4871	126000	0.0008	-	-	-	-
3.5010	126500	0.0008	-	-	-	-
3.5148	127000	0.0008	-	-	-	-
3.5286	127500	0.0008	-	-	-	-
3.5425	128000	0.0008	-	-	-	-
3.5563	128500	0.0008	-	-	-	-
3.5701	129000	0.0008	-	-	-	-
3.5840	129500	0.0008	-	-	-	-
3.5978	130000	0.0008	0.0003	0.8162	0.8520	0.8371
3.6117	130500	0.0008	-	-	-	-
3.6255	131000	0.0008	-	-	-	-
3.6393	131500	0.0008	-	-	-	-
3.6532	132000	0.0008	-	-	-	-
3.6670	132500	0.0008	-	-	-	-
3.6808	133000	0.0008	-	-	-	-
3.6947	133500	0.0008	-	-	-	-
3.7085	134000	0.0008	-	-	-	-
3.7224	134500	0.0008	-	-	-	-
3.7362	135000	0.0008	0.0003	0.8178	0.8542	0.8378
3.7500	135500	0.0008	-	-	-	-
3.7639	136000	0.0008	-	-	-	-
3.7777	136500	0.0008	-	-	-	-
3.7915	137000	0.0008	-	-	-	-
3.8054	137500	0.0008	-	-	-	-
3.8192	138000	0.0008	-	-	-	-
3.8331	138500	0.0008	-	-	-	-
3.8469	139000	0.0008	-	-	-	-
3.8607	139500	0.0008	-	-	-	-
3.8746	140000	0.0008	0.0003	0.8214	0.8542	0.8408
3.8884	140500	0.0008	-	-	-	-
3.9023	141000	0.0008	-	-	-	-
3.9161	141500	0.0007	-	-	-	-
3.9299	142000	0.0007	-	-	-	-
3.9438	142500	0.0008	-	-	-	-
3.9576	143000	0.0008	-	-	-	-
3.9714	143500	0.0007	-	-	-	-
3.9853	144000	0.0007	-	-	-	-
3.9991	144500	0.0007	-	-	-	-
4.0130	145000	0.0007	0.0003	0.8163	0.8521	0.8365
4.0268	145500	0.0007	-	-	-	-
4.0406	146000	0.0007	-	-	-	-
4.0545	146500	0.0007	-	-	-	-
4.0683	147000	0.0007	-	-	-	-
4.0821	147500	0.0007	-	-	-	-
4.0960	148000	0.0007	-	-	-	-
4.1098	148500	0.0007	-	-	-	-
4.1237	149000	0.0007	-	-	-	-
4.1375	149500	0.0007	-	-	-	-
4.1513	150000	0.0007	0.0003	0.8183	0.8537	0.8374
4.1652	150500	0.0007	-	-	-	-
4.1790	151000	0.0007	-	-	-	-
4.1928	151500	0.0007	-	-	-	-
4.2067	152000	0.0007	-	-	-	-
4.2205	152500	0.0007	-	-	-	-
4.2344	153000	0.0007	-	-	-	-
4.2482	153500	0.0007	-	-	-	-
4.2620	154000	0.0007	-	-	-	-
4.2759	154500	0.0007	-	-	-	-
4.2897	155000	0.0007	0.0003	0.8187	0.8525	0.8387
4.3035	155500	0.0007	-	-	-	-
4.3174	156000	0.0007	-	-	-	-
4.3312	156500	0.0007	-	-	-	-
4.3451	157000	0.0007	-	-	-	-
4.3589	157500	0.0007	-	-	-	-
4.3727	158000	0.0007	-	-	-	-
4.3866	158500	0.0007	-	-	-	-
4.4004	159000	0.0007	-	-	-	-
4.4142	159500	0.0007	-	-	-	-
4.4281	160000	0.0007	0.0003	0.8152	0.8516	0.8359
4.4419	160500	0.0007	-	-	-	-
4.4558	161000	0.0007	-	-	-	-
4.4696	161500	0.0007	-	-	-	-
4.4834	162000	0.0007	-	-	-	-
4.4973	162500	0.0007	-	-	-	-
4.5111	163000	0.0007	-	-	-	-
4.5249	163500	0.0007	-	-	-	-
4.5388	164000	0.0007	-	-	-	-
4.5526	164500	0.0007	-	-	-	-
4.5665	165000	0.0007	0.0003	0.8192	0.8532	0.8407
4.5803	165500	0.0007	-	-	-	-
4.5941	166000	0.0007	-	-	-	-
4.6080	166500	0.0007	-	-	-	-
4.6218	167000	0.0007	-	-	-	-
4.6357	167500	0.0007	-	-	-	-
4.6495	168000	0.0007	-	-	-	-
4.6633	168500	0.0007	-	-	-	-
4.6772	169000	0.0007	-	-	-	-
4.6910	169500	0.0007	-	-	-	-
4.7048	170000	0.0007	0.0003	0.8205	0.8526	0.8393
4.7187	170500	0.0007	-	-	-	-
4.7325	171000	0.0007	-	-	-	-
4.7464	171500	0.0007	-	-	-	-
4.7602	172000	0.0007	-	-	-	-
4.7740	172500	0.0007	-	-	-	-
4.7879	173000	0.0007	-	-	-	-
4.8017	173500	0.0007	-	-	-	-
4.8155	174000	0.0007	-	-	-	-
4.8294	174500	0.0007	-	-	-	-
4.8432	175000	0.0007	0.0003	0.8191	0.8524	0.8396
4.8571	175500	0.0007	-	-	-	-
4.8709	176000	0.0007	-	-	-	-
4.8847	176500	0.0007	-	-	-	-
4.8986	177000	0.0007	-	-	-	-
4.9124	177500	0.0007	-	-	-	-
4.9262	178000	0.0007	-	-	-	-
4.9401	178500	0.0007	-	-	-	-
4.9539	179000	0.0007	-	-	-	-
4.9678	179500	0.0007	-	-	-	-
4.9816	180000	0.0007	0.0003	0.8202	0.8538	0.8426
4.9954	180500	0.0007	-	-	-	-
5.0093	181000	0.0007	-	-	-	-
5.0231	181500	0.0007	-	-	-	-
5.0369	182000	0.0007	-	-	-	-
5.0508	182500	0.0007	-	-	-	-
5.0646	183000	0.0007	-	-	-	-
5.0785	183500	0.0007	-	-	-	-
5.0923	184000	0.0007	-	-	-	-
5.1061	184500	0.0007	-	-	-	-
5.1200	185000	0.0007	0.0003	0.8221	0.8548	0.8425
5.1338	185500	0.0007	-	-	-	-
5.1476	186000	0.0007	-	-	-	-
5.1615	186500	0.0007	-	-	-	-
5.1753	187000	0.0007	-	-	-	-
5.1892	187500	0.0007	-	-	-	-
5.2030	188000	0.0007	-	-	-	-
5.2168	188500	0.0007	-	-	-	-
5.2307	189000	0.0007	-	-	-	-
5.2445	189500	0.0007	-	-	-	-
5.2584	190000	0.0007	0.0003	0.8205	0.8530	0.8401
5.2722	190500	0.0007	-	-	-	-
5.2860	191000	0.0007	-	-	-	-
5.2999	191500	0.0007	-	-	-	-
5.3137	192000	0.0007	-	-	-	-
5.3275	192500	0.0007	-	-	-	-
5.3414	193000	0.0007	-	-	-	-
5.3552	193500	0.0007	-	-	-	-
5.3691	194000	0.0007	-	-	-	-
5.3829	194500	0.0007	-	-	-	-
5.3967	195000	0.0007	0.0003	0.8220	0.8526	0.8415
5.4106	195500	0.0007	-	-	-	-
5.4244	196000	0.0007	-	-	-	-
5.4382	196500	0.0007	-	-	-	-
5.4521	197000	0.0007	-	-	-	-
5.4659	197500	0.0007	-	-	-	-
5.4798	198000	0.0007	-	-	-	-
5.4936	198500	0.0007	-	-	-	-
5.5074	199000	0.0007	-	-	-	-
5.5213	199500	0.0007	-	-	-	-
5.5351	200000	0.0007	0.0003	0.8187	0.8525	0.8395
5.5489	200500	0.0007	-	-	-	-
5.5628	201000	0.0007	-	-	-	-
5.5766	201500	0.0007	-	-	-	-
5.5905	202000	0.0007	-	-	-	-
5.6043	202500	0.0007	-	-	-	-
5.6181	203000	0.0007	-	-	-	-
5.6320	203500	0.0007	-	-	-	-
5.6458	204000	0.0007	-	-	-	-
5.6596	204500	0.0007	-	-	-	-
5.6735	205000	0.0007	0.0003	0.8219	0.8531	0.8426
5.6873	205500	0.0007	-	-	-	-
5.7012	206000	0.0007	-	-	-	-
5.7150	206500	0.0007	-	-	-	-
5.7288	207000	0.0007	-	-	-	-
5.7427	207500	0.0007	-	-	-	-
5.7565	208000	0.0007	-	-	-	-
5.7703	208500	0.0007	-	-	-	-
5.7842	209000	0.0007	-	-	-	-
5.7980	209500	0.0007	-	-	-	-
5.8119	210000	0.0007	0.0003	0.8226	0.8535	0.8413
5.8257	210500	0.0007	-	-	-	-
5.8395	211000	0.0007	-	-	-	-
5.8534	211500	0.0007	-	-	-	-
5.8672	212000	0.0007	-	-	-	-
5.8811	212500	0.0007	-	-	-	-
5.8949	213000	0.0007	-	-	-	-
5.9087	213500	0.0007	-	-	-	-
5.9226	214000	0.0007	-	-	-	-
5.9364	214500	0.0007	-	-	-	-
5.9502	215000	0.0007	0.0003	0.8223	0.8542	0.8416
5.9641	215500	0.0007	-	-	-	-
5.9779	216000	0.0007	-	-	-	-
5.9918	216500	0.0007	-	-	-	-
6.0056	217000	0.0007	-	-	-	-
6.0194	217500	0.0007	-	-	-	-
6.0333	218000	0.0007	-	-	-	-
6.0471	218500	0.0007	-	-	-	-
6.0609	219000	0.0007	-	-	-	-
6.0748	219500	0.0007	-	-	-	-
6.0886	220000	0.0007	0.0003	0.8215	0.8538	0.8416
6.1025	220500	0.0007	-	-	-	-
6.1163	221000	0.0007	-	-	-	-
6.1301	221500	0.0007	-	-	-	-
6.1440	222000	0.0007	-	-	-	-
6.1578	222500	0.0007	-	-	-	-
6.1716	223000	0.0007	-	-	-	-
6.1855	223500	0.0007	-	-	-	-
6.1993	224000	0.0007	-	-	-	-
6.2132	224500	0.0007	-	-	-	-
6.2270	225000	0.0007	0.0003	0.8243	0.8545	0.8415
6.2408	225500	0.0007	-	-	-	-
6.2547	226000	0.0007	-	-	-	-
6.2685	226500	0.0007	-	-	-	-
6.2823	227000	0.0007	-	-	-	-
6.2962	227500	0.0007	-	-	-	-
6.3100	228000	0.0007	-	-	-	-
6.3239	228500	0.0007	-	-	-	-
6.3377	229000	0.0007	-	-	-	-
6.3515	229500	0.0007	-	-	-	-
6.3654	230000	0.0007	0.0003	0.8234	0.8539	0.8418
6.3792	230500	0.0007	-	-	-	-
6.3930	231000	0.0007	-	-	-	-
6.4069	231500	0.0007	-	-	-	-
6.4207	232000	0.0007	-	-	-	-
6.4346	232500	0.0007	-	-	-	-
6.4484	233000	0.0007	-	-	-	-
6.4622	233500	0.0007	-	-	-	-
6.4761	234000	0.0007	-	-	-	-
6.4899	234500	0.0007	-	-	-	-
6.5038	235000	0.0007	0.0003	0.8217	0.8537	0.8410
6.5176	235500	0.0007	-	-	-	-
6.5314	236000	0.0007	-	-	-	-
6.5453	236500	0.0007	-	-	-	-
6.5591	237000	0.0007	-	-	-	-
6.5729	237500	0.0007	-	-	-	-
6.5868	238000	0.0007	-	-	-	-
6.6006	238500	0.0007	-	-	-	-
6.6145	239000	0.0007	-	-	-	-
6.6283	239500	0.0007	-	-	-	-
6.6421	240000	0.0007	0.0003	0.8239	0.8537	0.8434
6.6560	240500	0.0007	-	-	-	-
6.6698	241000	0.0007	-	-	-	-
6.6836	241500	0.0007	-	-	-	-
6.6975	242000	0.0007	-	-	-	-
6.7113	242500	0.0007	-	-	-	-
6.7252	243000	0.0007	-	-	-	-
6.7390	243500	0.0007	-	-	-	-
6.7528	244000	0.0007	-	-	-	-
6.7667	244500	0.0007	-	-	-	-
6.7805	245000	0.0007	0.0003	0.8233	0.8534	0.8431
6.7943	245500	0.0007	-	-	-	-
6.8082	246000	0.0007	-	-	-	-
6.8220	246500	0.0007	-	-	-	-
6.8359	247000	0.0007	-	-	-	-
6.8497	247500	0.0007	-	-	-	-
6.8635	248000	0.0007	-	-	-	-
6.8774	248500	0.0007	-	-	-	-
6.8912	249000	0.0007	-	-	-	-
6.9050	249500	0.0007	-	-	-	-
6.9189	250000	0.0007	0.0003	0.8239	0.8543	0.8432
6.9327	250500	0.0007	-	-	-	-
6.9466	251000	0.0007	-	-	-	-
6.9604	251500	0.0007	-	-	-	-
6.9742	252000	0.0007	-	-	-	-
6.9881	252500	0.0007	-	-	-	-
7.0019	253000	0.0007	-	-	-	-
7.0157	253500	0.0007	-	-	-	-
7.0296	254000	0.0007	-	-	-	-
7.0434	254500	0.0007	-	-	-	-
7.0573	255000	0.0007	0.0003	0.8242	0.8541	0.8429
7.0711	255500	0.0007	-	-	-	-
7.0849	256000	0.0007	-	-	-	-
7.0988	256500	0.0007	-	-	-	-
7.1126	257000	0.0007	-	-	-	-
7.1264	257500	0.0007	-	-	-	-
7.1403	258000	0.0007	-	-	-	-
7.1541	258500	0.0007	-	-	-	-
7.1680	259000	0.0007	-	-	-	-
7.1818	259500	0.0007	-	-	-	-
7.1956	260000	0.0007	0.0003	0.8236	0.8537	0.8418
7.2095	260500	0.0007	-	-	-	-
7.2233	261000	0.0007	-	-	-	-
7.2372	261500	0.0007	-	-	-	-
7.2510	262000	0.0007	-	-	-	-
7.2648	262500	0.0007	-	-	-	-
7.2787	263000	0.0007	-	-	-	-
7.2925	263500	0.0007	-	-	-	-
7.3063	264000	0.0007	-	-	-	-
7.3202	264500	0.0007	-	-	-	-
7.3340	265000	0.0007	0.0003	0.8245	0.8536	0.8420
7.3479	265500	0.0007	-	-	-	-
7.3617	266000	0.0007	-	-	-	-
7.3755	266500	0.0007	-	-	-	-
7.3894	267000	0.0007	-	-	-	-
7.4032	267500	0.0007	-	-	-	-
7.4170	268000	0.0007	-	-	-	-
7.4309	268500	0.0007	-	-	-	-
7.4447	269000	0.0007	-	-	-	-
7.4586	269500	0.0007	-	-	-	-
7.4724	270000	0.0007	0.0003	0.8253	0.8545	0.8424
7.4862	270500	0.0007	-	-	-	-
7.5001	271000	0.0007	-	-	-	-
7.5139	271500	0.0007	-	-	-	-
7.5277	272000	0.0007	-	-	-	-
7.5416	272500	0.0007	-	-	-	-
7.5554	273000	0.0007	-	-	-	-
7.5693	273500	0.0007	-	-	-	-
7.5831	274000	0.0007	-	-	-	-
7.5969	274500	0.0007	-	-	-	-
7.6108	275000	0.0007	0.0003	0.8233	0.8534	0.8427
7.6246	275500	0.0007	-	-	-	-
7.6384	276000	0.0007	-	-	-	-
7.6523	276500	0.0007	-	-	-	-
7.6661	277000	0.0007	-	-	-	-
7.6800	277500	0.0007	-	-	-	-
7.6938	278000	0.0007	-	-	-	-
7.7076	278500	0.0007	-	-	-	-
7.7215	279000	0.0007	-	-	-	-
7.7353	279500	0.0007	-	-	-	-
7.7491	280000	0.0007	0.0003	0.8242	0.8541	0.8428
7.7630	280500	0.0007	-	-	-	-
7.7768	281000	0.0007	-	-	-	-
7.7907	281500	0.0007	-	-	-	-
7.8045	282000	0.0007	-	-	-	-
7.8183	282500	0.0007	-	-	-	-
7.8322	283000	0.0007	-	-	-	-
7.8460	283500	0.0007	-	-	-	-
7.8599	284000	0.0007	-	-	-	-
7.8737	284500	0.0007	-	-	-	-
7.8875	285000	0.0007	0.0003	0.8245	0.8542	0.8434
7.9014	285500	0.0007	-	-	-	-
7.9152	286000	0.0007	-	-	-	-
7.9290	286500	0.0007	-	-	-	-
7.9429	287000	0.0007	-	-	-	-
7.9567	287500	0.0007	-	-	-	-
7.9706	288000	0.0007	-	-	-	-
7.9844	288500	0.0007	-	-	-	-
7.9982	289000	0.0007	-	-	-	-

Framework Versions

Python: 3.10.16
Sentence Transformers: 3.3.1
Transformers: 4.51.3
PyTorch: 2.5.1+cu124
Accelerate: 1.2.1
Datasets: 3.2.0
Tokenizers: 0.21.1

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",
}

jvanhoof
/

all-MiniLM-L6-multilingual-v2-en-es-pt-pt-br-v2

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Direct Usage (Sentence Transformers)

Evaluation

Metrics

Semantic Similarity

Training Details

Training Dataset

Unnamed Dataset

Evaluation Dataset

Unnamed Dataset

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Training Logs

Framework Versions

Citation

BibTeX

Sentence Transformers

MSELoss

Model tree for jvanhoof/all-MiniLM-L6-multilingual-v2-en-es-pt-pt-br-v2

Evaluation results