This is a sentence-transformers model finetuned from BAAI/bge-m3 on the json dataset. It maps sentences & paragraphs to a 1024-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: BAAI/bge-m3
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 1024 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- json

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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("adriansanz/sitges-v2-5ep")
# Run inference
sentences = [
    "Publicada la llista d'infants admesos i exclosos a les estades esportives, s'obre un termini perquè les persones admeses puguin demanar qualsevol canvi a la sol·licitud inicial.",
    'Quin és el període en què es pot demanar un canvi a la sol·licitud inicial?',
    'Quin és el contingut del volant històric de convivència?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Evaluation

Metrics

Information Retrieval

Dataset: dim_1024
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1013
cosine_accuracy@3	0.1857
cosine_accuracy@5	0.2447
cosine_accuracy@10	0.3418
cosine_precision@1	0.1013
cosine_precision@3	0.0619
cosine_precision@5	0.0489
cosine_precision@10	0.0342
cosine_recall@1	0.1013
cosine_recall@3	0.1857
cosine_recall@5	0.2447
cosine_recall@10	0.3418
cosine_ndcg@10	0.205
cosine_mrr@10	0.1632
cosine_map@100	0.1819

Information Retrieval

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.097
cosine_accuracy@3	0.1814
cosine_accuracy@5	0.2616
cosine_accuracy@10	0.3418
cosine_precision@1	0.097
cosine_precision@3	0.0605
cosine_precision@5	0.0523
cosine_precision@10	0.0342
cosine_recall@1	0.097
cosine_recall@3	0.1814
cosine_recall@5	0.2616
cosine_recall@10	0.3418
cosine_ndcg@10	0.2045
cosine_mrr@10	0.1621
cosine_map@100	0.1811

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0844
cosine_accuracy@3	0.1772
cosine_accuracy@5	0.2363
cosine_accuracy@10	0.3418
cosine_precision@1	0.0844
cosine_precision@3	0.0591
cosine_precision@5	0.0473
cosine_precision@10	0.0342
cosine_recall@1	0.0844
cosine_recall@3	0.1772
cosine_recall@5	0.2363
cosine_recall@10	0.3418
cosine_ndcg@10	0.1948
cosine_mrr@10	0.1501
cosine_map@100	0.1683

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0759
cosine_accuracy@3	0.1688
cosine_accuracy@5	0.2363
cosine_accuracy@10	0.3418
cosine_precision@1	0.0759
cosine_precision@3	0.0563
cosine_precision@5	0.0473
cosine_precision@10	0.0342
cosine_recall@1	0.0759
cosine_recall@3	0.1688
cosine_recall@5	0.2363
cosine_recall@10	0.3418
cosine_ndcg@10	0.1889
cosine_mrr@10	0.1425
cosine_map@100	0.1596

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0802
cosine_accuracy@3	0.1646
cosine_accuracy@5	0.2321
cosine_accuracy@10	0.3249
cosine_precision@1	0.0802
cosine_precision@3	0.0549
cosine_precision@5	0.0464
cosine_precision@10	0.0325
cosine_recall@1	0.0802
cosine_recall@3	0.1646
cosine_recall@5	0.2321
cosine_recall@10	0.3249
cosine_ndcg@10	0.1892
cosine_mrr@10	0.1474
cosine_map@100	0.1622

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0464
cosine_accuracy@3	0.1519
cosine_accuracy@5	0.2194
cosine_accuracy@10	0.27
cosine_precision@1	0.0464
cosine_precision@3	0.0506
cosine_precision@5	0.0439
cosine_precision@10	0.027
cosine_recall@1	0.0464
cosine_recall@3	0.1519
cosine_recall@5	0.2194
cosine_recall@10	0.27
cosine_ndcg@10	0.1511
cosine_mrr@10	0.1137
cosine_map@100	0.126

Training Details

Training Dataset

json

Dataset: json
Size: 9,717 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 8 tokens
mean: 49.79 tokens
max: 190 tokens
min: 9 tokens
mean: 20.83 tokens
max: 43 tokens

Samples:

positive	anchor
`L'Ajuntament de Sitges atorga subvencions per a projectes i activitats d'interès públic o social que tinguin per finalitat les activitats esportives federades, escolars o populars desenvolupades per les entitats esportives i esportistes del municipi de Sitges al llarg de l'exercici per la qual es sol·licita la subvenció, i reuneixin les condicions assenyalades a les bases.`	`Quin és el requisit per a obtenir les subvencions per a projectes i activitats esportives?`
`L'Ajuntament de Sitges atorga subvencions per a projectes i activitats d'interès públic o social que tinguin per finalitat les activitats esportives federades, escolars o populars desenvolupades per les entitats esportives i esportistes del municipi de Sitges al llarg de l'exercici per la qual es sol·licita la subvenció, i reuneixin les condicions assenyalades a les bases.`	`Quin és el requisit per a obtenir les subvencions per a projectes i activitats esportives?`
`No es proporciona informació sobre el requisit principal per obtenir el certificat.`	`Quin és el requisit principal per obtenir el certificat?`

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 1024, 5 768, 6 512, 7 256, 8 128, 9 64 10 ], 11 "matryoshka_weights": [ 12 1, 13 1, 14 1, 15 1, 16 1, 17 1 18 ], 19 "n_dims_per_step": -1 20}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 5
lr_scheduler_type: cosine
warmup_ratio: 0.2
bf16: True
tf32: True
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
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: 5
max_steps: -1
lr_scheduler_type: cosine
lr_scheduler_kwargs: {}
warmup_ratio: 0.2
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: True
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: True
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_fused
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
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
eval_use_gather_object: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_1024_cosine_map@100	dim_128_cosine_map@100	dim_256_cosine_map@100	dim_512_cosine_map@100	dim_64_cosine_map@100	dim_768_cosine_map@100
0.2632	10	3.2527	-	-	-	-	-	-
0.5263	20	1.9679	-	-	-	-	-	-
0.7895	30	1.8319	-	-	-	-	-	-
1.0	38	-	0.1819	0.1622	0.1596	0.1683	0.126	0.1811
1.0526	40	1.3358	-	-	-	-	-	-
1.3158	50	1.1166	-	-	-	-	-	-
1.5789	60	0.8715	-	-	-	-	-	-
1.8421	70	0.8801	-	-	-	-	-	-
2.0	76	-	0.1819	0.1622	0.1596	0.1683	0.1260	0.1811
2.1053	80	0.6515	-	-	-	-	-	-
2.3684	90	0.536	-	-	-	-	-	-
2.6316	100	0.4682	-	-	-	-	-	-
2.8947	110	0.4686	-	-	-	-	-	-
3.0	114	-	0.1819	0.1622	0.1596	0.1683	0.1260	0.1811
3.1579	120	0.3161	-	-	-	-	-	-
3.4211	130	0.3554	-	-	-	-	-	-
3.6842	140	0.2886	-	-	-	-	-	-
3.9474	150	0.2616	-	-	-	-	-	-
4.0	152	-	0.1819	0.1622	0.1596	0.1683	0.1260	0.1811
4.2105	160	0.1902	-	-	-	-	-	-
4.4737	170	0.1894	-	-	-	-	-	-
4.7368	180	0.1858	-	-	-	-	-	-
5.0	190	0.1939	0.1819	0.1622	0.1596	0.1683	0.1260	0.1811

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.1.1
Transformers: 4.44.2
PyTorch: 2.4.1+cu121
Accelerate: 0.35.0.dev0
Datasets: 3.0.1
Tokenizers: 0.19.1

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",
}

MatryoshkaLoss

bibtex

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

bibtex

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

	positive	anchor
type	string	string
details	min: 8 tokens mean: 49.79 tokens max: 190 tokens	min: 9 tokens mean: 20.83 tokens max: 43 tokens

adriansanz/ST-tramits-sitges-001-5ep

SentenceTransformer based on BAAI/bge-m3

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Direct Usage (Sentence Transformers)

Evaluation

Metrics

Information Retrieval

Information Retrieval

Information Retrieval

Information Retrieval

Information Retrieval

Information Retrieval

Training Details

Training Dataset

json

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Training Logs

Framework Versions

Citation

BibTeX

Sentence Transformers

MatryoshkaLoss

MultipleNegativesRankingLoss

adriansanz/
ST-tramits-sitges-001-5ep