Add new SentenceTransformer model.

fe6dba7 verified over 1 year ago

29 kB

base_model: projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base
datasets: []
language:
  - ca
library_name: sentence-transformers
license: apache-2.0
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:4173
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      Queixa: Deixar constància de la vostra disconformitat per un mal servei
      (un tracte inapropiat, un temps d'espera excessiu, etc.), sense demanar
      cap indemnització.
    sentences:
      - >-
        Quin és el format de sortida del tràmit de baixa de la llicència de
        gual?
      - Quin és el tipus de venda que es realitza en els mercats setmanals?
      - Quin és el paper de la queixa en la resolució de conflictes?
  - source_sentence: >-
      L'empleat que en l'exercici de les seves tasques tingui assignada la
      funció de conducció de vehicles municipals, pot sol·licitar un ajut per
      les despeses ocasionades per a la renovació del carnet de conduir
      (certificat mèdic i administratiu).
    sentences:
      - Quin és el resultat esperat de les escoles que reben les subvencions?
      - Quin és el requisit per obtenir una autorització d'estacionament?
      - Quin és el requisit per a sol·licitar l'ajut social?
  - source_sentence: >-
      Aportació de documentació. Subvencions per finançar despeses d'hipoteca,
      subministrament i altres serveis i la manca d'ingressos de lloguer de les
      entitats culturals
    sentences:
      - Quin és el propòsit de la documentació?
      - Quin és el paper del públic assistent en el Ple Municipal?
      - >-
        Quin és el paper de l'ajuntament en la renovació del carnet de persona
        cuidadora?
  - source_sentence: >-
      la Fira de la Vila del Llibre de Sitges consistent en un conjunt de
      parades instal·lades al Passeig Marítim
    sentences:
      - >-
        Quin és el paper de la llicència de parcel·lació en la construcció
        d'edificacions?
      - >-
        Quin és l'objectiu del tràmit de participació en processos de selecció
        de personal de l'Ajuntament?
      - >-
        Quin és el lloc on es desenvolupa la Fira de la Vila del Llibre de
        Sitges?
  - source_sentence: >-
      Mitjançant aquest tràmit la persona interessada posa en coneixement de
      l'Ajuntament de Sitges l'inici d'un espectacle públic o activitat
      recreativa de caràcter extraordinari...
    sentences:
      - >-
        Quin és el paper de la persona interessada en la llicència per a
        espectacles públics o activitats recreatives de caràcter extraordinari?
      - >-
        Quin és el paper del Registre de Sol·licitants d'Habitatge amb Protecció
        Oficial en la gestió d'habitatges?
      - >-
        Quin és el tipus de familiars que es tenen en compte per l'ajut
        especial?
model-index:
  - name: BGE SITGES  CAT
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.07327586206896551
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.15732758620689655
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.21767241379310345
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.39439655172413796
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.07327586206896551
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.05244252873563218
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.043534482758620686
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.03943965517241379
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.07327586206896551
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.15732758620689655
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.21767241379310345
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.39439655172413796
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.20125893142070614
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.14385604816639316
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.17098930660026063
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.07327586206896551
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.15086206896551724
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.21767241379310345
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.39439655172413796
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.07327586206896551
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.050287356321839075
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.04353448275862069
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.03943965517241379
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.07327586206896551
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.15086206896551724
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.21767241379310345
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.39439655172413796
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.2016207682773376
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.14438799945265474
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.1715919733142084
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.07327586206896551
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.14870689655172414
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.21120689655172414
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.40086206896551724
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.07327586206896551
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.04956896551724138
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.04224137931034483
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.04008620689655173
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.07327586206896551
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.14870689655172414
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.21120689655172414
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.40086206896551724
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.2021149795452301
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.1433856732348113
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.16973847535400444
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.06896551724137931
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.14655172413793102
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.21767241379310345
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.38146551724137934
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.06896551724137931
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.048850574712643674
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.04353448275862069
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.03814655172413793
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.06896551724137931
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.14655172413793102
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.21767241379310345
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.38146551724137934
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.19535554125135882
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.1398416119321293
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.16597320243564267
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.05603448275862069
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.13793103448275862
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.1939655172413793
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.36853448275862066
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.05603448275862069
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.04597701149425287
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.03879310344827586
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.03685344827586207
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.05603448275862069
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.13793103448275862
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.1939655172413793
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.36853448275862066
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.18225870966588442
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.12688492063492074
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.15425908300208627
            name: Cosine Map@100

BGE SITGES CAT

This is a sentence-transformers model finetuned from projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base. 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: projecte-aina/ST-NLI-ca_paraphrase-multilingual-mpnet-base
Maximum Sequence Length: 128 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Language: ca
License: apache-2.0

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: XLMRobertaModel 
  (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("adriansanz/SITGES-aina4")
# Run inference
sentences = [
    "Mitjançant aquest tràmit la persona interessada posa en coneixement de l'Ajuntament de Sitges l'inici d'un espectacle públic o activitat recreativa de caràcter extraordinari...",
    'Quin és el paper de la persona interessada en la llicència per a espectacles públics o activitats recreatives de caràcter extraordinari?',
    "Quin és el paper del Registre de Sol·licitants d'Habitatge amb Protecció Oficial en la gestió d'habitatges?",
]
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

Information Retrieval

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0733
cosine_accuracy@3	0.1573
cosine_accuracy@5	0.2177
cosine_accuracy@10	0.3944
cosine_precision@1	0.0733
cosine_precision@3	0.0524
cosine_precision@5	0.0435
cosine_precision@10	0.0394
cosine_recall@1	0.0733
cosine_recall@3	0.1573
cosine_recall@5	0.2177
cosine_recall@10	0.3944
cosine_ndcg@10	0.2013
cosine_mrr@10	0.1439
cosine_map@100	0.171

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0733
cosine_accuracy@3	0.1509
cosine_accuracy@5	0.2177
cosine_accuracy@10	0.3944
cosine_precision@1	0.0733
cosine_precision@3	0.0503
cosine_precision@5	0.0435
cosine_precision@10	0.0394
cosine_recall@1	0.0733
cosine_recall@3	0.1509
cosine_recall@5	0.2177
cosine_recall@10	0.3944
cosine_ndcg@10	0.2016
cosine_mrr@10	0.1444
cosine_map@100	0.1716

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0733
cosine_accuracy@3	0.1487
cosine_accuracy@5	0.2112
cosine_accuracy@10	0.4009
cosine_precision@1	0.0733
cosine_precision@3	0.0496
cosine_precision@5	0.0422
cosine_precision@10	0.0401
cosine_recall@1	0.0733
cosine_recall@3	0.1487
cosine_recall@5	0.2112
cosine_recall@10	0.4009
cosine_ndcg@10	0.2021
cosine_mrr@10	0.1434
cosine_map@100	0.1697

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.069
cosine_accuracy@3	0.1466
cosine_accuracy@5	0.2177
cosine_accuracy@10	0.3815
cosine_precision@1	0.069
cosine_precision@3	0.0489
cosine_precision@5	0.0435
cosine_precision@10	0.0381
cosine_recall@1	0.069
cosine_recall@3	0.1466
cosine_recall@5	0.2177
cosine_recall@10	0.3815
cosine_ndcg@10	0.1954
cosine_mrr@10	0.1398
cosine_map@100	0.166

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.056
cosine_accuracy@3	0.1379
cosine_accuracy@5	0.194
cosine_accuracy@10	0.3685
cosine_precision@1	0.056
cosine_precision@3	0.046
cosine_precision@5	0.0388
cosine_precision@10	0.0369
cosine_recall@1	0.056
cosine_recall@3	0.1379
cosine_recall@5	0.194
cosine_recall@10	0.3685
cosine_ndcg@10	0.1823
cosine_mrr@10	0.1269
cosine_map@100	0.1543

Training Details

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: 6
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: False
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
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: 6
max_steps: -1
lr_scheduler_type: cosine
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: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: False
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
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	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
0.3065	5	3.3947	-	-	-	-	-	-
0.6130	10	2.6401	-	-	-	-	-	-
0.9195	15	2.0152	-	-	-	-	-	-
0.9808	16	-	1.3404	0.1639	0.1577	0.1694	0.1503	0.1638
1.2261	20	1.4542	-	-	-	-	-	-
1.5326	25	1.0135	-	-	-	-	-	-
1.8391	30	0.8437	-	-	-	-	-	-
1.9617	32	-	0.9436	0.1556	0.1596	0.1600	0.1467	0.1701
2.1456	35	0.7676	-	-	-	-	-	-
2.4521	40	0.5126	-	-	-	-	-	-
2.7586	45	0.4358	-	-	-	-	-	-
2.9425	48	-	0.7852	0.1650	0.1693	0.1720	0.1511	0.1686
3.0651	50	0.4192	-	-	-	-	-	-
3.3716	55	0.3429	-	-	-	-	-	-
3.6782	60	0.3025	-	-	-	-	-	-
3.9847	65	0.2863	0.7401	0.1646	0.1706	0.1759	0.1480	0.1694
4.2912	70	0.2474	-	-	-	-	-	-
4.5977	75	0.2324	-	-	-	-	-	-
4.9042	80	0.2344	-	-	-	-	-	-
4.9655	81	-	0.7217	0.1663	0.1699	0.1767	0.1512	0.1696
5.2107	85	0.2181	-	-	-	-	-	-
5.5172	90	0.2116	-	-	-	-	-	-
5.8238	95	0.1926	-	-	-	-	-	-
5.8851	96	-	0.7154	0.166	0.1697	0.1716	0.1543	0.171

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.42.3
PyTorch: 2.3.1+cu121
Accelerate: 0.32.1
Datasets: 2.20.0
Tokenizers: 0.19.1

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",
}

MatryoshkaLoss

@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

@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}
}