SentenceTransformer based on BAAI/bge-m3

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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("adriansanz/sqv-v4-10ep")
# Run inference
sentences = [
    "La persona consumidora presenti la reclamació davant de l'entitat acreditada en un termini superior a un any des de la data en què va presentar la reclamació a l'empresa.",
    "Quin és el paper de l'entitat acreditada en la tramitació d'una reclamació?",
    "Quin és el resultat de la modificació substancial de la llicència d'obres en relació a les autoritzacions administratives?",
]
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	0.0574
cosine_accuracy@3	0.153
cosine_accuracy@5	0.2348
cosine_accuracy@10	0.4174
cosine_precision@1	0.0574
cosine_precision@3	0.051
cosine_precision@5	0.047
cosine_precision@10	0.0417
cosine_recall@1	0.0574
cosine_recall@3	0.153
cosine_recall@5	0.2348
cosine_recall@10	0.4174
cosine_ndcg@10	0.2055
cosine_mrr@10	0.1419
cosine_map@100	0.1652

Information Retrieval

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0557
cosine_accuracy@3	0.16
cosine_accuracy@5	0.24
cosine_accuracy@10	0.407
cosine_precision@1	0.0557
cosine_precision@3	0.0533
cosine_precision@5	0.048
cosine_precision@10	0.0407
cosine_recall@1	0.0557
cosine_recall@3	0.16
cosine_recall@5	0.24
cosine_recall@10	0.407
cosine_ndcg@10	0.2016
cosine_mrr@10	0.1396
cosine_map@100	0.1638

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0696
cosine_accuracy@3	0.167
cosine_accuracy@5	0.2487
cosine_accuracy@10	0.4261
cosine_precision@1	0.0696
cosine_precision@3	0.0557
cosine_precision@5	0.0497
cosine_precision@10	0.0426
cosine_recall@1	0.0696
cosine_recall@3	0.167
cosine_recall@5	0.2487
cosine_recall@10	0.4261
cosine_ndcg@10	0.2158
cosine_mrr@10	0.1526
cosine_map@100	0.1755

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0557
cosine_accuracy@3	0.167
cosine_accuracy@5	0.2522
cosine_accuracy@10	0.4243
cosine_precision@1	0.0557
cosine_precision@3	0.0557
cosine_precision@5	0.0504
cosine_precision@10	0.0424
cosine_recall@1	0.0557
cosine_recall@3	0.167
cosine_recall@5	0.2522
cosine_recall@10	0.4243
cosine_ndcg@10	0.21
cosine_mrr@10	0.1453
cosine_map@100	0.1685

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0609
cosine_accuracy@3	0.1617
cosine_accuracy@5	0.2609
cosine_accuracy@10	0.4435
cosine_precision@1	0.0609
cosine_precision@3	0.0539
cosine_precision@5	0.0522
cosine_precision@10	0.0443
cosine_recall@1	0.0609
cosine_recall@3	0.1617
cosine_recall@5	0.2609
cosine_recall@10	0.4435
cosine_ndcg@10	0.2181
cosine_mrr@10	0.1502
cosine_map@100	0.1722

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0609
cosine_accuracy@3	0.1548
cosine_accuracy@5	0.2452
cosine_accuracy@10	0.4278
cosine_precision@1	0.0609
cosine_precision@3	0.0516
cosine_precision@5	0.049
cosine_precision@10	0.0428
cosine_recall@1	0.0609
cosine_recall@3	0.1548
cosine_recall@5	0.2452
cosine_recall@10	0.4278
cosine_ndcg@10	0.2108
cosine_mrr@10	0.1457
cosine_map@100	0.1676

Training Details

Training Dataset

json

Dataset: json
Size: 5,175 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 5 tokens
mean: 43.23 tokens
max: 117 tokens

min: 10 tokens
mean: 20.25 tokens
max: 46 tokens

	positive	anchor
type	string	string
details	min: 5 tokens mean: 43.23 tokens max: 117 tokens	min: 10 tokens mean: 20.25 tokens max: 46 tokens

Samples:

positive	anchor
`Aquest tràmit us permet consultar informació de les anotacions d'entrada i sortida que hi consten al registre de l'Ajuntament de Sant Quirze del Vallès.`	`Quin és el format de les dades de sortida del tràmit?`
`Tràmit a través del qual la persona interessada posa en coneixement de l’Ajuntament la voluntat de: ... Renunciar a una llicència prèviament atorgada.`	`Quin és el resultat de la renúncia a una llicència urbanística prèviament atorgada?`
`D’acord amb el plànol d'ubicació de parades: Mercat de diumenges a Les Fonts`	`Quin és el plànol d'ubicació de parades del mercat de diumenges a Les Fonts?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        1024,
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

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: 10
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: 10
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
0.4938	10	4.1082	-	-	-	-	-	-
0.9877	20	3.2445	0.1490	0.1440	0.1466	0.1546	0.1249	0.1521
1.4815	30	1.9296	-	-	-	-	-	-
1.9753	40	1.7067	0.1607	0.1548	0.1567	0.1648	0.1448	0.1593
2.4691	50	0.9578	-	-	-	-	-	-
2.9630	60	1.003	0.1640	0.1699	0.1660	0.1695	0.1568	0.1592
3.4568	70	0.6298	-	-	-	-	-	-
3.9506	80	0.7035	-	-	-	-	-	-
4.0	81	-	0.1707	0.1657	0.1769	0.1690	0.1610	0.1719
4.4444	90	0.4606	-	-	-	-	-	-
4.9383	100	0.5131	-	-	-	-	-	-
4.9877	101	-	0.1645	0.1686	0.1669	0.1620	0.1580	0.1722
5.4321	110	0.3748	-	-	-	-	-	-
5.9259	120	0.4799	-	-	-	-	-	-
5.9753	121	-	0.1670	0.1670	0.1725	0.1711	0.1628	0.1715
6.4198	130	0.3237	-	-	-	-	-	-
6.9136	140	0.4132	-	-	-	-	-	-
6.963	141	-	0.1746	0.1757	0.1697	0.1746	0.1655	0.1746
7.4074	150	0.3169	-	-	-	-	-	-
7.9012	160	0.3438	-	-	-	-	-	-
8.0	162	-	0.1692	0.1698	0.1718	0.1735	0.1707	0.1656
8.3951	170	0.2987	-	-	-	-	-	-
8.8889	180	0.3193	-	-	-	-	-	-
8.9877	182	-	0.1703	0.1703	0.1695	0.1710	0.1619	0.1666
9.3827	190	0.2883	-	-	-	-	-	-
9.8765	200	0.3098	0.1652	0.1722	0.1685	0.1755	0.1676	0.1638

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

@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}
}

adriansanz
/

ST-tramits-SQV-004-10ep

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

Model tree for adriansanz/ST-tramits-SQV-004-10ep

Evaluation results