SentenceTransformer based on NbAiLab/nb-sbert-base

This is a sentence-transformers model finetuned from NbAiLab/nb-sbert-base. It maps sentences & paragraphs to a 64-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: NbAiLab/nb-sbert-base
Maximum Sequence Length: 75 tokens
Output Dimensionality: 64 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': 75, '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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("ostoveland/SBertBaseMittanbudver3")
# Run inference
sentences = [
    'Støp og fliselegging av gang',
    'Støp av gulv i kjeller',
    'Reparasjon av råteskader på hus',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 64]

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

Training Details

Training Datasets

Unnamed Dataset

Size: 55,426 training samples
Columns: sentence_0, sentence_1, and sentence_2

Approximate statistics based on the first 1000 samples:

	sentence_0	sentence_1	sentence_2
type	string	string	string
details	min: 3 tokens mean: 11.59 tokens max: 49 tokens	min: 4 tokens mean: 10.69 tokens max: 39 tokens	min: 3 tokens mean: 10.44 tokens max: 39 tokens

Samples:

sentence_0	sentence_1	sentence_2
`Vaskerom`	`Ønsker tilbud på legging av våtromsbelegg lite bad:`	`Verdivurdering av 177 kvm stor enebolig.`
`Bytte lås i leilighet i Obos borettslag, Galgeberg.`	`Bytte postkasselås`	`Helsparkling av betongvegger med tapet`
`Legging av mikrosement`	`Ønsker tilbud på mikrosement`	`Betongsaging - 2 nye utvendige vinduer`

Loss: Matryoshka2dLoss with these parameters:

{
    "loss": "TripletLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1.0,
    "prior_layers_weight": 1.0,
    "kl_div_weight": 1.0,
    "kl_temperature": 0.3,
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": 1
}

Unnamed Dataset

Size: 22,563 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 4 tokens
mean: 10.79 tokens
max: 37 tokens

min: 4 tokens
mean: 10.17 tokens
max: 27 tokens

	sentence_0	sentence_1
type	string	string
details	min: 4 tokens mean: 10.79 tokens max: 37 tokens	min: 4 tokens mean: 10.17 tokens max: 27 tokens

Samples:

sentence_0	sentence_1
`Trefelling - 1 stor gran og en osp`	`trefelling av stor gran og osp`
`Bærebjelker - vurdering`	`sjekk av bærebjelker`
`Mindre graveoppdrag - 30m2 x 40cm dypt`	`mindre gravearbeid`

Loss: Matryoshka2dLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1.0,
    "prior_layers_weight": 1.0,
    "kl_div_weight": 1.0,
    "kl_temperature": 0.3,
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": 1
}

Unnamed Dataset

Size: 18,735 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 4 tokens
mean: 13.64 tokens
max: 55 tokens

min: 4 tokens
mean: 9.56 tokens
max: 27 tokens

min: 0.05
mean: 0.5
max: 0.95

	sentence_0	sentence_1	label
type	string	string	float
details	min: 4 tokens mean: 13.64 tokens max: 55 tokens	min: 4 tokens mean: 9.56 tokens max: 27 tokens	min: 0.05 mean: 0.5 max: 0.95

Samples:

sentence_0	sentence_1	label
`Pusse murvegg`	`Pusse opp vegg`	`0.75`
`Flyttevask av leilighet på 35 kvm`	`Flyttevask av leilighet på 40 kvm`	`0.95`
`Flis 30x 60 - 40m2`	`Flislegging av gulv, 40m2`	`0.75`

Loss: Matryoshka2dLoss with these parameters:

{
    "loss": "CoSENTLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1.0,
    "prior_layers_weight": 1.0,
    "kl_div_weight": 1.0,
    "kl_temperature": 0.3,
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": 1
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 4
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
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: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 4
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: 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: 0
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}
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: round_robin

Training Logs

Epoch	Step	Training Loss
0.2844	500	6.7584
0.5688	1000	7.3305
0.8532	1500	7.3915
1.0006	1759	-
1.1371	2000	7.4073
1.4215	2500	7.0864
1.7059	3000	6.9577
1.9903	3500	7.0965
2.0006	3518	-
2.2742	4000	6.9915
2.5586	4500	6.9164
2.8430	5000	6.8257
3.0006	5277	-
3.1268	5500	7.0359
3.4113	6000	6.9761
3.6957	6500	6.9392
3.9801	7000	6.8352
3.9983	7032	-

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

@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",
}

Matryoshka2dLoss

@misc{li20242d,
    title={2D Matryoshka Sentence Embeddings},
    author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
    year={2024},
    eprint={2402.14776},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

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}
}

TripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

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}
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}

Downloads last month: 283

Model tree for ostoveland/SBertBaseMittanbudver3

Base model

NbAiLab/nb-sbert-base

Finetuned

(15)

this model