Add new SentenceTransformer model.

7da27d4 verified 5 months ago

19.6 kB

	---
	base_model: NbAiLab/nb-sbert-base
	datasets: []
	language: []
	library_name: sentence-transformers
	metrics:
	- cosine_accuracy
	- dot_accuracy
	- manhattan_accuracy
	- euclidean_accuracy
	- max_accuracy
	pipeline_tag: sentence-similarity
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- generated_from_trainer
	- dataset_size:96724
	- loss:TripletLoss
	- loss:MultipleNegativesRankingLoss
	- loss:CoSENTLoss
	widget:
	- source_sentence: Fjerne 60 cm snø fra enebolig på 100 kvadratmeter
	sentences:
	- 'query: montere solskjerming inne'
	- 'query: 150 meter grøfting'
	- 'query: Snømåking på enebolig, 100 kvadratmeter'
	- source_sentence: Renovering av bad
	sentences:
	- Asfaltere innkjørsel
	- Nye garasjeporter m/åpner
	- Totalrenovering av lite bad i Lillestrøm
	- source_sentence: Lite tilbygg til eksisterende bolig
	sentences:
	- Renovere bolig
	- Vi skal pusse opp kjøkken
	- Bygge tilbygg
	- source_sentence: Gulvlegging 6 kvm gang
	sentences:
	- Installere gulvvarme
	- Montering av 8 spotlights brannsikre (4stk. på kjøket) og (2 stk i gangen)
	- Legge parkett i gang
	- source_sentence: Fullføre utvendig forefallent arbeid
	sentences:
	- Bytte av vinduer i hus
	- elektriker på bolig på 120kvm
	- Renovere bad
	model-index:
	- name: SentenceTransformer based on NbAiLab/nb-sbert-base
	results:
	- task:
	type: triplet
	name: Triplet
	dataset:
	name: test triplet evaluation
	type: test-triplet-evaluation
	metrics:
	- type: cosine_accuracy
	value: 0.9859055673009162
	name: Cosine Accuracy
	- type: dot_accuracy
	value: 0.016913319238900635
	name: Dot Accuracy
	- type: manhattan_accuracy
	value: 0.9844961240310077
	name: Manhattan Accuracy
	- type: euclidean_accuracy
	value: 0.9837914023960536
	name: Euclidean Accuracy
	- type: max_accuracy
	value: 0.9859055673009162
	name: Max Accuracy
	---

	# SentenceTransformer based on NbAiLab/nb-sbert-base

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [NbAiLab/nb-sbert-base](https://huggingface.co/NbAiLab/nb-sbert-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: [NbAiLab/nb-sbert-base](https://huggingface.co/NbAiLab/nb-sbert-base) <!-- at revision 56ae460305b0787432b6498e5adc17447e66fe66 -->
	- Maximum Sequence Length: 75 tokens
	- Output Dimensionality: 768 tokens
	- Similarity Function: Cosine Similarity
	<!-- - Training Dataset: Unknown -->
	<!-- - Language: Unknown -->
	<!-- - License: Unknown -->

	### Model Sources

	- Documentation: [Sentence Transformers Documentation](https://sbert.net)
	- Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
	- Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)

	### 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:

	```bash
	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("ostoveland/SBertBaseMittanbudver1")
	# Run inference
	sentences = [
	'Fullføre utvendig forefallent arbeid',
	'elektriker på bolig på 120kvm',
	'Renovere bad',
	]
	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]
	```

	<!--
	### Direct Usage (Transformers)

	<details><summary>Click to see the direct usage in Transformers</summary>

	</details>
	-->

	<!--
	### Downstream Usage (Sentence Transformers)

	You can finetune this model on your own dataset.

	<details><summary>Click to expand</summary>

	</details>
	-->

	<!--
	### Out-of-Scope Use

	List how the model may foreseeably be misused and address what users ought not to do with the model.
	-->

	## Evaluation

	### Metrics

	#### Triplet
	* Dataset: `test-triplet-evaluation`
	* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)

	\| Metric \| Value \|
	\|:-------------------\|:-----------\|
	\| cosine_accuracy \| 0.9859 \|
	\| dot_accuracy \| 0.0169 \|
	\| manhattan_accuracy \| 0.9845 \|
	\| euclidean_accuracy \| 0.9838 \|
	\| max_accuracy \| 0.9859 \|

	<!--
	## Bias, Risks and Limitations

	What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.
	-->

	<!--
	### Recommendations

	What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.
	-->

	## Training Details

	### Training Datasets

	#### Unnamed Dataset


	* Size: 55,426 training samples
	* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence_0 \| sentence_1 \| sentence_2 \|
	\|:--------\|:----------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|
	\| type \| string \| string \| string \|
	\| details \| <ul><li>min: 3 tokens</li><li>mean: 11.65 tokens</li><li>max: 44 tokens</li></ul> \| <ul><li>min: 4 tokens</li><li>mean: 10.92 tokens</li><li>max: 31 tokens</li></ul> \| <ul><li>min: 3 tokens</li><li>mean: 10.49 tokens</li><li>max: 35 tokens</li></ul> \|
	* Samples:
	\| sentence_0 \| sentence_1 \| sentence_2 \|
	\|:----------------------------------------\|:------------------------------------------\|:-----------------------------------------------------------------\|
	\| <code>Bygge støttemur</code> \| <code>Støttemur</code> \| <code>Bytte lås på dörr</code> \|
	\| <code>Understell bord i stål</code> \| <code>Lage stålunderstell til bord</code> \| <code>Bygge trebord</code> \|
	\| <code>Reparasjon vannbåren varme</code> \| <code>Vannbåren varme til enebolig</code> \| <code>* Fortsatt ledig: ombygning av eksisterende kjeller</code> \|
	* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
	```json
	{
	"distance_metric": "TripletDistanceMetric.EUCLIDEAN",
	"triplet_margin": 5
	}
	```

	#### Unnamed Dataset


	* Size: 22,563 training samples
	* Columns: <code>sentence_0</code> and <code>sentence_1</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence_0 \| sentence_1 \|
	\|:--------\|:----------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|
	\| type \| string \| string \|
	\| details \| <ul><li>min: 4 tokens</li><li>mean: 11.09 tokens</li><li>max: 37 tokens</li></ul> \| <ul><li>min: 8 tokens</li><li>mean: 12.94 tokens</li><li>max: 30 tokens</li></ul> \|
	* Samples:
	\| sentence_0 \| sentence_1 \|
	\|:-------------------------------------------------------------------------------------------\|:----------------------------------------\|
	\| <code>utforing av gavlvegg</code> \| <code>query: utforing av vegg</code> \|
	\| <code>Montere kjøkken</code> \| <code>query: kjøkkenmontering</code> \|
	\| <code>Sette opp lettvegg med skyvedør, bygge bod i carport, forlenge tak på carport</code> \| <code>query: bygge bod i carport</code> \|
	* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "cos_sim"
	}
	```

	#### Unnamed Dataset


	* Size: 18,735 training samples
	* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence_0 \| sentence_1 \| label \|
	\|:--------\|:----------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------\|:-----------------------------------------------------------------\|
	\| type \| string \| string \| float \|
	\| details \| <ul><li>min: 3 tokens</li><li>mean: 13.08 tokens</li><li>max: 46 tokens</li></ul> \| <ul><li>min: 4 tokens</li><li>mean: 9.52 tokens</li><li>max: 27 tokens</li></ul> \| <ul><li>min: 0.05</li><li>mean: 0.51</li><li>max: 0.95</li></ul> \|
	* Samples:
	\| sentence_0 \| sentence_1 \| label \|
	\|:---------------------------------------------------------\|:-------------------------------------------\|:------------------\|
	\| <code>Renovering av hus - plantegninger og fasade</code> \| <code>elektriker på bolig på 120kvm</code> \| <code>0.15</code> \|
	\| <code>Blending av innvendig dør</code> \| <code>Tette igjen døråpning</code> \| <code>0.75</code> \|
	\| <code>Fortsatt ledig: Kappe teglstein på pipeløp</code> \| <code>Murearbeid</code> \| <code>0.45</code> \|
	* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "pairwise_cos_sim"
	}
	```

	### Training Hyperparameters
	#### Non-Default Hyperparameters

	- `per_device_train_batch_size`: 32
	- `per_device_eval_batch_size`: 32
	- `num_train_epochs`: 6
	- `multi_dataset_batch_sampler`: round_robin

	#### All Hyperparameters
	<details><summary>Click to expand</summary>

	- `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
	- `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`: 6
	- `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
	- `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
	- `batch_sampler`: batch_sampler
	- `multi_dataset_batch_sampler`: round_robin

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| test-triplet-evaluation_max_accuracy \|
	\|:------:\|:-----:\|:-------------:\|:------------------------------------:\|
	\| 0.2844 \| 500 \| 3.6092 \| - \|
	\| 0.5688 \| 1000 \| 2.9852 \| - \|
	\| 0.8532 \| 1500 \| 2.7542 \| - \|
	\| 1.0011 \| 1760 \| - \| 0.9831 \|
	\| 1.1365 \| 2000 \| 2.5467 \| - \|
	\| 1.4209 \| 2500 \| 2.3263 \| - \|
	\| 1.7053 \| 3000 \| 2.2608 \| - \|
	\| 1.9898 \| 3500 \| 2.2042 \| - \|
	\| 2.0011 \| 3520 \| - \| 0.9859 \|
	\| 2.2730 \| 4000 \| 2.1615 \| - \|
	\| 2.5575 \| 4500 \| 2.0934 \| - \|
	\| 2.8419 \| 5000 \| 2.1226 \| - \|
	\| 3.0011 \| 5280 \| - \| 0.9859 \|
	\| 3.1251 \| 5500 \| 2.1977 \| - \|
	\| 3.4096 \| 6000 \| 2.1209 \| - \|
	\| 3.6940 \| 6500 \| 2.1006 \| - \|
	\| 3.9784 \| 7000 \| 2.1495 \| - \|
	\| 4.0011 \| 7040 \| - \| 0.9859 \|
	\| 4.2617 \| 7500 \| 2.1792 \| - \|
	\| 4.5461 \| 8000 \| 2.0958 \| - \|
	\| 4.8305 \| 8500 \| 2.1065 \| - \|
	\| 5.0011 \| 8800 \| - \| 0.9859 \|
	\| 5.1138 \| 9000 \| 2.1762 \| - \|
	\| 5.3982 \| 9500 \| 2.1347 \| - \|
	\| 5.6826 \| 10000 \| 2.1198 \| - \|
	\| 5.9670 \| 10500 \| 2.1251 \| - \|
	\| 5.9943 \| 10548 \| - \| 0.9859 \|


	### Framework Versions
	- Python: 3.10.12
	- Sentence Transformers: 3.0.1
	- Transformers: 4.41.2
	- PyTorch: 2.3.0+cu121
	- Accelerate: 0.31.0
	- Datasets: 2.20.0
	- 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",
	}
	```

	#### TripletLoss
	```bibtex
	@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
	```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}
	}
	```

	#### CoSENTLoss
	```bibtex
	@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},
	}
	```

	<!--
	## Glossary

	Clearly define terms in order to be accessible across audiences.
	-->

	<!--
	## Model Card Authors

	Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.
	-->

	<!--
	## Model Card Contact

	Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.
	-->