test11 / README.md
ostoveland's picture
Add new SentenceTransformer model.
fa3e358 verified
metadata
base_model: BAAI/bge-m3
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:24000
  - loss:TripletLoss
  - loss:MultipleNegativesRankingLoss
  - loss:CoSENTLoss
widget:
  - source_sentence: installere gulv  lite loft
    sentences:
      - 'query: gjerdeoppsett'
      - 'query: støping av helleplass med skiferheller, 100 kvm'
      - 'query: legge nytt gulv på lite loft'
  - source_sentence: Montering av Baderomsinnredning
    sentences:
      - Installere baderomsmøbler
      - Montere dusjkabinett
      - lage fasadetegninger
  - source_sentence: '* Fortsatt ledig: Klippe gress'
    sentences:
      - Klippe gress i hagen
      - Male hus utvendig
      - Rydde hage
  - source_sentence: Totalrenovering av bad ca 6m2
    sentences:
      - Installere dusjkabinett
      - Pusse opp bad
      - Skifte tak
  - source_sentence: Skorstein/pipe har fått avvik ved inspeksjon av feier
    sentences:
      - Bygge garasje med skråtak
      - Graving og planering av tomt
      - Feier har funnet feil  skorstein
model-index:
  - name: SentenceTransformer based on BAAI/bge-m3
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: test triplet evaluation
          type: test-triplet-evaluation
        metrics:
          - type: cosine_accuracy
            value: 0.9704016913319239
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0.02959830866807611
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 0.9718111346018323
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 0.9704016913319239
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 0.9718111346018323
            name: Max Accuracy

SentenceTransformer based on BAAI/bge-m3

This is a sentence-transformers model finetuned from BAAI/bge-m3. 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

Model Sources

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("ostoveland/test11")
# Run inference
sentences = [
    'Skorstein/pipe har fått avvik ved inspeksjon av feier',
    'Feier har funnet feil på skorstein',
    'Bygge garasje med skråtak',
]
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

Triplet

Metric Value
cosine_accuracy 0.9704
dot_accuracy 0.0296
manhattan_accuracy 0.9718
euclidean_accuracy 0.9704
max_accuracy 0.9718

Training Details

Training Datasets

Unnamed Dataset

  • Size: 8,000 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: 9.89 tokens
    • max: 33 tokens
    • min: 4 tokens
    • mean: 7.9 tokens
    • max: 23 tokens
    • min: 3 tokens
    • mean: 7.21 tokens
    • max: 31 tokens
  • Samples:
    sentence_0 sentence_1 sentence_2
    Rehabilitering av sokkeleleilighet 35 kvadrat Pusse opp sokkeleilighet Bygge ny sokkeleilighet
    Klippe hekk Beskjære hekk Felle trær
    Sette opp hybel kjøkken (KVIK) Montere hybelkjøkken Installere kjøkkeninnredning
  • Loss: TripletLoss with these parameters:
    {
        "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
        "triplet_margin": 5
    }
    

Unnamed Dataset

  • Size: 8,000 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: 3 tokens
    • mean: 9.8 tokens
    • max: 35 tokens
    • min: 7 tokens
    • mean: 11.81 tokens
    • max: 25 tokens
  • Samples:
    sentence_0 sentence_1
    Ønsker pris på ny Mitsubishi Kirigamine 6,6 + montering + demontering query: prisforespørsel på Mitsubishi Kirigamine 6,6 med montering og demontering
    utskifting av store vinduer i enebolig query: vindusbytte i enebolig
    bygging query: konstruksjonsarbeid
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Unnamed Dataset

  • Size: 8,000 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: 3 tokens
    • mean: 10.32 tokens
    • max: 48 tokens
    • min: 3 tokens
    • mean: 8.19 tokens
    • max: 20 tokens
    • min: 0.05
    • mean: 0.5
    • max: 0.95
  • Samples:
    sentence_0 sentence_1 label
    Fliselegging av bad 6m2 Legge fliser på kjøkken 0.55
    Fortsatt ledig: Tilbygg/påbygg Renovering og påbygg 0.65
    Gravejobb i gårdsplass (grus og leire) Gravejobb i hagen 0.65
  • Loss: CoSENTLoss with these parameters:
    {
        "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: 1
  • 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
  • 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: 1
  • 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

Training Logs

Epoch Step Training Loss test-triplet-evaluation_max_accuracy
0.6667 500 5.2587 -
1.0 750 - 0.9718

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

@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

@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},
}