jilangdi's picture
Add new SentenceTransformer model.
53f8929 verified
metadata
language: []
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:5749
  - loss:CosineSimilarityLoss
base_model: distilbert/distilbert-base-uncased
datasets: []
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: A chef is preparing some food.
    sentences:
      - Five birds stand on the snow.
      - A chef prepared a meal.
      - There is no 'still' that is not relative to some other object.
  - source_sentence: A woman is adding oil on fishes.
    sentences:
      - Large cruise ship floating on the water.
      - >-
        It refers to the maximum f-stop (which is defined as the ratio of focal
        length to effective aperture diameter).
      - The woman is cutting potatoes.
  - source_sentence: The player shoots the winning points.
    sentences:
      - Minimum wage laws hurt the least skilled, least productive the most.
      - The basketball player is about to score points for his team.
      - Three televisions, on on the floor, the other two on a box.
  - source_sentence: >-
      Stars form in star-formation regions, which itself develop from molecular
      clouds.
    sentences:
      - >-
        Although I believe Searle is mistaken, I don't think you have found the
        problem.
      - >-
        It may be possible for a solar system like ours to exist outside of a
        galaxy.
      - >-
        A blond-haired child performing on the trumpet in front of a house while
        his younger brother watches.
  - source_sentence: >-
      While Queen may refer to both Queen regent (sovereign) or Queen consort,
      the King has always been the sovereign.
    sentences:
      - At first, I thought this is a bit of a tricky question.
      - A man plays the guitar.
      - >-
        There is a very good reason not to refer to the Queen's spouse as "King"
        - because they aren't the King.
pipeline_tag: sentence-similarity
co2_eq_emissions:
  emissions: 39.55504012195411
  energy_consumed: 0.07407546705036323
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: AMD EPYC 7H12 64-Core Processor
  ram_total_size: 229.14864349365234
  hours_used: 0.147
  hardware_used: 8 x NVIDIA GeForce RTX 3090
model-index:
  - name: SentenceTransformer based on distilbert/distilbert-base-uncased
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.8600140595861905
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8598983710598386
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8243680239709271
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8279844492084353
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.824951390126028
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8287648794439747
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8082965335059282
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8091677829512911
            name: Spearman Dot
          - type: pearson_max
            value: 0.8600140595861905
            name: Pearson Max
          - type: spearman_max
            value: 0.8598983710598386
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.8268457854861329
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8228490860497294
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8156507100664523
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8121071145557491
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8163157326426538
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8129552976781299
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7410469543934988
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7354483817269781
            name: Spearman Dot
          - type: pearson_max
            value: 0.8268457854861329
            name: Pearson Max
          - type: spearman_max
            value: 0.8228490860497294
            name: Spearman Max
          - type: pearson_cosine
            value: 0.8291194587336435
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.826073377213203
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8189784822965882
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8168853954005567
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8196499152175635
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8172865511141795
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7476019871405575
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7396418058035931
            name: Spearman Dot
          - type: pearson_max
            value: 0.8291194587336435
            name: Pearson Max
          - type: spearman_max
            value: 0.826073377213203
            name: Spearman Max

SentenceTransformer based on distilbert/distilbert-base-uncased

This is a sentence-transformers model finetuned from distilbert/distilbert-base-uncased. 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: distilbert/distilbert-base-uncased
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (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("jilangdi/distilbert-base-uncased-sts")
# Run inference
sentences = [
    'While Queen may refer to both Queen regent (sovereign) or Queen consort, the King has always been the sovereign.',
    'There is a very good reason not to refer to the Queen\'s spouse as "King" - because they aren\'t the King.',
    'A man plays the guitar.',
]
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

Semantic Similarity

Metric Value
pearson_cosine 0.86
spearman_cosine 0.8599
pearson_manhattan 0.8244
spearman_manhattan 0.828
pearson_euclidean 0.825
spearman_euclidean 0.8288
pearson_dot 0.8083
spearman_dot 0.8092
pearson_max 0.86
spearman_max 0.8599

Semantic Similarity

Metric Value
pearson_cosine 0.8268
spearman_cosine 0.8228
pearson_manhattan 0.8157
spearman_manhattan 0.8121
pearson_euclidean 0.8163
spearman_euclidean 0.813
pearson_dot 0.741
spearman_dot 0.7354
pearson_max 0.8268
spearman_max 0.8228

Semantic Similarity

Metric Value
pearson_cosine 0.8291
spearman_cosine 0.8261
pearson_manhattan 0.819
spearman_manhattan 0.8169
pearson_euclidean 0.8196
spearman_euclidean 0.8173
pearson_dot 0.7476
spearman_dot 0.7396
pearson_max 0.8291
spearman_max 0.8261

Training Details

Training Dataset

Unnamed Dataset

  • Size: 5,749 training samples
  • Columns: sentence1, sentence2, and score
  • Approximate statistics based on the first 1000 samples:
    sentence1 sentence2 score
    type string string float
    details
    • min: 6 tokens
    • mean: 10.0 tokens
    • max: 28 tokens
    • min: 5 tokens
    • mean: 9.95 tokens
    • max: 25 tokens
    • min: 0.0
    • mean: 0.54
    • max: 1.0
  • Samples:
    sentence1 sentence2 score
    A plane is taking off. An air plane is taking off. 1.0
    A man is playing a large flute. A man is playing a flute. 0.76
    A man is spreading shreded cheese on a pizza. A man is spreading shredded cheese on an uncooked pizza. 0.76
  • Loss: CosineSimilarityLoss with these parameters:
    {
        "loss_fct": "torch.nn.modules.loss.MSELoss"
    }
    

Evaluation Dataset

Unnamed Dataset

  • Size: 1,500 evaluation samples
  • Columns: sentence1, sentence2, and score
  • Approximate statistics based on the first 1000 samples:
    sentence1 sentence2 score
    type string string float
    details
    • min: 5 tokens
    • mean: 15.1 tokens
    • max: 45 tokens
    • min: 6 tokens
    • mean: 15.11 tokens
    • max: 53 tokens
    • min: 0.0
    • mean: 0.47
    • max: 1.0
  • Samples:
    sentence1 sentence2 score
    A man with a hard hat is dancing. A man wearing a hard hat is dancing. 1.0
    A young child is riding a horse. A child is riding a horse. 0.95
    A man is feeding a mouse to a snake. The man is feeding a mouse to the snake. 1.0
  • Loss: CosineSimilarityLoss with these parameters:
    {
        "loss_fct": "torch.nn.modules.loss.MSELoss"
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 16
  • per_device_eval_batch_size: 16
  • num_train_epochs: 4
  • warmup_ratio: 0.1
  • fp16: True

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • 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: 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: 1.0
  • num_train_epochs: 4
  • max_steps: -1
  • lr_scheduler_type: linear
  • 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: False
  • fp16: True
  • 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: proportional

Training Logs

Epoch Step Training Loss loss sts-dev_spearman_cosine sts-test_spearman_cosine
2.2222 100 0.0423 0.0273 0.8592 -
4.0 180 - - - 0.8228
2.2222 100 0.0049 0.0273 0.8599 -
4.0 180 - - - 0.8261

Environmental Impact

Carbon emissions were measured using CodeCarbon.

  • Energy Consumed: 0.074 kWh
  • Carbon Emitted: 0.040 kg of CO2
  • Hours Used: 0.147 hours

Training Hardware

  • On Cloud: No
  • GPU Model: 8 x NVIDIA GeForce RTX 3090
  • CPU Model: AMD EPYC 7H12 64-Core Processor
  • RAM Size: 229.15 GB

Framework Versions

  • Python: 3.10.14
  • Sentence Transformers: 3.0.1
  • Transformers: 4.41.2
  • PyTorch: 2.3.1+cu121
  • Accelerate: 0.31.0
  • Datasets: 2.19.2
  • 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",
}