rajistics's picture
Add new SentenceTransformer model.
6f04aed verified
metadata
language:
  - en
license: apache-2.0
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:100K<n<1M
  - loss:MultipleNegativesRankingLoss
base_model: microsoft/mpnet-base
metrics:
  - cosine_accuracy
  - dot_accuracy
  - manhattan_accuracy
  - euclidean_accuracy
  - max_accuracy
widget:
  - source_sentence: No animals.
    sentences:
      - It doesn't get it.
      - The person is sleeping.
      - the man is at home sleeping
  - source_sentence: Three boys.
    sentences:
      - All of them
      - Oh, what a fool I feel!
      - The lady is taking a nap.
  - source_sentence: Suggesetions
    sentences:
      - said San'doro.
      - He wears contact lens.
      - a cat sleeps on a pillow
  - source_sentence: It's true.
    sentences:
      - It is true
      - A whale eats the fish.
      - a cat sleeps on a pillow
  - source_sentence: Yes it did.
    sentences:
      - oh does it sure
      - The puppets eat human.
      - the woman is asleep at home
pipeline_tag: sentence-similarity
model-index:
  - name: MPNet base trained on AllNLI triplets
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: all nli dev
          type: all-nli-dev
        metrics:
          - type: cosine_accuracy
            value: 0.8452308626974484
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0.15264277035236937
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 0.8420413122721749
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 0.8399149453219927
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 0.8452308626974484
            name: Max Accuracy
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: all nli test
          type: all-nli-test
        metrics:
          - type: cosine_accuracy
            value: 0.8662430019670146
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0.13269783628385534
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 0.8607958844000605
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 0.8635194431835376
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 0.8662430019670146
            name: Max Accuracy

MPNet base trained on AllNLI triplets

This is a sentence-transformers model finetuned from microsoft/mpnet-base on the sentence-transformers/all-nli dataset. 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: microsoft/mpnet-base
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity
  • Training Dataset:
  • Language: en
  • License: apache-2.0

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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("rajistics/mpnet-base-all-nli-triplet")
# Run inference
sentences = [
    'Yes it did.',
    'oh does it sure',
    'The puppets eat human.',
]
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

Triplet

Metric Value
cosine_accuracy 0.8452
dot_accuracy 0.1526
manhattan_accuracy 0.842
euclidean_accuracy 0.8399
max_accuracy 0.8452

Triplet

Metric Value
cosine_accuracy 0.8662
dot_accuracy 0.1327
manhattan_accuracy 0.8608
euclidean_accuracy 0.8635
max_accuracy 0.8662

Training Details

Training Dataset

sentence-transformers/all-nli

  • Dataset: sentence-transformers/all-nli at d482672
  • Size: 100,000 training samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 7 tokens
    • mean: 10.46 tokens
    • max: 46 tokens
    • min: 6 tokens
    • mean: 12.81 tokens
    • max: 40 tokens
    • min: 5 tokens
    • mean: 13.4 tokens
    • max: 50 tokens
  • Samples:
    anchor positive negative
    A person on a horse jumps over a broken down airplane. A person is outdoors, on a horse. A person is at a diner, ordering an omelette.
    Children smiling and waving at camera There are children present The kids are frowning
    A boy is jumping on skateboard in the middle of a red bridge. The boy does a skateboarding trick. The boy skates down the sidewalk.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Evaluation Dataset

sentence-transformers/all-nli

  • Dataset: sentence-transformers/all-nli at d482672
  • Size: 6,584 evaluation samples
  • Columns: anchor, positive, and negative
  • Approximate statistics based on the first 1000 samples:
    anchor positive negative
    type string string string
    details
    • min: 6 tokens
    • mean: 17.95 tokens
    • max: 63 tokens
    • min: 4 tokens
    • mean: 9.78 tokens
    • max: 29 tokens
    • min: 5 tokens
    • mean: 10.35 tokens
    • max: 29 tokens
  • Samples:
    anchor positive negative
    Two women are embracing while holding to go packages. Two woman are holding packages. The men are fighting outside a deli.
    Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink. Two kids in numbered jerseys wash their hands. Two kids in jackets walk to school.
    A man selling donuts to a customer during a world exhibition event held in the city of Angeles A man selling donuts to a customer. A woman drinks her coffee in a small cafe.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 16
  • per_device_eval_batch_size: 16
  • num_train_epochs: 1
  • warmup_ratio: 0.1
  • fp16: True
  • batch_sampler: no_duplicates

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: 1
  • 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: no_duplicates
  • multi_dataset_batch_sampler: proportional

Training Logs

Epoch Step Training Loss loss all-nli-dev_max_accuracy all-nli-test_max_accuracy
0 0 - - 0.6832 -
0.016 100 2.6596 1.0454 0.7942 -
0.032 200 0.9172 0.8283 0.8071 -
0.048 300 1.3038 0.8209 0.8048 -
0.064 400 0.8026 0.8679 0.8009 -
0.08 500 0.8252 0.9687 0.7906 -
0.096 600 0.9903 1.0263 0.7893 -
0.112 700 0.8719 1.3540 0.7708 -
0.128 800 0.9602 1.4494 0.7622 -
0.144 900 1.0746 1.3507 0.7646 -
0.16 1000 1.0095 1.4260 0.7672 -
0.176 1100 1.1258 1.2828 0.7661 -
0.192 1200 0.9865 1.4121 0.7418 -
0.208 1300 0.8064 1.4133 0.7471 -
0.224 1400 0.8036 1.2877 0.7631 -
0.24 1500 0.899 1.0845 0.7764 -
0.256 1600 0.7128 1.0439 0.7679 -
0.272 1700 0.8902 1.2055 0.7638 -
0.288 1800 0.8587 1.1773 0.7641 -
0.304 1900 0.797 1.0642 0.7898 -
0.32 2000 0.7618 1.0628 0.8232 -
0.336 2100 0.6756 1.1256 0.8155 -
0.352 2200 0.6782 1.0629 0.8382 -
0.368 2300 0.7761 1.1455 0.8071 -
0.384 2400 0.8032 1.0287 0.7884 -
0.4 2500 0.7219 1.0806 0.8323 -
0.416 2600 0.5967 0.9803 0.8180 -
0.432 2700 0.8474 1.3061 0.8223 -
0.448 2800 0.9129 0.9933 0.8136 -
0.464 2900 0.8005 0.8897 0.8235 -
0.48 3000 0.73 0.9185 0.8349 -
0.496 3100 0.7637 0.9318 0.8367 -
0.512 3200 0.5791 0.8514 0.8452 -
0.5123 3202 - - - 0.8662

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.0.0
  • Transformers: 4.41.1
  • PyTorch: 2.3.0+cu121
  • Accelerate: 0.30.1
  • 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",
}

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}
}