metadata

base_model: microsoft/mpnet-base
datasets:
  - sentence-transformers/all-nli
language:
  - en
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:10000
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: A man dressed in yellow rescue gear walks in a field.
    sentences:
      - A person messes with some papers.
      - The man is outdoors.
      - The man is bowling.
  - source_sentence: >-
      A young woman tennis player dressed in black carries many tennis balls on
      her racket.
    sentences:
      - A young woman tennis player have many tennis balls.
      - Two men are fishing.
      - A young woman never wears white dress.
  - source_sentence: An older gentleman enjoys a scenic stroll through the countryside.
    sentences:
      - A pirate boards the spaceship.
      - A man walks the countryside.
      - Girls standing at a whiteboard in front of class.
  - source_sentence: >-
      A kid in a red and black coat is laying on his back in the snow with his
      arm in the air and a red sled is next to him.
    sentences:
      - It is a cold day.
      - A girl with her hands in a tub.
      - The kid is on a sugar high.
  - source_sentence: A young boy playing in the grass.
    sentences:
      - A woman in a restaurant.
      - The boy is in the sand.
      - There is a child in the grass.
model-index:
  - name: SentenceTransformer based on microsoft/mpnet-base
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.8037115824193053
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8280034834882098
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8246115594820148
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8246698532463935
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8269079166689298
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8265033797728895
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7864251532602605
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7996406955949785
            name: Spearman Dot
          - type: pearson_max
            value: 0.8269079166689298
            name: Pearson Max
          - type: spearman_max
            value: 0.8280034834882098
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.7555884394670088
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7629008268135758
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7748676335047628
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7596079881029025
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7763712683425394
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7608569856209585
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.735478302248904
            name: Pearson Dot
          - type: spearman_dot
            value: 0.729962390312057
            name: Spearman Dot
          - type: pearson_max
            value: 0.7763712683425394
            name: Pearson Max
          - type: spearman_max
            value: 0.7629008268135758
            name: Spearman Max

SentenceTransformer based on microsoft/mpnet-base

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:
- sentence-transformers/all-nli
Language: en

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': 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("manuel-couto-pintos/mpnet-base-nli-v2")
# Run inference
sentences = [
    'A young boy playing in the grass.',
    'There is a child in the grass.',
    'The boy is in the sand.',
]
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

Dataset: sts-dev
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8037
spearman_cosine	0.828
pearson_manhattan	0.8246
spearman_manhattan	0.8247
pearson_euclidean	0.8269
spearman_euclidean	0.8265
pearson_dot	0.7864
spearman_dot	0.7996
pearson_max	0.8269
spearman_max	0.828

Semantic Similarity

Dataset: sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7556
spearman_cosine	0.7629
pearson_manhattan	0.7749
spearman_manhattan	0.7596
pearson_euclidean	0.7764
spearman_euclidean	0.7609
pearson_dot	0.7355
spearman_dot	0.73
pearson_max	0.7764
spearman_max	0.7629

Training Details

Training Dataset

sentence-transformers/all-nli

Dataset: sentence-transformers/all-nli
Size: 10,000 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
Size: 1,000 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: 128
per_device_eval_batch_size: 128
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: 128
per_device_eval_batch_size: 128
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
eval_on_start: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	loss	sts-dev_spearman_cosine	sts-test_spearman_cosine
0	0	-	0.6320	-
0.1266	10	3.9540	0.7586	-
0.2532	20	1.4977	0.8334	-
0.3797	30	1.3551	0.8398	-
0.5063	40	1.5181	0.8434	-
0.6329	50	1.4927	0.8335	-
0.7595	60	1.5868	0.8287	-
0.8861	70	1.5348	0.8280	-
1.0	79	-	-	0.7629

Framework Versions

Python: 3.10.13
Sentence Transformers: 3.0.1
Transformers: 4.42.1
PyTorch: 2.0.1+cu117
Accelerate: 0.34.0
Datasets: 2.15.0
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",
}

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}
}