metadata

base_model: microsoft/mpnet-base
datasets:
  - sentence-transformers/all-nli
language:
  - en
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:942
  - loss:CoSENTLoss
widget:
  - source_sentence: >-
      The entire city was surrounded by open countryside with a scattering of
      small villages.
    sentences:
      - Let's leave it.
      - It was proven that Mrs. Vandemeyer and the girl were hiding something.
      - There is only one large village in the countryside.
  - source_sentence: >-
      or just get out and walk uh or even jog a little although i don't do that
      regularly but Washington's a great place to do that
    sentences:
      - '"Washington''s is a great place for a walk or a jog."'
      - A man has some bananas.
      - The sidewalk was deserted.
  - source_sentence: A woman walks by a brick building that's covered with graffiti.
    sentences:
      - When I was in high school, my favorite author was Virginia Wolf.
      - A woman is outside.
      - A man in a photo booth at a carnival.
  - source_sentence: A woman swinging a tennis racket on an outdoor court.
    sentences:
      - A woman walking on an old bridge near a mountain.
      - A woman is playing basketball at the park.
      - Yanomamo eats food.
  - source_sentence: >-
      Several people with parachutes are overlooking a beautiful view of fields
      and hills.
    sentences:
      - Your little girl wrote about how well your farewell activity went.
      - The Crosethe Rue De Rivoli was built for Cardinal Richelieu to live in.
      - Several people mow the grass.

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("amorfati/custom-emb-model")
# Run inference
sentences = [
    'Several people with parachutes are overlooking a beautiful view of fields and hills.',
    'Several people mow the grass.',
    'Your little girl wrote about how well your farewell activity went.',
]
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]

Training Details

Training Dataset

sentence-transformers/all-nli

Dataset: sentence-transformers/all-nli at d482672
Size: 942 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 4 tokens
mean: 21.24 tokens
max: 94 tokens

min: 4 tokens
mean: 12.16 tokens
max: 36 tokens

min: 0.0
mean: 0.51
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 4 tokens mean: 21.24 tokens max: 94 tokens	min: 4 tokens mean: 12.16 tokens max: 36 tokens	min: 0.0 mean: 0.51 max: 1.0

Samples:

sentence1	sentence2	score
`somehow, somewhere.`	`Someplace, in some way.`	`1.0`
`A boy is sitting on a boat with two flags.`	`A blonde person sitting.`	`0.5`
`A asian male suit clad, uses a umbrella to shield himself from the rain.`	`He is late for a meeting.`	`0.5`

Loss: CoSENTLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "pairwise_cos_sim"
}

Evaluation Dataset

sentence-transformers/all-nli

Dataset: sentence-transformers/all-nli at d482672
Size: 120 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: 21.39 tokens
max: 78 tokens

min: 5 tokens
mean: 12.47 tokens
max: 31 tokens

min: 0.0
mean: 0.58
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 5 tokens mean: 21.39 tokens max: 78 tokens	min: 5 tokens mean: 12.47 tokens max: 31 tokens	min: 0.0 mean: 0.58 max: 1.0

Samples:

sentence1	sentence2	score
`When we leave the house we shall be followed again, but not molested, FOR IT IS Mr. BROWN'S PLAN THAT WE ARE TO LEAD HIM.`	`Mr. Brown has made a plan for us to lead him.`	`1.0`
`She hates me."`	`She loves me.`	`0.0`
`That, too, was locked or bolted on the inside.`	`She didn't want anyone to enter the room.`	`0.5`

Loss: CoSENTLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "pairwise_cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1

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: 2e-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: 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: proportional

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.3.0+cu121
Accelerate: 0.32.1
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",
}

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},
}