metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:557850
  - loss:MultipleNegativesRankingLoss
base_model: microsoft/mpnet-base
widget:
  - source_sentence: A man is jumping unto his filthy bed.
    sentences:
      - A young male is looking at a newspaper while 2 females walks past him.
      - The bed is dirty.
      - The man is on the moon.
  - source_sentence: >-
      A carefully balanced male stands on one foot near a clean ocean beach
      area.
    sentences:
      - A man is ouside near the beach.
      - Three policemen patrol the streets on bikes
      - A man is sitting on his couch.
  - source_sentence: The man is wearing a blue shirt.
    sentences:
      - Near the trashcan the man stood and smoked
      - >-
        A man in a blue shirt leans on a wall beside a road with a blue van and
        red car with water in the background.
      - A man in a black shirt is playing a guitar.
  - source_sentence: The girls are outdoors.
    sentences:
      - Two girls riding on an amusement part ride.
      - a guy laughs while doing laundry
      - >-
        Three girls are standing together in a room, one is listening, one is
        writing on a wall and the third is talking to them.
  - source_sentence: >-
      A construction worker peeking out of a manhole while his coworker sits on
      the sidewalk smiling.
    sentences:
      - A worker is looking out of a manhole.
      - A man is giving a presentation.
      - The workers are both inside the manhole.
datasets:
  - sentence-transformers/all-nli
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
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: 0.903857837181045
            name: Cosine Accuracy
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: all nli test
          type: all-nli-test
        metrics:
          - type: cosine_accuracy
            value: 0.9154183688909063
            name: Cosine Accuracy

MPNet base trained on AllNLI triplets

This is a sentence-transformers model finetuned from microsoft/mpnet-base on the 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 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- all-nli
Language: en
License: apache-2.0

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("jangikim/mpnet-base-all-nli-triplet")
# Run inference
sentences = [
    'A construction worker peeking out of a manhole while his coworker sits on the sidewalk smiling.',
    'A worker is looking out of a manhole.',
    'The workers are both inside the manhole.',
]
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

Datasets: all-nli-dev and all-nli-test
Evaluated with TripletEvaluator

Metric	all-nli-dev	all-nli-test
cosine_accuracy	0.9039	0.9154

Training Details

Training Dataset

all-nli

Dataset: all-nli at d482672
Size: 557,850 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

all-nli

Dataset: 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
torch_empty_cache_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
include_for_metrics: []
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
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	all-nli-dev_cosine_accuracy	all-nli-test_cosine_accuracy
0	0	-	-	0.6211	-
0.016	100	2.5306	1.0656	0.7749	-
0.032	200	0.9109	0.8554	0.7936	-
0.048	300	1.2488	0.8116	0.8045	-
0.064	400	0.7921	0.8638	0.7980	-
0.08	500	0.7285	1.0676	0.7693	-
0.096	600	0.9519	1.2276	0.7673	-
0.112	700	0.8569	1.2144	0.7749	-
0.128	800	1.3088	1.3994	0.7555	-
0.144	900	1.2227	1.4842	0.7570	-
0.16	1000	1.104	1.1708	0.7629	-
0.176	1100	1.069	1.3670	0.7577	-
0.192	1200	0.9874	1.4517	0.7394	-
0.208	1300	0.7999	1.2141	0.7518	-
0.224	1400	0.776	1.2913	0.7605	-
0.24	1500	1.0367	1.0660	0.7743	-
0.256	1600	0.6614	1.1335	0.7631	-
0.272	1700	1.0519	1.9327	0.7022	-
0.288	1800	1.1647	1.2847	0.7503	-
0.304	1900	0.8315	1.1214	0.7547	-
0.32	2000	0.6953	1.0206	0.8094	-
0.336	2100	0.6189	1.0757	0.8176	-
0.352	2200	0.6519	1.0730	0.8202	-
0.368	2300	0.9357	1.5665	0.7749	-
0.384	2400	1.1421	1.1033	0.7948	-
0.4	2500	0.898	1.2376	0.7795	-
0.416	2600	0.6352	0.9549	0.8237	-
0.432	2700	0.8724	1.2148	0.8085	-
0.448	2800	1.5489	0.9826	0.8111	-
0.464	2900	0.8694	0.9075	0.8202	-
0.48	3000	0.7603	0.8855	0.8392	-
0.496	3100	0.832	0.8339	0.8389	-
0.512	3200	0.6681	0.8775	0.8474	-
0.528	3300	0.6928	0.7839	0.8666	-
0.544	3400	0.5855	0.8005	0.8540	-
0.56	3500	0.5602	0.8667	0.8530	-
0.576	3600	0.6113	0.7388	0.8490	-
0.592	3700	0.5827	0.7075	0.8609	-
0.608	3800	0.5542	0.6796	0.8738	-
0.624	3900	0.5551	0.7380	0.8659	-
0.64	4000	0.7671	0.7355	0.8680	-
0.656	4100	0.9996	0.7832	0.8791	-
0.672	4200	0.9447	0.6966	0.8835	-
0.688	4300	0.722	0.6668	0.8896	-
0.704	4400	0.6671	0.6204	0.8899	-
0.72	4500	0.5729	0.5900	0.8818	-
0.736	4600	0.6538	0.5833	0.8900	-
0.752	4700	0.6969	0.6433	0.8862	-
0.768	4800	0.6354	0.5750	0.8905	-
0.784	4900	0.5742	0.5635	0.8897	-
0.8	5000	0.6725	0.6278	0.8900	-
0.816	5100	0.5477	0.5660	0.8906	-
0.832	5200	0.5927	0.5440	0.8944	-
0.848	5300	0.5112	0.5509	0.8975	-
0.864	5400	0.6042	0.5706	0.8950	-
0.88	5500	0.5593	0.5485	0.8928	-
0.896	5600	0.5597	0.5399	0.9005	-
0.912	5700	0.628	0.5356	0.8996	-
0.928	5800	0.5313	0.5115	0.8981	-
0.944	5900	0.7392	0.5187	0.8985	-
0.96	6000	0.7582	0.5322	0.9031	-
0.976	6100	0.6313	0.5243	0.9033	-
0.992	6200	0.0004	0.5232	0.9039	-
1.0	6250	-	-	-	0.9154

Framework Versions

Python: 3.10.15
Sentence Transformers: 3.3.1
Transformers: 4.46.3
PyTorch: 2.5.1+cu124
Accelerate: 1.1.1
Datasets: 3.1.0
Tokenizers: 0.20.3

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}
}