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 retrieval.

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
Supported Modality: Text
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({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'MPNetModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', '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("vanthuanngo/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)
# tensor([[1.0000, 0.5312, 0.5531],
#         [0.5312, 1.0000, 0.5788],
#         [0.5531, 0.5788, 1.0000]])

Evaluation

Metrics

Triplet

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

Metric	all-nli-dev	all-nli-test
cosine_accuracy	0.908	0.9192

Training Details

Training Dataset

all-nli

Dataset: all-nli
Size: 100,000 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 100 samples:

	anchor	positive	negative
type	string	string	string
modality	text	text	text
details	min: 8 tokens mean: 14.59 tokens max: 30 tokens	min: 6 tokens mean: 13.96 tokens max: 28 tokens	min: 5 tokens mean: 15.1 tokens max: 30 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",
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Evaluation Dataset

all-nli

Dataset: all-nli
Size: 6,584 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 100 samples:

	anchor	positive	negative
type	string	string	string
modality	text	text	text
details	min: 7 tokens mean: 17.57 tokens max: 36 tokens	min: 5 tokens mean: 9.98 tokens max: 28 tokens	min: 5 tokens mean: 10.38 tokens max: 18 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",
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
num_train_epochs: 1
learning_rate: 2e-05
warmup_steps: 0.1
fp16: True
per_device_eval_batch_size: 16
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

per_device_train_batch_size: 16
num_train_epochs: 1
max_steps: -1
learning_rate: 2e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 16
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: False
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	all-nli-dev_cosine_accuracy	all-nli-test_cosine_accuracy
-1	-1	-	-	0.6211	-
0.032	100	3.2838	1.0054	0.7898	-
0.064	200	1.5474	0.7535	0.8259	-
0.096	300	1.2962	0.6850	0.8372	-
0.128	400	1.1566	0.6085	0.8501	-
0.16	500	1.0620	0.5883	0.8616	-
0.192	600	1.0402	0.5365	0.8765	-
0.224	700	0.9202	0.5511	0.8780	-
0.256	800	0.8944	0.5104	0.8879	-
0.288	900	0.9017	0.4762	0.8982	-
0.32	1000	0.8457	0.4782	0.8996	-
0.352	1100	0.8095	0.4818	0.8943	-
0.384	1200	0.7978	0.4674	0.8958	-
0.416	1300	0.7707	0.4732	0.8955	-
0.448	1400	0.7295	0.4571	0.8969	-
0.48	1500	0.7467	0.4579	0.8978	-
0.512	1600	0.7340	0.4436	0.9001	-
0.544	1700	0.6812	0.4444	0.9007	-
0.576	1800	0.6673	0.4434	0.9007	-
0.608	1900	0.6608	0.4347	0.9014	-
0.64	2000	0.6418	0.4249	0.9039	-
0.672	2100	0.7000	0.4317	0.9049	-
0.704	2200	0.6341	0.4296	0.9008	-
0.736	2300	0.6400	0.4265	0.9028	-
0.768	2400	0.6071	0.4333	0.9039	-
0.8	2500	0.6367	0.4310	0.9054	-
0.832	2600	0.5882	0.4221	0.9060	-
0.864	2700	0.5762	0.4217	0.9049	-
0.896	2800	0.5537	0.4170	0.9066	-
0.928	2900	0.6233	0.4176	0.9089	-
0.96	3000	0.4039	0.4157	0.9083	-
0.992	3100	0.0020	0.4151	0.9080	-
1.0	3125	-	0.4151	0.9080	-
-1	-1	-	-	-	0.9192

Training Time

Training: 42.3 minutes

Framework Versions

Python: 3.12.6
Sentence Transformers: 5.5.1
Transformers: 5.10.1
PyTorch: 2.12.0+cu130
Accelerate: 1.13.0
Datasets: 4.8.5
Tokenizers: 0.22.2

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{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

Loading…