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:
- sentence-transformers/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("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

Dataset: all-nli-dev
Evaluated with TripletEvaluator

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

Triplet

Dataset: all-nli-test
Evaluated with TripletEvaluator

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}
}