tomaarsen/st-v3-test-mpnet-base-allnli-stsb

SentenceTransformer based on microsoft/mpnet-base

This is a sentence-transformers model finetuned from microsoft/mpnet-base on the multi_nli, snli and stsb datasets. 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: 384 tokens
• Output Dimensionality: 768 tokens
• Training Datasets:
  • multi_nli
  • snli
  • stsb
• 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': 384, '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("tomaarsen/st-v3-test-mpnet-base-allnli-stsb")
# Run inference
sentences = [
    "He ran like an athlete.",
    " Then he ran.",
    "yeah i mean just when uh the they military paid for her education",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

Evaluation

Metrics

Semantic Similarity

• Dataset: sts-dev
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7331
spearman_cosine	0.7435
pearson_manhattan	0.7389
spearman_manhattan	0.7474
pearson_euclidean	0.7356
spearman_euclidean	0.7436
pearson_dot	0.7093
spearman_dot	0.715
pearson_max	0.7389
spearman_max	0.7474

Semantic Similarity

• Dataset: sts-test
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6751
spearman_cosine	0.6616
pearson_manhattan	0.6718
spearman_manhattan	0.6589
pearson_euclidean	0.6693
spearman_euclidean	0.6578
pearson_dot	0.649
spearman_dot	0.6335
pearson_max	0.6751
spearman_max	0.6616

Training Details

Training Datasets

multi_nli

• Dataset: multi_nli at da70db2
• Size: 10,000 training samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	min: 4 tokens mean: 26.95 tokens max: 189 tokens	min: 5 tokens mean: 14.11 tokens max: 49 tokens	0: ~34.30% 1: ~28.20% 2: ~37.50%

• Samples:

  premise	hypothesis	label
  Conceptually cream skimming has two basic dimensions - product and geography.	Product and geography are what make cream skimming work.	1
  you know during the season and i guess at at your level uh you lose them to the next level if if they decide to recall the the parent team the Braves decide to call to recall a guy from triple A then a double A guy goes up to replace him and a single A guy goes up to replace him	You lose the things to the following level if the people recall.	0
  One of our number will carry out your instructions minutely.	A member of my team will execute your orders with immense precision.	0

• Loss: sentence_transformers.losses.SoftmaxLoss.SoftmaxLoss

snli

• Dataset: snli at cdb5c3d
• Size: 10,000 training samples
• Columns: snli_premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	snli_premise	hypothesis	label
  type	string	string	int
  details	min: 6 tokens mean: 17.38 tokens max: 52 tokens	min: 4 tokens mean: 10.7 tokens max: 31 tokens	0: ~33.40% 1: ~33.30% 2: ~33.30%

• Samples:

  snli_premise	hypothesis	label
  A person on a horse jumps over a broken down airplane.	A person is training his horse for a competition.	1
  A person on a horse jumps over a broken down airplane.	A person is at a diner, ordering an omelette.	2
  A person on a horse jumps over a broken down airplane.	A person is outdoors, on a horse.	0

• Loss: sentence_transformers.losses.SoftmaxLoss.SoftmaxLoss

stsb

• Dataset: stsb at 8913289
• Size: 5,749 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 6 tokens mean: 10.0 tokens max: 28 tokens	min: 5 tokens mean: 9.95 tokens max: 25 tokens	min: 0.0 mean: 0.54 max: 1.0

• Samples:

  sentence1	sentence2	label
  A plane is taking off.	An air plane is taking off.	1.0
  A man is playing a large flute.	A man is playing a flute.	0.76
  A man is spreading shreded cheese on a pizza.	A man is spreading shredded cheese on an uncooked pizza.	0.76

• Loss: sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Evaluation Datasets

multi_nli

• Dataset: multi_nli at da70db2
• Size: 100 evaluation samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	min: 5 tokens mean: 27.67 tokens max: 138 tokens	min: 6 tokens mean: 13.48 tokens max: 27 tokens	0: ~35.00% 1: ~31.00% 2: ~34.00%

• Samples:

  premise	hypothesis	label
  The new rights are nice enough	Everyone really likes the newest benefits	1
  This site includes a list of all award winners and a searchable database of Government Executive articles.	The Government Executive articles housed on the website are not able to be searched.	2
  uh i don't know i i have mixed emotions about him uh sometimes i like him but at the same times i love to see somebody beat him	I like him for the most part, but would still enjoy seeing someone beat him.	0

• Loss: sentence_transformers.losses.SoftmaxLoss.SoftmaxLoss

snli

• Dataset: snli at cdb5c3d
• Size: 9,842 evaluation samples
• Columns: snli_premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	snli_premise	hypothesis	label
  type	string	string	int
  details	min: 6 tokens mean: 18.44 tokens max: 57 tokens	min: 5 tokens mean: 10.57 tokens max: 25 tokens	0: ~33.10% 1: ~33.30% 2: ~33.60%

• Samples:

  snli_premise	hypothesis	label
  Two women are embracing while holding to go packages.	The sisters are hugging goodbye while holding to go packages after just eating lunch.	1
  Two women are embracing while holding to go packages.	Two woman are holding packages.	0
  Two women are embracing while holding to go packages.	The men are fighting outside a deli.	2

• Loss: sentence_transformers.losses.SoftmaxLoss.SoftmaxLoss

stsb

• Dataset: stsb at 8913289
• Size: 1,500 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	min: 5 tokens mean: 15.1 tokens max: 45 tokens	min: 6 tokens mean: 15.11 tokens max: 53 tokens	min: 0.0 mean: 0.47 max: 1.0

• Samples:

  sentence1	sentence2	label
  A man with a hard hat is dancing.	A man wearing a hard hat is dancing.	1.0
  A young child is riding a horse.	A child is riding a horse.	0.95
  A man is feeding a mouse to a snake.	The man is feeding a mouse to the snake.	1.0

• Loss: sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• seed: 33
• bf16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• prediction_loss_only: False
• 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: 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
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 33
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: True
• 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}
• 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: None
• 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
• 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
• round_robin_sampler: False

Training Logs

Epoch	Step	Training Loss	multi nli loss	snli loss	stsb loss	sts-dev spearman cosine
0.0493	10	0.9199	1.1019	1.1017	0.3016	0.6324
0.0985	20	1.0063	1.1000	1.0966	0.2635	0.6093
0.1478	30	1.002	1.0995	1.0908	0.1766	0.5328
0.1970	40	0.7946	1.0980	1.0913	0.0923	0.5991
0.2463	50	0.9891	1.0967	1.0781	0.0912	0.6457
0.2956	60	0.784	1.0938	1.0699	0.0934	0.6629
0.3448	70	0.6735	1.0940	1.0728	0.0640	0.7538
0.3941	80	0.7713	1.0893	1.0676	0.0612	0.7653
0.4433	90	0.9772	1.0870	1.0573	0.0636	0.7621
0.4926	100	0.8613	1.0862	1.0515	0.0632	0.7583
0.5419	110	0.7528	1.0814	1.0397	0.0617	0.7536
0.5911	120	0.6541	1.0854	1.0329	0.0657	0.7512
0.6404	130	1.051	1.0658	1.0211	0.0607	0.7340
0.6897	140	0.8516	1.0631	1.0171	0.0587	0.7467
0.7389	150	0.7484	1.0563	1.0122	0.0556	0.7537
0.7882	160	0.7368	1.0534	1.0100	0.0588	0.7526
0.8374	170	0.8373	1.0498	1.0030	0.0565	0.7491
0.8867	180	0.9311	1.0387	0.9981	0.0588	0.7302
0.9360	190	0.5445	1.0357	0.9967	0.0565	0.7382
0.9852	200	0.9154	1.0359	0.9964	0.0556	0.7435

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Carbon Emitted: 0.018 kg of CO2
• Hours Used: 0.13 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.11.6
• Sentence Transformers: 2.7.0.dev0
• Transformers: 4.39.3
• PyTorch: 2.1.0+cu121
• Accelerate: 0.26.1
• Datasets: 2.18.0
• Tokenizers: 0.15.2

Citation

BibTeX

Sentence Transformers and SoftmaxLoss

@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",
}