Add new SentenceTransformer model

cd3aa07 verified 27 days ago

14 kB

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:852480
  - loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/all-mpnet-base-v2
widget:
  - source_sentence: anal ectopia
    sentences:
      - Acute Chagas disease without heart involvement
      - Ectopic anus
      - chronic inactive rheumatic heart disease
  - source_sentence: lactose intolerance
    sentences:
      - infectious granulomas of the central nervous system, site unspecified
      - lm - [lactose malabsorption]
      - monoblastic leukaemia
  - source_sentence: syndromes with eye anomalies as a major feature
    sentences:
      - Syndromes with eye anomalies as a major feature
      - abnormality of nail surface
      - dermatomyositis
  - source_sentence: dibothriocephalus latus
    sentences:
      - dibothriocephaliasis
      - postprocedural pelvic peritoneal adhesions
      - saccadic pulse-step mismatch
  - source_sentence: indeterminate cell histiocytosis
    sentences:
      - other specified progressive focal atrophies
      - fetal nephrocalcinosis
      - Indeterminate cell histiocytosis
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/all-mpnet-base-v2
Maximum Sequence Length: 32 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

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})
  (2): Normalize({})
)

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("seanfarrell/icd11_synonym_model")
# Run inference
sentences = [
    'indeterminate cell histiocytosis',
    'Indeterminate cell histiocytosis',
    'fetal nephrocalcinosis',
]
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, 1.0000, 0.0856],
#         [1.0000, 1.0000, 0.0856],
#         [0.0856, 0.0856, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 852,480 training samples
Columns: anchor and positive
Approximate statistics based on the first 100 samples:
anchor positive
type string string

modality text text
details
min: 5 tokens
mean: 12.02 tokens
max: 29 tokens

min: 4 tokens
mean: 12.19 tokens
max: 29 tokens

	anchor	positive
type	string	string
modality	text	text
details	min: 5 tokens mean: 12.02 tokens max: 29 tokens	min: 4 tokens mean: 12.19 tokens max: 29 tokens

Samples:

anchor	positive
`fracture, dislocation or subluxation of spine due to birth injury`	`Fracture, dislocation or subluxation of spine due to birth injury`
`malignant neoplasms of bladder`	`Malignant neoplasms of bladder`
`Toxic shock syndrome due to other specified infectious agent`	`toxic shock syndrome due to other specified infectious agent`

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: 512
num_train_epochs: 1
learning_rate: 2e-05
lr_scheduler_type: cosine
warmup_steps: 166
weight_decay: 0.01
bf16: True
per_device_eval_batch_size: 256
dataloader_drop_last: True
dataloader_num_workers: 4

All Hyperparameters

Click to expand

per_device_train_batch_size: 512
num_train_epochs: 1
max_steps: -1
learning_rate: 2e-05
lr_scheduler_type: cosine
lr_scheduler_kwargs: None
warmup_steps: 166
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.01
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: True
fp16: False
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: 256
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: True
dataloader_num_workers: 4
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
dataloader_multiprocessing_context: None
dataloader_in_order: True
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
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}
warmup_ratio: None

Training Logs

Epoch	Step	Training Loss
0.0300	50	0.8889
0.0601	100	0.7854
0.0901	150	0.7348
0.1201	200	0.6554
0.1502	250	0.6254
0.1802	300	0.5845
0.2102	350	0.5857
0.2402	400	0.5496
0.2703	450	0.5358
0.3003	500	0.5186
0.3303	550	0.5068
0.3604	600	0.4737
0.3904	650	0.4635
0.4204	700	0.4621
0.4505	750	0.4498
0.4805	800	0.4508
0.5105	850	0.4135
0.5405	900	0.4298
0.5706	950	0.4096
0.6006	1000	0.3973
0.6306	1050	0.4013
0.6607	1100	0.3847
0.6907	1150	0.3742
0.7207	1200	0.3726
0.7508	1250	0.3738
0.7808	1300	0.3742
0.8108	1350	0.3786
0.8408	1400	0.3710
0.8709	1450	0.3806
0.9009	1500	0.3719
0.9309	1550	0.3721
0.9610	1600	0.3482
0.9910	1650	0.3703

Training Time

Training: 3.2 minutes

Framework Versions

Python: 3.13.15
Sentence Transformers: 5.7.0
Transformers: 5.18.0
PyTorch: 2.11.0+cu130
Accelerate: 1.15.0
Datasets: 4.8.5
Tokenizers: 0.23.2

Additional Resources

Training and Finetuning Embedding Models with Sentence Transformers: the end-to-end guide for training or finetuning Sentence Transformer models.
Introduction to Matryoshka Embedding Models: variable-size embeddings that can be truncated with minimal quality loss.
Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval: post-training compression of embedding vectors.
Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video models through the same API.
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: train multimodal embedding models, with a Visual Document Retrieval walkthrough.

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},
}