metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:10053
  - loss:MultipleNegativesRankingLoss
base_model: allenai/specter2_base
widget:
  - source_sentence: Fluorescence quenching of tryptophan residues
    sentences:
      - 'Fluorescence of buried tyrosine residues in proteins. '
      - >-
        A fluorescence quenching study of tryptophanyl residues of (Ca2+ +
        Mg2+)-ATPase from sarcoplasmic reticulum. 
      - 'Some hormonal influences on the acetylation of sulfanilamide in vivo. '
  - source_sentence: Human migration to the Americas
    sentences:
      - >-
        Homo sapiens in the Americas. Overview of the earliest human expansion
        in the New World. 
      - >-
        Profiles of College Drinkers Defined by Alcohol Behaviors at the Week
        Level: Replication Across Semesters and Prospective Associations With
        Hazardous Drinking and Dependence-Related Symptoms. 
      - 'Human migration. '
  - source_sentence: Human Mobility Prediction
    sentences:
      - 'Human mobility prediction from region functions with taxi trajectories. '
      - 'Understanding Human Mobility from Twitter. '
      - >-
        Ovarian cancer gene therapy using HPV-16 pseudovirion carrying the
        HSV-tk gene. 
  - source_sentence: Nevirapine Resistance
    sentences:
      - 'Nevirapine toxicity. '
      - 'Recognizing rhenium. '
      - 'Update on nevirapine: quest for a niche. '
  - source_sentence: EHL tendon reconstruction
    sentences:
      - >-
        A Combined Surgical Approach for Extensor Hallucis Longus
        Reconstruction: Two Case Reports. 
      - 'Flexor tendon reconstruction. '
      - 'Noble gases and neuroprotection: summary of current evidence. '
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - dot_accuracy
  - manhattan_accuracy
  - euclidean_accuracy
  - max_accuracy
model-index:
  - name: SentenceTransformer based on allenai/specter2_base
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: triplet dev
          type: triplet-dev
        metrics:
          - type: cosine_accuracy
            value: 0.573
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0.455
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 0.576
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 0.577
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 0.577
            name: Max Accuracy

SentenceTransformer based on allenai/specter2_base

This is a sentence-transformers model finetuned from allenai/specter2_base on the json 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: allenai/specter2_base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- json

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: PeftModelForFeatureExtraction 
  (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("sentence_transformers_model_id")
# Run inference
sentences = [
    'EHL tendon reconstruction',
    'A Combined Surgical Approach for Extensor Hallucis Longus Reconstruction: Two Case Reports. ',
    'Flexor tendon reconstruction. ',
]
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: triplet-dev
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.573
dot_accuracy	0.455
manhattan_accuracy	0.576
euclidean_accuracy	0.577
max_accuracy	0.577

Training Details

Training Dataset

json

Dataset: json
Size: 10,053 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 4 tokens mean: 7.54 tokens max: 24 tokens	min: 4 tokens mean: 20.11 tokens max: 63 tokens	min: 3 tokens mean: 12.36 tokens max: 48 tokens

Samples:

anchor	positive	negative
`COM-induced secretome changes in U937 monocytes`	`Characterization of calcium oxalate crystal-induced changes in the secretome of U937 human monocytes.`	`Monocytes.`
`Metamaterials`	`Sound attenuation optimization using metaporous materials tuned on exceptional points.`	`Metamaterials: A cat's eye for all directions.`
`Pediatric Parasitology`	`Parasitic infections among school age children 6 to 11-years-of-age in the Eastern province.`	`[DIALOGUE ON PEDIATRIC PARASITOLOGY].`

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: 512
per_device_eval_batch_size: 512
learning_rate: 0.001
num_train_epochs: 1
lr_scheduler_type: cosine_with_restarts
warmup_ratio: 0.1
bf16: 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: 512
per_device_eval_batch_size: 512
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: 0.001
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: cosine_with_restarts
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: 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, '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
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	triplet-dev_cosine_accuracy
0	0	-	0.373
0.05	1	4.5633	-
0.1	2	4.5857	-
0.15	3	4.1852	-
0.2	4	3.2547	-
0.25	5	2.3117	-
0.3	6	1.949	-
0.35	7	1.7767	-
0.4	8	1.79	-
0.45	9	1.6081	-
0.5	10	1.7499	-
0.55	11	1.6395	-
0.6	12	1.5645	-
0.65	13	1.5804	-
0.7	14	1.5303	-
0.75	15	1.5452	-
0.8	16	1.5012	-
0.85	17	1.5283	-
0.9	18	1.5982	-
0.95	19	1.4714	-
1.0	20	1.3331	0.573

Framework Versions

Python: 3.9.19
Sentence Transformers: 3.1.1
Transformers: 4.45.2
PyTorch: 2.5.0
Accelerate: 1.0.1
Datasets: 2.19.0
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}
}