Sentence Similarity
sentence-transformers
Safetensors
English
feature-extraction
dense
Generated from Trainer
dataset_size:1200
loss:ContrastiveLoss
Eval Results (legacy)
Instructions to use mancer146/embeddinggemma-300m-haystack-contrastive-thin-fixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use mancer146/embeddinggemma-300m-haystack-contrastive-thin-fixed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("mancer146/embeddinggemma-300m-haystack-contrastive-thin-fixed") sentences = [ "TaxYear: 2025 PRELIMINARY\nLandJustValue: $571,965\nImprovementsJustValue: $444,893\nTotalJustValue: $1,016,858\nSchoolAssessedValue: $657,902\nCountyTaxableValue: $607,180\nTotalTaxes: $5,881.02\n\nTaxYear: 2024\nLandJustValue: $529,037\nImprovementsJustValue: $522,202\nTotalJustValue: $1,051,239\nSchoolAssessedValue: $639,361\nCountyTaxableValue: $589,361\nTotalTaxes: $6,003.53\n\nTaxYear: 2023\nLandJustValue: $500,470\nImprovementsJustValue: $572,889\nTotalJustValue: $1,073,359\nSchoolAssessedValue: $620,739\nCountyTaxableValue: $570,739\nTotalTaxes: $5,956.52\n\nTaxYear: 2022\nLandJustValue: $230,519\nImprovementsJustValue: $610,503\nTotalJustValue: $841,022\nSchoolAssessedValue: $602,659\nCountyTaxableValue: $552,659\nTotalTaxes: $6,124.86\n\nTaxYear: 2021\nLandJustValue: $112,658\nImprovementsJustValue: $472,448\nTotalJustValue: $585,106\nSchoolAssessedValue: $585,106\nCountyTaxableValue: $535,106\nTotalTaxes: $6,190.98section: Tax,\ncounty: Collier,\nparcel_id: 82660002628", "area_under_air: 2111\nlivable_floor_area: 2111\nparcel_identifier: 51978031927\nproperty_structure_built_year: 2004\nproperty_type: SingleFamily\nsubdivision: INDIGO LAKES UNIT\ntotal_area: 2551", "monthly_tax_amount: 490.09\nperiod_end_date: 2025-12-31\nperiod_start_date: 2025-01-01\nproperty_assessed_value_amount: 657902\nproperty_building_amount: 444893\nproperty_land_amount: 571965\nproperty_market_value_amount: 1016858\nproperty_taxable_value_amount: 607180\ntax_year: 2025\nyearly_tax_amount: 5881.02\n\nmonthly_tax_amount: 510.41\nperiod_end_date: 2022-12-31\nperiod_start_date: 2022-01-01\nproperty_assessed_value_amount: 602659\nproperty_building_amount: 610503\nproperty_land_amount: 230519\nproperty_market_value_amount: 841022\nproperty_taxable_value_amount: 552659\ntax_year: 2022\nyearly_tax_amount: 6124.86", "ownership_transfer_date: 2013-07-09\npurchase_price_amount: 830000\n\nownership_transfer_date: 2011-10-03\npurchase_price_amount: 685000\n\nownership_transfer_date: 2009-07-01\npurchase_price_amount: 432500\n\nownership_transfer_date: 1999-02-22\npurchase_price_amount: 0\n\nownership_transfer_date: 2001-01-25\npurchase_price_amount: 360000" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
metadata
language:
- en
license: apache-2.0
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:1200
- loss:ContrastiveLoss
base_model: google/embeddinggemma-300m
widget:
- source_sentence: |-
TaxYear: 2025 PRELIMINARY
LandJustValue: $571,965
ImprovementsJustValue: $444,893
TotalJustValue: $1,016,858
SchoolAssessedValue: $657,902
CountyTaxableValue: $607,180
TotalTaxes: $5,881.02
TaxYear: 2024
LandJustValue: $529,037
ImprovementsJustValue: $522,202
TotalJustValue: $1,051,239
SchoolAssessedValue: $639,361
CountyTaxableValue: $589,361
TotalTaxes: $6,003.53
TaxYear: 2023
LandJustValue: $500,470
ImprovementsJustValue: $572,889
TotalJustValue: $1,073,359
SchoolAssessedValue: $620,739
CountyTaxableValue: $570,739
TotalTaxes: $5,956.52
TaxYear: 2022
LandJustValue: $230,519
ImprovementsJustValue: $610,503
TotalJustValue: $841,022
SchoolAssessedValue: $602,659
CountyTaxableValue: $552,659
TotalTaxes: $6,124.86
TaxYear: 2021
LandJustValue: $112,658
ImprovementsJustValue: $472,448
TotalJustValue: $585,106
SchoolAssessedValue: $585,106
CountyTaxableValue: $535,106
TotalTaxes: $6,190.98section: Tax,
county: Collier,
parcel_id: 82660002628
sentences:
- |-
area_under_air: 2111
livable_floor_area: 2111
parcel_identifier: 51978031927
property_structure_built_year: 2004
property_type: SingleFamily
subdivision: INDIGO LAKES UNIT
total_area: 2551
- |-
monthly_tax_amount: 490.09
period_end_date: 2025-12-31
period_start_date: 2025-01-01
property_assessed_value_amount: 657902
property_building_amount: 444893
property_land_amount: 571965
property_market_value_amount: 1016858
property_taxable_value_amount: 607180
tax_year: 2025
yearly_tax_amount: 5881.02
monthly_tax_amount: 510.41
period_end_date: 2022-12-31
period_start_date: 2022-01-01
property_assessed_value_amount: 602659
property_building_amount: 610503
property_land_amount: 230519
property_market_value_amount: 841022
property_taxable_value_amount: 552659
tax_year: 2022
yearly_tax_amount: 6124.86
- |-
ownership_transfer_date: 2013-07-09
purchase_price_amount: 830000
ownership_transfer_date: 2011-10-03
purchase_price_amount: 685000
ownership_transfer_date: 2009-07-01
purchase_price_amount: 432500
ownership_transfer_date: 1999-02-22
purchase_price_amount: 0
ownership_transfer_date: 2001-01-25
purchase_price_amount: 360000
- source_sentence: |-
TaxYear: 2025 PRELIMINARY
LandJustValue: $0
ImprovementsJustValue: $261,720
TotalJustValue: $261,720
SchoolAssessedValue: $261,720
CountyTaxableValue: $261,720
TotalTaxes: $3,142.17
TaxYear: 2024
LandJustValue: $0
ImprovementsJustValue: $261,720
TotalJustValue: $261,720
SchoolAssessedValue: $261,720
CountyTaxableValue: $261,720
TotalTaxes: $3,551.55
TaxYear: 2023
LandJustValue: $0
ImprovementsJustValue: $298,680
TotalJustValue: $298,680
SchoolAssessedValue: $298,680
CountyTaxableValue: $298,680
TotalTaxes: $4,125.27
TaxYear: 2022
LandJustValue: $0
ImprovementsJustValue: $233,985
TotalJustValue: $233,985
SchoolAssessedValue: $233,985
CountyTaxableValue: $172,700
TotalTaxes: $2,771.07
TaxYear: 2021
LandJustValue: $0
ImprovementsJustValue: $157,000
TotalJustValue: $157,000
SchoolAssessedValue: $157,000
CountyTaxableValue: $157,000
TotalTaxes: $2,342.18section: Tax,
county: Collier,
parcel_id: 31760000209
sentences:
- |-
first_name: George
last_name: Lewis
middle_name: P
first_name: Karen
last_name: Lewis
middle_name: L
- >-
area_under_air: 997
livable_floor_area: 997
parcel_identifier: 31731720000
property_legal_description_text: FAIRWAY FOREST GARDEN VILLAS A
CONDOMINIUM UNIT 179
property_structure_built_year: 1987
property_type: Condominium
total_area: 997
- |-
monthly_tax_amount: 195.18
period_end_date: 2021-12-31
period_start_date: 2021-01-01
property_assessed_value_amount: 157000
property_building_amount: 157000
property_land_amount: 0
property_market_value_amount: 157000
property_taxable_value_amount: 157000
tax_year: 2021
yearly_tax_amount: 2342.18
monthly_tax_amount: 261.85
period_end_date: 2025-12-31
period_start_date: 2025-01-01
property_assessed_value_amount: 261720
property_building_amount: 261720
property_land_amount: 0
property_market_value_amount: 261720
property_taxable_value_amount: 261720
tax_year: 2025
yearly_tax_amount: 3142.17
monthly_tax_amount: 295.96
period_end_date: 2024-12-31
period_start_date: 2024-01-01
property_assessed_value_amount: 261720
property_building_amount: 261720
property_land_amount: 0
property_market_value_amount: 261720
property_taxable_value_amount: 261720
tax_year: 2024
yearly_tax_amount: 3551.55
monthly_tax_amount: 230.92
period_end_date: 2022-12-31
period_start_date: 2022-01-01
property_assessed_value_amount: 233985
property_building_amount: 233985
property_land_amount: 0
property_market_value_amount: 233985
property_taxable_value_amount: 172700
tax_year: 2022
yearly_tax_amount: 2771.07
monthly_tax_amount: 343.77
period_end_date: 2023-12-31
period_start_date: 2023-01-01
property_assessed_value_amount: 298680
property_building_amount: 298680
property_land_amount: 0
property_market_value_amount: 298680
property_taxable_value_amount: 298680
tax_year: 2023
yearly_tax_amount: 4125.27
- source_sentence: >-
ParcelID: 31347702043
FullAddress: 9424 MONTELANICO LOOP, NAPLES 34119
Legal: ESPLANADE GOLF AND COUNTRY CLUB OF NAPLES PHASE 3 BLOCKS K1 K2 AND
H3 LOT 1390
Subdivision: 281740 - ESPLANADE G&CC PH3 B-K1,K2,H3 CLUB OF NAPLES PHASE 3
BLOCKS K1 K2 AND H3
UseCode: 1 - SINGLE FAMILY RESIDENTIAL
Section: 15
Township: 48
Range: 26section: Property,
county: Collier,
parcel_id: 31347702043
sentences:
- |-
monthly_tax_amount: 1296.8
period_end_date: 2023-12-31
period_start_date: 2023-01-01
property_assessed_value_amount: 1452003
property_building_amount: 1459158
property_land_amount: 1594430
property_market_value_amount: 3053588
property_taxable_value_amount: 1402003
tax_year: 2023
yearly_tax_amount: 15561.55
monthly_tax_amount: 1339.02
period_end_date: 2021-12-31
period_start_date: 2021-01-01
property_assessed_value_amount: 1368652
property_building_amount: 1188323
property_land_amount: 180329
property_market_value_amount: 1368652
property_taxable_value_amount: 1318652
tax_year: 2021
yearly_tax_amount: 16068.19
monthly_tax_amount: 1315.87
period_end_date: 2024-12-31
period_start_date: 2024-01-01
property_assessed_value_amount: 1495563
property_building_amount: 1262216
property_land_amount: 1402668
property_market_value_amount: 2664884
property_taxable_value_amount: 1445563
tax_year: 2024
yearly_tax_amount: 15790.39
monthly_tax_amount: 1187.99
period_end_date: 2025-12-31
period_start_date: 2025-01-01
property_assessed_value_amount: 1538934
property_building_amount: 1117620
property_land_amount: 1508245
property_market_value_amount: 2625865
property_taxable_value_amount: 1488212
tax_year: 2025
yearly_tax_amount: 14255.93
monthly_tax_amount: 1334.85
period_end_date: 2022-12-31
period_start_date: 2022-01-01
property_assessed_value_amount: 1409712
property_building_amount: 1553410
property_land_amount: 470644
property_market_value_amount: 2024054
property_taxable_value_amount: 1359712
tax_year: 2022
yearly_tax_amount: 16018.16
- >-
area_under_air: 2313
livable_floor_area: 2313
parcel_identifier: 31347702043
property_legal_description_text: ESPLANADE GOLF AND COUNTRY CLUB OF
NAPLES PHASE 3 BLOCKS K1 K2 AND H3 LOT 1390
property_structure_built_year: 2018
property_type: SingleFamily
subdivision: ESPLANADE G&CC PH3 B-K1,K2,H3 CLUB OF NAPLES PHASE 3 BLOCKS
K1 K2 AND H3
total_area: 2767
- |-
city_name: NAPLES
county_name: Collier
postal_code: 34105
range: 25
section: 14
state_code: FL
street_name: WOODSHIRE
street_number: 1018
street_suffix_type: Ln
township: 49
- source_sentence: |-
OwnerLine 1: 21 VB PROPERTIES LLCsection: Owners,
county: Collier,
parcel_id: 23270120001
sentences:
- |-
first_name: Kenneth
last_name: Holman
middle_name: W
- |-
city_name: NAPLES
county_name: Collier
state_code: FL
street_name: WILLOWBROOK
street_number: 765
street_suffix_type: Dr
township: 49
- 'name: 21'
- source_sentence: >-
FullAddress: 5852 NORTHRIDGE DR, NAPLES 34110
Legal: CARLTON LAKES UNIT NO 2 BLK A LOT 5 NKA VILLAS I AT CARLTON LAKES
(HO) UNIT A-5
Section: 19
Township: 48
Range: 26section: Address,
county: Collier,
parcel_id: 25540003380
sentences:
- |-
monthly_tax_amount: 317.4
period_end_date: 2022-12-31
period_start_date: 2022-01-01
property_assessed_value_amount: 381299
property_building_amount: 441115
property_land_amount: 134469
property_market_value_amount: 575584
property_taxable_value_amount: 331299
tax_year: 2022
yearly_tax_amount: 3808.76
monthly_tax_amount: 517.39
period_end_date: 2025-12-31
period_start_date: 2025-01-01
property_assessed_value_amount: 692367
property_building_amount: 324162
property_land_amount: 368205
property_market_value_amount: 692367
property_taxable_value_amount: 641645
tax_year: 2025
yearly_tax_amount: 6208.64
monthly_tax_amount: 320.37
period_end_date: 2021-12-31
period_start_date: 2021-01-01
property_assessed_value_amount: 370193
property_building_amount: 334803
property_land_amount: 35390
property_market_value_amount: 370193
property_taxable_value_amount: 320193
tax_year: 2021
yearly_tax_amount: 3844.46
- |-
first_name: Christina
last_name: Zajac
middle_name: R
first_name: Thomas
last_name: Zajac
middle_name: H
- |-
city_name: NAPLES
county_name: Collier
lot: 5
postal_code: 34110
range: 26
section: 19
state_code: FL
street_name: NORTHRIDGE
street_number: 5852
street_suffix_type: Dr
township: 48
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy
- cosine_accuracy_threshold
- cosine_f1
- cosine_f1_threshold
- cosine_precision
- cosine_recall
- cosine_ap
- cosine_mcc
model-index:
- name: EmbeddingGemma-300m trained to measure coverage
results:
- task:
type: binary-classification
name: Binary Classification
dataset:
name: Unknown
type: unknown
metrics:
- type: cosine_accuracy
value: 0.96
name: Cosine Accuracy
- type: cosine_accuracy_threshold
value: 0.9879488945007324
name: Cosine Accuracy Threshold
- type: cosine_f1
value: 0.9607843137254902
name: Cosine F1
- type: cosine_f1_threshold
value: 0.98133385181427
name: Cosine F1 Threshold
- type: cosine_precision
value: 0.9423076923076923
name: Cosine Precision
- type: cosine_recall
value: 0.98
name: Cosine Recall
- type: cosine_ap
value: 0.9530095295398296
name: Cosine Ap
- type: cosine_mcc
value: 0.920736884379251
name: Cosine Mcc
EmbeddingGemma-300m trained to measure coverage
This is a sentence-transformers model finetuned from google/embeddinggemma-300m 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: google/embeddinggemma-300m
- Maximum Sequence Length: 2048 tokens
- Output Dimensionality: 768 dimensions
- Similarity Function: Cosine Similarity
- Training Dataset:
- json
- 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': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
(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})
(2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
(3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
(4): 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("mancer146/embeddinggemma-300m-haystack-contrastive-thin-fixed")
# Run inference
queries = [
"FullAddress: 5852 NORTHRIDGE DR, NAPLES 34110\nLegal: CARLTON LAKES UNIT NO 2 BLK A LOT 5 NKA VILLAS I AT CARLTON LAKES (HO) UNIT A-5\nSection: 19\nTownship: 48\nRange: 26section: Address,\ncounty: Collier,\nparcel_id: 25540003380",
]
documents = [
'city_name: NAPLES\ncounty_name: Collier\nlot: 5\npostal_code: 34110\nrange: 26\nsection: 19\nstate_code: FL\nstreet_name: NORTHRIDGE\nstreet_number: 5852\nstreet_suffix_type: Dr\ntownship: 48',
'monthly_tax_amount: 317.4\nperiod_end_date: 2022-12-31\nperiod_start_date: 2022-01-01\nproperty_assessed_value_amount: 381299\nproperty_building_amount: 441115\nproperty_land_amount: 134469\nproperty_market_value_amount: 575584\nproperty_taxable_value_amount: 331299\ntax_year: 2022\nyearly_tax_amount: 3808.76\n\nmonthly_tax_amount: 517.39\nperiod_end_date: 2025-12-31\nperiod_start_date: 2025-01-01\nproperty_assessed_value_amount: 692367\nproperty_building_amount: 324162\nproperty_land_amount: 368205\nproperty_market_value_amount: 692367\nproperty_taxable_value_amount: 641645\ntax_year: 2025\nyearly_tax_amount: 6208.64\n\nmonthly_tax_amount: 320.37\nperiod_end_date: 2021-12-31\nperiod_start_date: 2021-01-01\nproperty_assessed_value_amount: 370193\nproperty_building_amount: 334803\nproperty_land_amount: 35390\nproperty_market_value_amount: 370193\nproperty_taxable_value_amount: 320193\ntax_year: 2021\nyearly_tax_amount: 3844.46',
'first_name: Christina\nlast_name: Zajac\nmiddle_name: R\n\nfirst_name: Thomas\nlast_name: Zajac\nmiddle_name: H',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.9881, 0.8106, 0.6785]])
Evaluation
Metrics
Binary Classification
- Evaluated with
BinaryClassificationEvaluator
| Metric | Value |
|---|---|
| cosine_accuracy | 0.96 |
| cosine_accuracy_threshold | 0.9879 |
| cosine_f1 | 0.9608 |
| cosine_f1_threshold | 0.9813 |
| cosine_precision | 0.9423 |
| cosine_recall | 0.98 |
| cosine_ap | 0.953 |
| cosine_mcc | 0.9207 |
Training Details
Training Dataset
json
- Dataset: json
- Size: 1,200 training samples
- Columns:
input_text,output_text, andlabel - Approximate statistics based on the first 1000 samples:
input_text output_text label type string string int details - min: 36 tokens
- mean: 188.79 tokens
- max: 536 tokens
- min: 5 tokens
- mean: 165.35 tokens
- max: 801 tokens
- 0: ~50.10%
- 1: ~49.90%
- Samples:
input_text output_text label OwnerLine 1: JERI HURCKES LIVING TRUSTsection: Owners,
county: Collier,
parcel_id: 82660021104name: JERI HURCKES LIVING TRUST1OwnerLine 1: GUALARIO, ANTHONY=& DIANAsection: Owners,
county: Collier,
parcel_id: 16054320005first_name: Anthony
last_name: Gualario0Date: 02/11/14
Amount: $496,300
BookPage: 5009-963section: Sales,
county: Collier,
parcel_id: 69770005923ownership_transfer_date: 2014-02-11
purchase_price_amount: 00 - Loss:
ContrastiveLosswith these parameters:{ "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", "margin": 0.1, "size_average": true }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy: stepsper_device_train_batch_size: 3per_device_eval_batch_size: 3gradient_accumulation_steps: 2learning_rate: 2e-05num_train_epochs: 5warmup_ratio: 0.05fp16: Trueprompts: {'input_text': 'STS', 'output_text': 'STS'}
All Hyperparameters
Click to expand
overwrite_output_dir: Falsedo_predict: Falseeval_strategy: stepsprediction_loss_only: Trueper_device_train_batch_size: 3per_device_eval_batch_size: 3per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 2eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 2e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1.0num_train_epochs: 5max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.05warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falseuse_ipex: Falsebf16: Falsefp16: Truefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Falseignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}parallelism_config: Nonedeepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torchoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: Falseneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Falseprompts: {'input_text': 'STS', 'output_text': 'STS'}batch_sampler: batch_samplermulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}
Training Logs
| Epoch | Step | Training Loss | cosine_ap |
|---|---|---|---|
| 0.4 | 40 | - | 0.8426 |
| 0.8 | 80 | - | 0.8858 |
| 1.2 | 120 | - | 0.8194 |
| 1.6 | 160 | - | 0.8856 |
| 2.0 | 200 | - | 0.9643 |
| 2.4 | 240 | - | 0.9469 |
| 2.8 | 280 | - | 0.9426 |
| 3.2 | 320 | - | 0.9084 |
| 3.6 | 360 | - | 0.9337 |
| 4.0 | 400 | - | 0.9449 |
| 4.4 | 440 | - | 0.9555 |
| 4.8 | 480 | - | 0.9525 |
| 5.0 | 500 | 0.0006 | - |
| -1 | -1 | - | 0.9530 |
Framework Versions
- Python: 3.11.13
- Sentence Transformers: 5.1.2
- Transformers: 4.57.0.dev0
- PyTorch: 2.6.0+cu124
- Accelerate: 1.9.0
- Datasets: 4.1.1
- Tokenizers: 0.22.1
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",
}
ContrastiveLoss
@inproceedings{hadsell2006dimensionality,
author={Hadsell, R. and Chopra, S. and LeCun, Y.},
booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
title={Dimensionality Reduction by Learning an Invariant Mapping},
year={2006},
volume={2},
number={},
pages={1735-1742},
doi={10.1109/CVPR.2006.100}
}