metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:3820
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: samsung ms23h3125ak/ms23h3125ak
    sentences:
      - Canon EOS M50 + 15-45mm IS STM
      - Bosch KIV32X23GB Integrated
      - Indesit DIF04B1 Integrated
      - Samsung MS23H3125AK Black
      - Samsung RB29FWRNDBC Black
      - Hisense RQ560N4WC1
      - Samsung UE32M5520
      - Nikon CoolPix A10
      - Hotpoint RPD10457JKK
      - HP Intel Xeon X5670 2.93GHz Socket 1366 3200MHz bus Upgrade Tray
      - Indesit DFG15B1S Silver
      - Samsung WW10M86DQOO
      - Bosch SMV46MX00G Integrated
      - LG 49SK8100PLA
      - Nikon CoolPix W300
      - AMD Ryzen 3 1300X 3.5GHz  Box
      - LG OLED65B8PLA
      - Samsung Galaxy J5 SM-J530
      - LG 65UK6500PLA
      - Siemens WM14T391GB
      - Apple iPhone SE 32GB
  - source_sentence: lg oled65c8pla
    sentences:
      - Beko LCSM1545W White
      - Bosch KAN90VI20G Stainless Steel
      - Canon PowerShot SX60 HS
      - Hotpoint WMAQF621P
      - Apple iPhone 7 Plus 32GB
      - Hotpoint FFU4DK Black
      - Fujifilm Finepix XP130
      - Bosch WAN24108GB
      - LG OLED65E8PLA
      - Intel Core i7-8700K 3.7GHz  Box
      - Fujifilm X-Pro2
      - LG OLED65C8PLA
      - Samsung UE55NU8000
      - LG 49LK5900PLA
      - Apple iPhone 8 64GB
      - Samsung UE65NU7100
      - AEG L6FBG942R
      - AMD Ryzen 7 1700 3GHz Box
      - Panasonic TX-49FX750B
      - Bosch WKD28351GB
      - Bosch GUD15A50GB Integrated
  - source_sentence: 15.748 cm 6.2 2960 x 1440 samoled octa core 2.3ghz quad 1.7gh
    sentences:
      - Apple iPhone SE 32GB
      - Apple iPhone X 64GB
      - LG 55SK9500PLA
      - Sony Cyber-shot DSC-WX500
      - Samsung Galaxy A5 SM-A520F
      - Apple iPhone 8 Plus 64GB
      - Indesit IWDD7123
      - Bosch SMS67MW01G White
      - Bosch KGV33XW30G White
      - Samsung WW80K5413UW
      - AMD Ryzen 3 1300X 3.5GHz  Box
      - Bosch WAW28750GB
      - Samsung Galaxy S8+ 64GB
      - Bosch KGN39VW35G White
      - Intel Core i7-7700K 4.2GHz  Box
      - Hotpoint RZAAV22P White
      - Samsung UE49NU8000
      - HP AMD Opteron 6276 2.3GHz Upgrade Tray
      - Praktica Luxmedia Z250
      - Hotpoint HFC2B19SV White
      - Hisense RB385N4EW1 White
  - source_sentence: boxed processor amd ryzen 3 1200 4 x 3.1 ghz quad
    sentences:
      - Bosch KGN36HI32 Stainless Steel
      - Bosch SMS24AW01G White
      - Hotpoint WDAL8640P
      - Doro 6050
      - Samsung QE55Q7FN
      - AMD Ryzen 3 1200 3.1GHz Box
      - Samsung UE55NU7500
      - Huawei Honor 10 128GB Dual SIM
      - Sony Xperia L1
      - Hotpoint FFU4DK Black
      - Hoover DXOC 68C3B
      - Sony Xperia XA1
      - Nikon D7200 + 18-105mm VR
      - HP Intel Xeon DP E5640 2.66GHz Socket 1366 1066MHz bus Upgrade Tray
      - Samsung UE49NU8000
      - Panasonic Lumix DMC-FT30
      - Hotpoint FDL 9640K UK
      - Apple iPhone 6S Plus 128GB
      - Nikon D5600 + AF-P 18-55mm VR
      - HP AMD Opteron 6238 2.6GHz Upgrade Tray
      - Apple iPhone SE 32GB
  - source_sentence: lg 49uk6300plb/49uk6300plb
    sentences:
      - Bosch KIR24V20GB Integrated
      - Bosch WAWH8660GB
      - Intel Core i5-7600K 3.80GHz  Box
      - Sony Bravia KD-65AF8
      - Samsung RL4362FBASL Stainless Steel
      - Bosch SMI50C15GB Silver
      - Apple iPhone XS Max 256GB
      - Fujifilm X-T100 + XC 15-45/f3.5-5.6 OIS PZ
      - Bosch KGN36VW35G White
      - Samsung WW70K5410UW
      - Samsung Galaxy J6
      - LG 49UK6300PLB
      - Doro Secure 580
      - Sony Xperia XZ1 Compact
      - Bosch SMV50C10GB Integrated
      - Bosch KGN34VB35G Black
      - Panasonic NN-E27JWMBPQ White
      - Samsung WW10M86DQOA/EU
      - LG 55SK9500PLA
      - Samsung QE65Q8DN
      - Canon EOS 80D
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Product Category Retrieval Test
          type: Product-Category-Retrieval-Test
        metrics:
          - type: cosine_accuracy@1
            value: 0.8085774058577406
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9476987447698745
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9644351464435147
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9769874476987448
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8085774058577406
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3158995815899582
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19288702928870294
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09769874476987449
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8085774058577406
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9476987447698745
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9644351464435147
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9769874476987448
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9041917131034228
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.879607906621505
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8805000617705705
            name: Cosine Map@100

SentenceTransformer

This is a sentence-transformers model trained. It maps sentences & paragraphs to a 512-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
Maximum Sequence Length: 384 tokens
Output Dimensionality: 512 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): 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})
    (2): Normalize()
  )
  (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': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)

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("llmvetter/embedding_finetune")
# Run inference
sentences = [
    'lg 49uk6300plb/49uk6300plb',
    'LG 49UK6300PLB',
    'Samsung Galaxy J6',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Dataset: Product-Category-Retrieval-Test
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8086
cosine_accuracy@3	0.9477
cosine_accuracy@5	0.9644
cosine_accuracy@10	0.977
cosine_precision@1	0.8086
cosine_precision@3	0.3159
cosine_precision@5	0.1929
cosine_precision@10	0.0977
cosine_recall@1	0.8086
cosine_recall@3	0.9477
cosine_recall@5	0.9644
cosine_recall@10	0.977
cosine_ndcg@10	0.9042
cosine_mrr@10	0.8796
cosine_map@100	0.8805

Training Details

Training Dataset

Unnamed Dataset

Size: 3,820 training samples
Columns: sentence_0, sentence_1, sentence_2, sentence_3, sentence_4, sentence_5, sentence_6, sentence_7, sentence_8, sentence_9, sentence_10, sentence_11, sentence_12, sentence_13, sentence_14, sentence_15, sentence_16, sentence_17, sentence_18, sentence_19, sentence_20, and sentence_21

Approximate statistics based on the first 1000 samples:

	sentence_0	sentence_1	sentence_2	sentence_3	sentence_4	sentence_5	sentence_6	sentence_7	sentence_8	sentence_9	sentence_10	sentence_11	sentence_12	sentence_13	sentence_14	sentence_15	sentence_16	sentence_17	sentence_18	sentence_19	sentence_20	sentence_21
type	string	string	string	string	string	string	string	string	string	string	string	string	string	string	string	string	string	string	string	string	string	string
details	min: 4 tokens mean: 18.41 tokens max: 47 tokens	min: 6 tokens mean: 10.94 tokens max: 30 tokens	min: 6 tokens mean: 11.11 tokens max: 30 tokens	min: 6 tokens mean: 11.15 tokens max: 30 tokens	min: 6 tokens mean: 10.89 tokens max: 30 tokens	min: 6 tokens mean: 10.89 tokens max: 30 tokens	min: 6 tokens mean: 10.98 tokens max: 30 tokens	min: 6 tokens mean: 11.07 tokens max: 30 tokens	min: 6 tokens mean: 11.04 tokens max: 30 tokens	min: 6 tokens mean: 10.84 tokens max: 30 tokens	min: 6 tokens mean: 10.82 tokens max: 30 tokens	min: 6 tokens mean: 10.81 tokens max: 30 tokens	min: 6 tokens mean: 11.05 tokens max: 30 tokens	min: 6 tokens mean: 10.92 tokens max: 30 tokens	min: 6 tokens mean: 11.18 tokens max: 30 tokens	min: 6 tokens mean: 11.07 tokens max: 30 tokens	min: 6 tokens mean: 10.93 tokens max: 30 tokens	min: 6 tokens mean: 11.02 tokens max: 30 tokens	min: 6 tokens mean: 11.04 tokens max: 30 tokens	min: 6 tokens mean: 11.02 tokens max: 30 tokens	min: 6 tokens mean: 10.95 tokens max: 30 tokens	min: 6 tokens mean: 10.86 tokens max: 30 tokens

Samples:

sentence_0	sentence_1	sentence_2	sentence_3	sentence_4	sentence_5	sentence_6	sentence_7	sentence_8	sentence_9	sentence_10	sentence_11	sentence_12	sentence_13	sentence_14	sentence_15	sentence_16	sentence_17	sentence_18	sentence_19	sentence_20	sentence_21
`sony kd49xf8505bu 49 4k ultra hd tv`	`Sony Bravia KD-49XF8505`	`Intel Core i7-8700K 3.7GHz Box`	`Bosch WAN24100GB`	`AMD FX-6300 3.5GHz Box`	`Bosch WIW28500GB`	`Bosch KGN36VL35G Stainless Steel`	`Indesit XWDE751480XS`	`CAT S41 Dual SIM`	`Sony Xperia XA1 Ultra 32GB`	`Samsung Galaxy J6`	`Samsung QE55Q7FN`	`Bosch KGN39VW35G White`	`Intel Core i5 7400 3.0GHz Box`	`Neff C17UR02N0B Stainless Steel`	`Samsung RR39M7340SA Silver`	`Samsung RB41J7255SR Stainless Steel`	`Hoover DXOC 68C3B`	`Canon PowerShot SX730 HS`	`Samsung RR39M7340BC Black`	`Praktica Luxmedia WP240`	`HP Intel Xeon DP E5506 2.13GHz Socket 1366 800MHz bus Upgrade Tray`
`doro 8040 4g sim free mobile phone black`	`Doro 8040`	`Bosch HMT75M551 Stainless Steel`	`Bosch SMI50C15GB Silver`	`Samsung WW90K5413UX`	`Panasonic Lumix DMC-TZ70`	`Sony KD-49XF7073`	`Nikon CoolPix W100`	`Samsung WD90J6A10AW`	`Bosch CFA634GS1B Stainless Steel`	`HP AMD Opteron 8425 HE 2.1GHz Socket F 4800MHz bus Upgrade Tray`	`Canon EOS 800D + 18-55mm IS STM`	`Samsung UE50NU7400`	`Apple iPhone 6S 128GB`	`Samsung RS52N3313SA/EU Graphite`	`Bosch WAW325H0GB`	`Sony Bravia KD-55AF8`	`Sony Alpha 6500`	`Doro 5030`	`LG GSL761WBXV Black`	`Bosch SMS67MW00G White`	`AEG L6FBG942R`
`fridgemaster muz4965 undercounter freezer white a rated`	`Fridgemaster MUZ4965 White`	`Samsung UE49NU7100`	`Nikon CoolPix A10`	`Samsung UE55NU7100`	`Samsung QE55Q7FN`	`Bosch KGN49XL30G Stainless Steel`	`Samsung UE49NU7500`	`LG 55UK6300PLB`	`Hoover DXOC 68C3B`	`Panasonic Lumix DMC-FZ2000`	`Panasonic Lumix DMC-TZ80`	`Bosch WKD28541GB`	`Apple iPhone 6 32GB`	`Sony Bravia KDL-32WE613`	`Lec TF50152W White`	`Bosch KGV36VW32G White`	`Bosch WAYH8790GB`	`Samsung RS68N8240B1/EU Black`	`Sony Xperia XZ1`	`HP Intel Xeon DP E5506 2.13GHz Socket 1366 800MHz bus Upgrade Tray`	`Sharp R372WM White`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 8
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
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: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 8
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: 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: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
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
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss	Product-Category-Retrieval-Test_cosine_ndcg@10
1.0	120	-	0.7406
2.0	240	-	0.8437
3.0	360	-	0.8756
4.0	480	-	0.8875
4.1667	500	2.5302	-
5.0	600	-	0.8963
6.0	720	-	0.9015
7.0	840	-	0.9042

Framework Versions

Python: 3.11.10
Sentence Transformers: 3.3.1
Transformers: 4.47.1
PyTorch: 2.5.1+cu124
Accelerate: 1.2.1
Datasets: 3.2.0
Tokenizers: 0.21.0

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}
}