metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:25012
  - loss:MultipleNegativesRankingLoss
base_model: nomic-ai/modernbert-embed-base
widget:
  - source_sentence: ÇİFT KLİMALI BARAN FREE COOLING UNIT MONTAJ KITI.
    sentences:
      - Building construction machinery and accessories
      - Building construction machinery and accessories
      - Mounting Hardware
  - source_sentence: >-
      HUAWEI.TN1-L4G-100GHz-FEC /Line Wavelength Conversion Board with 4xGigabit
      Ethernet Line Capacity
    sentences:
      - Fixed network equipment and components
      - Audio and visual equipment
      - System boards processors interfaces or modules
  - source_sentence: ASR 9922 System Fan Tray v3, Spare
    sentences:
      - Security and control equipment
      - Computers
      - System boards processors interfaces or modules
  - source_sentence: Enhanced Cat.5E UTP Patch Cord 1.5M, White
    sentences:
      - Electrical cable and accessories
      - Computer accessories
      - Air circulation and parts and accessories
  - source_sentence: Controller CXC
    sentences:
      - Personal communication devices
      - Fixed network equipment and components
      - Power generation control equipment
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on nomic-ai/modernbert-embed-base
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: pearson_cosine
            value: .nan
            name: Pearson Cosine
          - type: spearman_cosine
            value: .nan
            name: Spearman Cosine

SentenceTransformer based on nomic-ai/modernbert-embed-base

This is a sentence-transformers model finetuned from nomic-ai/modernbert-embed-base. 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: nomic-ai/modernbert-embed-base
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 768 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): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (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()
)

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("alpcansoydas/product-model-02.12.25-total46clas-ifhavemorethan100sampleperclass-0.71acc")
# Run inference
sentences = [
    'Controller CXC',
    'Power generation control equipment',
    'Personal communication devices',
]
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

Semantic Similarity

Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan

Training Details

Training Dataset

Unnamed Dataset

Size: 25,012 training samples
Columns: sentence1 and sentence2
Approximate statistics based on the first 1000 samples:
sentence1 sentence2
type string string
details
min: 4 tokens
mean: 18.46 tokens
max: 85 tokens

min: 4 tokens
mean: 6.42 tokens
max: 11 tokens

	sentence1	sentence2
type	string	string
details	min: 4 tokens mean: 18.46 tokens max: 85 tokens	min: 4 tokens mean: 6.42 tokens max: 11 tokens

Samples:

sentence1	sentence2
`HPE MSA 14.4T SAS 10K SFF M2 6pk HDD Bdl`	`Media storage devices`
`Huawei Solar Greensites Solution (Yerli Panel_4*540Wp_Huawei Panel + PVPU+Konstrüksiyon+İşçilik)`	`Power generation control equipment`
`NetEngine9000 10G EVPN Port License(per 10G)`	`Network management software`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

Size: 3,127 evaluation samples
Columns: sentence1 and sentence2
Approximate statistics based on the first 1000 samples:
sentence1 sentence2
type string string
details
min: 3 tokens
mean: 18.0 tokens
max: 77 tokens

min: 4 tokens
mean: 6.4 tokens
max: 11 tokens

	sentence1	sentence2
type	string	string
details	min: 3 tokens mean: 18.0 tokens max: 77 tokens	min: 4 tokens mean: 6.4 tokens max: 11 tokens

Samples:

sentence1	sentence2
`CONNECTION CABLE`	`Electrical cable and accessories`
`MMU2 B 4-16 (24V, -48V)`	`Electronic component parts and raw materials and accessories`
`3ft C14 to C13 locking power cable 15A/250V - red`	`Electrical cable and accessories`

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: 32
per_device_eval_batch_size: 32
warmup_ratio: 0.1
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
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: 1.0
num_train_epochs: 3
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
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: True
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: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	spearman_cosine
0.1279	100	2.5126	2.1189	nan
0.2558	200	1.9979	1.9490	nan
0.3836	300	1.8803	1.9128	nan
0.5115	400	1.8242	1.8253	nan
0.6394	500	1.8024	1.7830	nan
0.7673	600	1.7425	1.7727	nan
0.8951	700	1.7302	1.7469	nan
1.0230	800	1.6722	1.7273	nan
1.1509	900	1.4698	1.7384	nan
1.2788	1000	1.5151	1.7111	nan
1.4066	1100	1.5151	1.7173	nan
1.5345	1200	1.494	1.6988	nan
1.6624	1300	1.4935	1.7058	nan
1.7903	1400	1.5143	1.6664	nan
1.9182	1500	1.5253	1.6636	nan
2.0460	1600	1.4355	1.6781	nan
2.1739	1700	1.3638	1.6944	nan
2.3018	1800	1.319	1.6829	nan
2.4297	1900	1.2848	1.7047	nan
2.5575	2000	1.3207	1.6950	nan
2.6854	2100	1.2769	1.6911	nan
2.8133	2200	1.2934	1.6958	nan
2.9412	2300	1.3244	1.6897	nan

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.3.1
Transformers: 4.48.0.dev0
PyTorch: 2.5.1+cu121
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}
}