MultiEccomerceEmbeddingModel / README.md

IshTale

Add new SentenceTransformer model

d1ff998 verified 3 months ago

preview code

raw

history blame contribute delete

13 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:269337
  - loss:CoSENTLoss
base_model: intfloat/multilingual-e5-large
widget:
  - source_sentence: motion-activated security light with adjustable settings
    sentences:
      - >-
        LED Black Motion Sensor 2-Light Bullet Flood Light- 3000K Adjustable
        Dual Head Outdoor Security Light, Dusk to Dawn, Waterproof, Hardwired
        Spotlight for Yard, Patio, Garage, Landscape
      - Waterpik Cordless Advanced Water Flosser
      - >-
        Tabi Ballet Flats Shoes for Women Rounde Toe Wide Width Split Toe Low
        Heel Comfortable Flats Shoes
  - source_sentence: microdevice for line smoothing
    sentences:
      - SkinMedica TNS Advanced+ Serum
      - >-
        Waterproof Beach Bag for Women with Phone Pouch, Large Tote Bag for
        Pool, Travel and Vacation
      - Fisher-Price 4-in-1 Step 'n Play Piano
  - source_sentence: hair strengthening serum
    sentences:
      - >-
        Yaheetech Adjustable Dumbbell Set Free Weight Dumbbells
        40lbs/52.5lbs/90lbs Fast Adjust Dumbbells Dumbbell Weight Set, with Tray
        for Men/Women Strength Training Equipment
      - DeLonghi Dedica Arte Espresso Machine
      - Opalescence Go Teeth Whitening Trays
  - source_sentence: slime making kit with glue and additives
    sentences:
      - Faber-Castell Polychromos Color Pencils Set of 120
      - >-
        Keter Delivery Box for Porch with Lockable Secure Storage Compartment to
        Keep Packages Safe, One Size, Brown
      - Stillman & Birn Zeta Series Sketchbook
  - source_sentence: antioxidant serum for skin protection
    sentences:
      - Louisville Ladder 16-foot Fiberglass Extension Ladder
      - Crayola Light Up Tracing Pad
      - Logitech MX Master 3S Wireless Mouse
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on intfloat/multilingual-e5-large

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-large. It maps sentences & paragraphs to a 1024-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: intfloat/multilingual-e5-large
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 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': 512, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'word_embedding_dimension': 1024, '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("IshTale/MultiEccomerceEmbeddingModel")
# Run inference
sentences = [
    'antioxidant serum for skin protection',
    'Louisville Ladder 16-foot Fiberglass Extension Ladder',
    'Logitech MX Master 3S Wireless Mouse',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.4999, 0.4880],
#         [0.4999, 1.0000, 0.6445],
#         [0.4880, 0.6445, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 269,337 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 5 tokens
mean: 11.2 tokens
max: 23 tokens

min: 3 tokens
mean: 24.29 tokens
max: 66 tokens

min: -1.0
mean: 0.05
max: 0.99

	sentence_0	sentence_1	label
type	string	string	float
details	min: 5 tokens mean: 11.2 tokens max: 23 tokens	min: 3 tokens mean: 24.29 tokens max: 66 tokens	min: -1.0 mean: 0.05 max: 0.99

Samples:

sentence_0	sentence_1	label
`motorized Nerf blaster with dinosaur theme`	`B. Toys by Battat Wooden Activity Cube`	`-0.07861651138439901`
`smart mirror with adjustable lighting`	`Pfaff Passport 2.0 Sewing Machine`	`-0.835469516572358`
`black tea with orange rind and spices`	`Valrhona Cocoa Powder`	`-0.13135949520666002`

Loss: CoSENTLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 1
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: 1
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}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
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
hub_revision: None
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
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
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.0594	500	5.6346
0.1188	1000	5.5107
0.1782	1500	5.4706
0.2376	2000	5.4402
0.2970	2500	5.4039
0.3564	3000	5.4252
0.4158	3500	5.3693
0.4752	4000	5.3776
0.5346	4500	5.3672
0.5940	5000	5.4059
0.6534	5500	5.336
0.7128	6000	5.3467
0.7722	6500	5.3086

Framework Versions

Python: 3.12.11
Sentence Transformers: 5.1.0
Transformers: 4.56.1
PyTorch: 2.8.0+cu126
Accelerate: 1.10.1
Datasets: 4.0.0
Tokenizers: 0.22.0

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",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}