---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:9829
- loss:MultipleNegativesRankingLoss
base_model: intfloat/multilingual-e5-small
widget:
- source_sentence: 'query: DAIRY PRODUCE; CHEESE (NOT GRATED, POWDERED OR PROCESSED),
N.E.C. IN HEADING NO. 0406 POWDERED IN VACUUM PACKS 14290 PCS'
sentences:
- 'passage: Tôm đông lạnh, sơ chế, bỏ đầu bỏ vỏ, để xuất khẩu theo điều kiện thương
mại tiêu chuẩn, điều kiện giao hàng FOB'
- 'passage: Phô mai loại khác, để thông quan và khai báo nhập khẩu, kèm hóa đơn
thương mại và phiếu đóng gói'
- 'passage: Organic fresh tomatoes, hydroponic, for bulk procurement program, palletized
for container shipment'
- source_sentence: 'query: Tôm thẻ chân trắng đông lạnh xuất khẩu'
sentences:
- 'passage: Red Delicious apples, fresh, for export'
- 'passage: Cá nước ngọt đông lạnh, đóng thùng'
- 'passage: กุ้งแช่แข็ง IQF ส่งออก สำหรับการขนส่งข้ามพรมแดน เงื่อนไขการขนส่ง CIF'
- source_sentence: 'query: 新鲜脐橙 加州进口，用于国际批发分销，托盘装集装箱运输'
sentences:
- 'passage: VEGETABLES; TOMATOES, FRESH OR CHILLED SIZE 72MM IN REEFER CONTAINER'
- 'passage: CONVENTIONAL FRUIT, EDIBLE; ORANGES, FRESH OR DRIED IN BULK BAGS, for
industrial procurement contract, shipping term FOB'
- 'passage: Thịt bò đông lạnh không xương, Halal'
- source_sentence: 'query: MEAT; OF BOVINE ANIMALS, BONELESS CUTS, FRESH OR CHILLED
IN CONTAINER, for cross-border shipment, shipping term FOB'
sentences:
- 'passage: Fresh plum tomatoes for Italian cooking, for bulk procurement program,
palletized for container shipment'
- 'passage: Boneless beef sirloin, fresh, not frozen, for bonded warehouse delivery,
palletized for container shipment'
- 'passage: ORGANIC VEGETABLES, ALLIACEOUS; ONIONS AND SHALLOTS, FRESH OR CHILLED
WHITE ONION VARIETY IN CARTONS'
- source_sentence: 'query: CRUSTACEANS; FROZEN, SHRIMPS AND PRAWNS, EXCLUDING COLD-WATER
VARIETIES, IN SHELL OR NOT, SMOKED, COOKED OR NOT BEFORE OR DURING SMOKING; IN
SHELL, COOKED BY STEAMING OR BY BOILING IN WATER 21/25 COUNT IN SACKS 8576.9 KG'
sentences:
- 'passage: กุ้งแช่แข็ง IQF ส่งออก สำหรับการขนส่งข้ามพรมแดน เงื่อนไขการขนส่ง CIF'
- 'passage: DAIRY PRODUCE; MILK AND CREAM, CONCENTRATED OR CONTAINING ADDED SUGAR
OR OTHER SWEETENING MATTER, IN POWDER, GRANULES OR OTHER SOLID FORMS, OF A FAT
CONTENT NOT EXCEEDING 1.5% (BY WEIGHT) FAT CONTENT 3.5% IN VACUUM PACKS'
- 'passage: CRUSTACEANS; FROZEN, SHRIMPS AND PRAWNS, EXCLUDING COLD-WATER VARIETIES,
IN SHELL OR NOT, SMOKED, COOKED OR NOT BEFORE OR DURING SMOKING; IN SHELL, COOKED
BY STEAMING OR BY BOILING IN WATER'
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on intfloat/multilingual-e5-small
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). It maps sentences & paragraphs to a 384-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-small](https://huggingface.co/intfloat/multilingual-e5-small)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 384 dimensions
- **Similarity Function:** Cosine Similarity
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'})
(1): Pooling({'word_embedding_dimension': 384, '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:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
'query: CRUSTACEANS; FROZEN, SHRIMPS AND PRAWNS, EXCLUDING COLD-WATER VARIETIES, IN SHELL OR NOT, SMOKED, COOKED OR NOT BEFORE OR DURING SMOKING; IN SHELL, COOKED BY STEAMING OR BY BOILING IN WATER 21/25 COUNT IN SACKS 8576.9 KG',
'passage: CRUSTACEANS; FROZEN, SHRIMPS AND PRAWNS, EXCLUDING COLD-WATER VARIETIES, IN SHELL OR NOT, SMOKED, COOKED OR NOT BEFORE OR DURING SMOKING; IN SHELL, COOKED BY STEAMING OR BY BOILING IN WATER',
'passage: กุ้งแช่แข็ง IQF ส่งออก สำหรับการขนส่งข้ามพรมแดน เงื่อนไขการขนส่ง CIF',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9576, 0.7030],
# [0.9576, 1.0000, 0.6773],
# [0.7030, 0.6773, 1.0000]])
```
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 9,829 training samples
* Columns: anchor and positive
* Approximate statistics based on the first 1000 samples:
| | anchor | positive |
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | - min: 9 tokens
- mean: 36.3 tokens
- max: 114 tokens
| - min: 8 tokens
- mean: 34.27 tokens
- max: 113 tokens
|
* Samples:
| anchor | positive |
|:---------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| query: Chilled beef tenderloin, boneless, vacuum packed | passage: Thịt bò không xương tươi cho nhà hàng, cho hợp đồng mua sắm công nghiệp, hàng lô hỗn hợp |
| query: 优质鲜牛肉 无骨 出口级别 | passage: 优质鲜牛肉 无骨 出口级别，用于国际批发分销，装20尺集装箱 |
| query: 冷却去骨黄牛肉 真空包装 | passage: FROZEN MEAT; OF BOVINE ANIMALS, BONELESS CUTS, FRESH OR CHILLED SKIN-ON IN TINS 15204.2 KG, for industrial procurement contract, shipping term CIF |
* Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 4
- `num_train_epochs`: 2
- `learning_rate`: 2e-05
- `warmup_steps`: 0.1
- `gradient_accumulation_steps`: 16
- `warmup_ratio`: 0.1
#### All Hyperparameters
Click to expand
- `per_device_train_batch_size`: 4
- `num_train_epochs`: 2
- `max_steps`: -1
- `learning_rate`: 2e-05
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: None
- `warmup_steps`: 0.1
- `optim`: adamw_torch_fused
- `optim_args`: None
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `optim_target_modules`: None
- `gradient_accumulation_steps`: 16
- `average_tokens_across_devices`: True
- `max_grad_norm`: 1.0
- `label_smoothing_factor`: 0.0
- `bf16`: False
- `fp16`: False
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `use_liger_kernel`: False
- `liger_kernel_config`: None
- `use_cache`: False
- `neftune_noise_alpha`: None
- `torch_empty_cache_steps`: None
- `auto_find_batch_size`: False
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `include_num_input_tokens_seen`: no
- `log_level`: passive
- `log_level_replica`: warning
- `disable_tqdm`: False
- `project`: huggingface
- `trackio_space_id`: trackio
- `eval_strategy`: no
- `per_device_eval_batch_size`: 8
- `prediction_loss_only`: True
- `eval_on_start`: False
- `eval_do_concat_batches`: True
- `eval_use_gather_object`: False
- `eval_accumulation_steps`: None
- `include_for_metrics`: []
- `batch_eval_metrics`: False
- `save_only_model`: False
- `save_on_each_node`: False
- `enable_jit_checkpoint`: False
- `push_to_hub`: False
- `hub_private_repo`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_always_push`: False
- `hub_revision`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `restore_callback_states_from_checkpoint`: False
- `full_determinism`: False
- `seed`: 42
- `data_seed`: None
- `use_cpu`: False
- `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
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `dataloader_prefetch_factor`: None
- `remove_unused_columns`: True
- `label_names`: None
- `train_sampling_strategy`: random
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `ddp_backend`: None
- `ddp_timeout`: 1800
- `fsdp`: []
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `deepspeed`: None
- `debug`: []
- `skip_memory_metrics`: True
- `do_predict`: False
- `resume_from_checkpoint`: None
- `warmup_ratio`: 0.1
- `local_rank`: -1
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}