---
language:
- en
license: apache-2.0
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:208
- loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-base-en
widget:
- source_sentence: '
Name : Gastronomia Italia
Category: Dining Services, Business Meetings
Department: Sales
Location: Milan, Italy
Amount: 143.27
Card: EU Client Engagement
Trip Name: Milan Networking Event
'
sentences:
- Professional Services
- 'Travel: Meals & Entertainment'
- Advertising & Marketing
- source_sentence: '
Name : NexaCloud Technologies
Category: Implement Services, Cloud Solutions
Department: IT Operations
Location: Berlin, Germany
Amount: 1490.65
Card: Cloud Optimization Initiative
Trip Name: unknown
'
sentences:
- Conference & Event Fees
- Software & Licenses
- Hardware & Equipment
- source_sentence: '
Name : EcoStay Hospitality Group
Category: Lodging Services, Sustainability Consulting
Department: Executive
Location: Barcelona, Spain
Amount: 978.45
Card: International Strategy Meeting
Trip Name: unknown
'
sentences:
- 'Travel: Accommodation'
- 'Travel: Accommodation'
- 'Travel: Meals & Entertainment'
- source_sentence: '
Name : FusionLink
Category: Event Management Solutions, Digital Strategy Services
Department: Sales
Location: New York, NY
Amount: 982.75
Card: Product Launch Activation
Trip Name: unknown
'
sentences:
- Advertising & Marketing
- Subscriptions & Memberships
- Conference & Event Fees
- source_sentence: '
Name : BlueWave Innovations
Category: Renewable Energy Solutions, Infrastructure Management
Department: Office Administration
Location: Miami, FL
Amount: 935.47
Card: Building Energy Optimization
Trip Name: unknown
'
sentences:
- Office Rent & Utilities
- Hardware & Equipment
- Data Services & Analytics
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: BGE Base EN Cost Categories Fine-tuned
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: ir eval eval
type: ir_eval_eval
metrics:
- type: cosine_accuracy@1
value: 0.3333333333333333
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.6515151515151515
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.7272727272727273
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8636363636363636
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.3333333333333333
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.21717171717171715
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.14545454545454545
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08636363636363635
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.3333333333333333
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.6515151515151515
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.7272727272727273
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.8636363636363636
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.5961980756043176
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.5113335738335738
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.5214978265446181
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: ir eval test
type: ir_eval_test
metrics:
- type: cosine_accuracy@1
value: 0.5961538461538461
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9038461538461539
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9615384615384616
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 1.0
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.5961538461538461
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.30128205128205127
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.19230769230769224
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09999999999999996
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.5961538461538461
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9038461538461539
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9615384615384616
name: Cosine Recall@5
- type: cosine_recall@10
value: 1.0
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8208291440797191
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.761080586080586
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.7610805860805863
name: Cosine Map@100
---
# BGE Base EN Cost Categories Fine-tuned
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en). 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:** [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Language:** en
- **License:** apache-2.0
### 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': True, 'architecture': 'BertModel'})
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("aaa961/bge-base-en-cost-categories-3sets")
# Run inference
sentences = [
'\nName : BlueWave Innovations\nCategory: Renewable Energy Solutions, Infrastructure Management\nDepartment: Office Administration\nLocation: Miami, FL\nAmount: 935.47\nCard: Building Energy Optimization\nTrip Name: unknown\n',
'Office Rent & Utilities',
'Data Services & Analytics',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7791, 0.7019],
# [0.7791, 1.0000, 0.7114],
# [0.7019, 0.7114, 1.0000]])
```
## Evaluation
### Metrics
#### Information Retrieval
* Datasets: `ir_eval_eval` and `ir_eval_test`
* Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | ir_eval_eval | ir_eval_test |
|:--------------------|:-------------|:-------------|
| cosine_accuracy@1 | 0.3333 | 0.5962 |
| cosine_accuracy@3 | 0.6515 | 0.9038 |
| cosine_accuracy@5 | 0.7273 | 0.9615 |
| cosine_accuracy@10 | 0.8636 | 1.0 |
| cosine_precision@1 | 0.3333 | 0.5962 |
| cosine_precision@3 | 0.2172 | 0.3013 |
| cosine_precision@5 | 0.1455 | 0.1923 |
| cosine_precision@10 | 0.0864 | 0.1 |
| cosine_recall@1 | 0.3333 | 0.5962 |
| cosine_recall@3 | 0.6515 | 0.9038 |
| cosine_recall@5 | 0.7273 | 0.9615 |
| cosine_recall@10 | 0.8636 | 1.0 |
| **cosine_ndcg@10** | **0.5962** | **0.8208** |
| cosine_mrr@10 | 0.5113 | 0.7611 |
| cosine_map@100 | 0.5215 | 0.7611 |
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 208 training samples
* Columns: anchor and positive
* Approximate statistics based on the first 208 samples:
| | anchor | positive |
|:--------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
| type | string | string |
| details | - min: 33 tokens
- mean: 39.84 tokens
- max: 49 tokens
| - min: 3 tokens
- mean: 5.62 tokens
- max: 7 tokens
|
* Samples:
| anchor | positive |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------|
|
Name : Transcend
Category: Upskilling
Department: Human Resource
Location: London, UK
Amount: 859.47
Card: Technology Skills Enhancement
Trip Name: unknown
Employee Training & Development |
|
Name : Ayden
Category: Financial Software
Department: Finance
Location: Berlin, DE
Amount: 1273.45
Card: Enterprise Technology Services
Trip Name: unknown
Subscription & Revenue Infrastructure |
|
Name : Urban Sphere
Category: Utilities Management, Facility Services
Department: Office Administration
Location: New York, NY
Amount: 937.32
Card: Monthly Operations Budget
Trip Name: unknown
Office Rent & Utilities |
* 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,
"directions": [
"query_to_doc"
],
"partition_mode": "joint",
"hardness_mode": null,
"hardness_strength": 0.0
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 16
- `num_train_epochs`: 5
- `learning_rate`: 2e-05
- `lr_scheduler_type`: cosine
- `warmup_steps`: 0.1
- `optim`: adamw_torch_fused
- `gradient_accumulation_steps`: 4
- `bf16`: True
- `eval_strategy`: epoch
- `per_device_eval_batch_size`: 16
- `load_best_model_at_end`: True
#### All Hyperparameters
Click to expand
- `per_device_train_batch_size`: 16
- `num_train_epochs`: 5
- `max_steps`: -1
- `learning_rate`: 2e-05
- `lr_scheduler_type`: cosine
- `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`: 4
- `average_tokens_across_devices`: True
- `max_grad_norm`: 1.0
- `label_smoothing_factor`: 0.0
- `bf16`: True
- `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`: epoch
- `per_device_eval_batch_size`: 16
- `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`: True
- `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`: None
- `local_rank`: -1
- `prompts`: None
- `batch_sampler`: batch_sampler
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}