Add new SentenceTransformer model

de48773 verified 9 months ago

25 kB

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:360
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: Details for hostname <hostname> please
    sentences:
      - Tell me about the entity/device <hostname>
      - I need the MAC address for <ip>
      - Tell me MAC address for IP <ip>
  - source_sentence: List all anomalies for hostname <hostname>
    sentences:
      - What are the anomalies for the entity with <hostname>
      - Say something about the device with MAC <mac>
      - Provide MAC address of <ip>
  - source_sentence: Fetch details of device <hostname>
    sentences:
      - Show anomalies detected for <hostname>
      - Provide me details of entity <hostname>
      - Provide MAC address of <ip>
  - source_sentence: I want to know about IP <ip>
    sentences:
      - Details for IP <ip> please
      - Say something about the device <hostname>
      - Provide MAC address of <ip>
  - source_sentence: Details for <hostname> please
    sentences:
      - Fetch details of device <mac>
      - Say something about the device with <hostname>
      - Fetch details of device <hostname>
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: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.05
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.05
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.075
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.016666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.01
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0075000000000000015
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.05
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.05
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.075
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.03579899373088597
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.02361111111111111
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.05892676282475917
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.05
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.05
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.075
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.016666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.01
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0075000000000000015
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.05
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.05
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.075
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.03579899373088597
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.02361111111111111
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.05892676282475917
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.05
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.05
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.016666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.01
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.01
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.05
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.05
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.043025614388833164
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.026111111111111106
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.057867541303413296
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.025
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.05
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.05
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.075
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.025
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.016666666666666666
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.01
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0075000000000000015
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.025
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.05
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.05
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.075
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.045025749891599534
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.03611111111111111
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.0700664255230172
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.025
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.05
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.125
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.008333333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.01
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.0125
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.025
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.05
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.125
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.04554503439298109
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.022638888888888885
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.05082432768780783
            name: Cosine Map@100

SentenceTransformer

This is a sentence-transformers model trained on the json dataset. 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
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- json

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': True, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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:

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("FAWAS97/bge-base-financial-matryoshka")
# Run inference
sentences = [
    'Details for <hostname> please',
    'Say something about the device with <hostname>',
    'Fetch details of device <mac>',
]
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, 0.8608, 0.6315],
#         [0.8608, 1.0000, 0.6646],
#         [0.6315, 0.6646, 1.0000]])

Evaluation

Metrics

Information Retrieval

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 768
}
```

Metric	Value
cosine_accuracy@1	0.0
cosine_accuracy@3	0.05
cosine_accuracy@5	0.05
cosine_accuracy@10	0.075
cosine_precision@1	0.0
cosine_precision@3	0.0167
cosine_precision@5	0.01
cosine_precision@10	0.0075
cosine_recall@1	0.0
cosine_recall@3	0.05
cosine_recall@5	0.05
cosine_recall@10	0.075
cosine_ndcg@10	0.0358
cosine_mrr@10	0.0236
cosine_map@100	0.0589

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 512
}
```

Metric	Value
cosine_accuracy@1	0.0
cosine_accuracy@3	0.05
cosine_accuracy@5	0.05
cosine_accuracy@10	0.075
cosine_precision@1	0.0
cosine_precision@3	0.0167
cosine_precision@5	0.01
cosine_precision@10	0.0075
cosine_recall@1	0.0
cosine_recall@3	0.05
cosine_recall@5	0.05
cosine_recall@10	0.075
cosine_ndcg@10	0.0358
cosine_mrr@10	0.0236
cosine_map@100	0.0589

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 256
}
```

Metric	Value
cosine_accuracy@1	0.0
cosine_accuracy@3	0.05
cosine_accuracy@5	0.05
cosine_accuracy@10	0.1
cosine_precision@1	0.0
cosine_precision@3	0.0167
cosine_precision@5	0.01
cosine_precision@10	0.01
cosine_recall@1	0.0
cosine_recall@3	0.05
cosine_recall@5	0.05
cosine_recall@10	0.1
cosine_ndcg@10	0.043
cosine_mrr@10	0.0261
cosine_map@100	0.0579

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 128
}
```

Metric	Value
cosine_accuracy@1	0.025
cosine_accuracy@3	0.05
cosine_accuracy@5	0.05
cosine_accuracy@10	0.075
cosine_precision@1	0.025
cosine_precision@3	0.0167
cosine_precision@5	0.01
cosine_precision@10	0.0075
cosine_recall@1	0.025
cosine_recall@3	0.05
cosine_recall@5	0.05
cosine_recall@10	0.075
cosine_ndcg@10	0.045
cosine_mrr@10	0.0361
cosine_map@100	0.0701

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator with these parameters:
```
{
    "truncate_dim": 64
}
```

Metric	Value
cosine_accuracy@1	0.0
cosine_accuracy@3	0.025
cosine_accuracy@5	0.05
cosine_accuracy@10	0.125
cosine_precision@1	0.0
cosine_precision@3	0.0083
cosine_precision@5	0.01
cosine_precision@10	0.0125
cosine_recall@1	0.0
cosine_recall@3	0.025
cosine_recall@5	0.05
cosine_recall@10	0.125
cosine_ndcg@10	0.0455
cosine_mrr@10	0.0226
cosine_map@100	0.0508

Training Details

Training Dataset

json

Dataset: json
Size: 360 training samples
Columns: positive and anchor
Approximate statistics based on the first 360 samples:
positive anchor
type string string
details
min: 8 tokens
mean: 10.77 tokens
max: 15 tokens

min: 8 tokens
mean: 10.91 tokens
max: 16 tokens
Samples:

positive anchor

Show hardware address of Fetch MAC for hostname

Show hardware address of Fetch MAC for

Does have problems? Show anomalies detected for

	positive	anchor
type	string	string
details	min: 8 tokens mean: 10.77 tokens max: 15 tokens	min: 8 tokens mean: 10.91 tokens max: 16 tokens

positive	anchor
`Show hardware address of`	`Fetch MAC for hostname`
`Show hardware address of`	`Fetch MAC for`
`Does have problems?`	`Show anomalies detected for`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        384,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: True
load_best_model_at_end: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-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: 4
max_steps: -1
lr_scheduler_type: cosine
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: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: True
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: True
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: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
1.0	1	0.0358	0.0358	0.0358	0.0526	0.0308
2.0	2	0.0358	0.0358	0.0430	0.0454	0.0380
3.0	3	0.0358	0.0358	0.0430	0.0450	0.0455
4.0	4	0.0358	0.0358	0.0430	0.0450	0.0455

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.11
Sentence Transformers: 5.1.0
Transformers: 4.56.1
PyTorch: 2.8.0+cu128
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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

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}
}