eridu / README.md

rjurney

Major update to README.md for model card

2ca55d2 verified 4 months ago

preview code

raw

history blame

17.6 kB

metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:2130620
  - loss:ContrastiveLoss
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
widget:
  - source_sentence: Russell Jurney
    sentences:
      - Russell H. Jurney
      - Russ Jurney
      - Русс Джерни
  - source_sentence: Ben Lorica
    sentences:
      - Benjamin Lorica
      - 罗瑞卡
      - 罗睿姬
  - source_sentence: Yevgeny Prigozhin
    sentences:
      - Евге́ний Ви́кторович Приго́жин
      - Y. Prighozhin
  - source_sentence: M.R. James
    sentences:
      - Montague Rhodes James
      - J.R. James
      - Mr. James
  - source_sentence: Muhammad Ali
    sentences:
      - مُحَمَّد عَلِيّ
      - Mohammed Ali
      - Sonny Liston
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - cosine_mcc
model-index:
  - name: Graphlet-AI/eridu
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: sentence transformers paraphrase multilingual MiniLM L12 v2
          type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
        metrics:
          - type: cosine_accuracy
            value: 0.9905380542935456
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.6790644526481628
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.9856131536880567
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.6790644526481628
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.9816899806664392
            name: Cosine Precision
          - type: cosine_recall
            value: 0.9895678092399404
            name: Cosine Recall
          - type: cosine_ap
            value: 0.9977983578816215
            name: Cosine Ap
          - type: cosine_mcc
            value: 0.9785817179348335
            name: Cosine Mcc

Graphlet-AI/eridu

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 for person and company name matching using the Open Sanctions matcher training data. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used as part of a deep, fuzzy entity resolution process.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Maximum Sequence Length: 128 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Language: en
License: apache-2.0

Model Sources

Documentation: Graphlet-AI/eridu Documentation
Repository: Graphlet-AI/eridu on GitHub
Hugging Face: Graphlet-AI/eridu on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: 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})
)

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("Graphlet-AI/eridu")

names = [
    "Russell Jurney",
    "Russ Jurney",
    "Русс Джерни",
]

embeddings = model.encode(names)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

print(similarities.numpy())
# [[0.9999999  0.99406826 0.99406105]
#  [0.9940683  1.         0.9969202 ]
#  [0.99406105 0.9969202  1.        ]]

Evaluation

Metrics

Binary Classification

Dataset: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9905
cosine_accuracy_threshold	0.6791
cosine_f1	0.9856
cosine_f1_threshold	0.6791
cosine_precision	0.9817
cosine_recall	0.9896
cosine_ap	0.9978
cosine_mcc	0.9786

Training Details

Training Dataset

Unnamed Dataset

Size: 2,130,620 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string float
details
min: 3 tokens
mean: 9.28 tokens
max: 57 tokens

min: 3 tokens
mean: 9.11 tokens
max: 65 tokens

min: 0.0
mean: 0.34
max: 1.0
Samples:

sentence1 sentence2 label

ג'ק וייט Jack White 1.0

Абдуллоҳ Гул Савицкая Светлана 0.0

ショーン・ジャスティン・ペン شان پن 1.0

	sentence1	sentence2	label
type	string	string	float
details	min: 3 tokens mean: 9.28 tokens max: 57 tokens	min: 3 tokens mean: 9.11 tokens max: 65 tokens	min: 0.0 mean: 0.34 max: 1.0

sentence1	sentence2	label
`ג'ק וייט`	`Jack White`	`1.0`
`Абдуллоҳ Гул`	`Савицкая Светлана`	`0.0`
`ショーン・ジャスティン・ペン`	`شان پن`	`1.0`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 0.5,
    "size_average": true
}

Evaluation Dataset

Unnamed Dataset

Size: 266,328 evaluation samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string float
details
min: 3 tokens
mean: 9.27 tokens
max: 79 tokens

min: 3 tokens
mean: 8.99 tokens
max: 61 tokens

min: 0.0
mean: 0.32
max: 1.0

	sentence1	sentence2	label
type	string	string	float
details	min: 3 tokens mean: 9.27 tokens max: 79 tokens	min: 3 tokens mean: 8.99 tokens max: 61 tokens	min: 0.0 mean: 0.32 max: 1.0

Samples:

sentence1	sentence2	label
`Анатолий Николаевич Герасимов`	`Anatoli Nikolajewitsch Gerassimow`	`1.0`
`Igor Stanislavovitsj Prokopenko`	`Angelo Lauricella`	`0.0`
`Кофе, Линда`	`Святлана Яўгенаўна Савіцкая`	`0.0`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 0.5,
    "size_average": true
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 5000
per_device_eval_batch_size: 5000
gradient_accumulation_steps: 4
weight_decay: 0.02
num_train_epochs: 10
warmup_ratio: 0.1
fp16: True
load_best_model_at_end: True
optim: adafactor
gradient_checkpointing: 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: 5000
per_device_eval_batch_size: 5000
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 4
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.02
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 10
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: 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}
tp_size: 0
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: adafactor
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: True
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
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	sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap
-1	-1	-	-	0.7195
0.9368	100	-	0.0083	0.9597
1.8712	200	-	0.0043	0.9877
2.8056	300	-	0.0028	0.9936
3.7400	400	-	0.0021	0.9954
4.6745	500	0.0224	0.0016	0.9964
5.6089	600	-	0.0015	0.9970
6.5433	700	-	0.0014	0.9974
7.4778	800	-	0.0013	0.9975
8.4122	900	-	0.0013	0.9977
9.3466	1000	0.0052	0.0012	0.9978
9.9087	1060	-	0.0012	0.9978

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.12.9
Sentence Transformers: 3.4.1
Transformers: 4.51.3
PyTorch: 2.7.0+cu126
Accelerate: 1.6.0
Datasets: 3.6.0
Tokenizers: 0.21.1

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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}