metadata

base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
datasets:
  - sentence-transformers/quora-duplicates
language:
  - en
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - dot_accuracy
  - dot_accuracy_threshold
  - dot_f1
  - dot_f1_threshold
  - dot_precision
  - dot_recall
  - dot_ap
  - manhattan_accuracy
  - manhattan_accuracy_threshold
  - manhattan_f1
  - manhattan_f1_threshold
  - manhattan_precision
  - manhattan_recall
  - manhattan_ap
  - euclidean_accuracy
  - euclidean_accuracy_threshold
  - euclidean_f1
  - euclidean_f1_threshold
  - euclidean_precision
  - euclidean_recall
  - euclidean_ap
  - max_accuracy
  - max_accuracy_threshold
  - max_f1
  - max_f1_threshold
  - max_precision
  - max_recall
  - max_ap
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:323432
  - loss:OnlineContrastiveLoss
widget:
  - source_sentence: >-
      How do I have a successful career in animation industry with all distance
      mode of education (from schooling)?
    sentences:
      - >-
        The LINE app is blocked in China. I bought a VPN, but it's still not
        working. Can someone help me?
      - What is independent?
      - How do I find all distance education schools in any city?
  - source_sentence: How can I get the funding for my startup without revealing my idea?
    sentences:
      - How has demonetization affected big business people like Mukesh Ambani?
      - How should I go about getting funding for my idea?
      - What are the advantages and disadvantages of studying an MBBS in China?
  - source_sentence: >-
      I am an okay looking young women but I am always feeling ugly since I'm
      not extremely beautiful. How can I stop those thoughts?
    sentences:
      - >-
        Whenever I think about my failures in life, I always feel that I lack
        some qualities. But which are those qualities, I am not able to find
        out. How can I find which qualities I lack?
      - What songs make you cry?
      - What does histrionic personality disorder feel like physically to you?
  - source_sentence: >-
      What do you think of Prime Minister Narendra Modi's decision to introduce
      new INR 500 and INR 2000 currency notes?
    sentences:
      - >-
        What do you think of the decision by the Indian Government to replace
        1000 notes with 2000 notes?
      - How do you find volume from density and mass?
      - What are the consequences of having a blood sugar level over 300?
  - source_sentence: Why do complementary angles have to be adjacent?
    sentences:
      - What is an AEG airsoft gun?
      - How can I get rid of my bad habits?
      - Can two adjacent angles be complementary?
model-index:
  - name: >-
      SentenceTransformer based on
      sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.8683618194860125
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.7981455326080322
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.8292439905343131
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.7598952651023865
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.7746589487768696
            name: Cosine Precision
          - type: cosine_recall
            value: 0.8921046460992195
            name: Cosine Recall
          - type: cosine_ap
            value: 0.8822291610822541
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.8359964382003018
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 17.112058639526367
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.7914425390403506
            name: Dot F1
          - type: dot_f1_threshold
            value: 16.083341598510742
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.7294350282485875
            name: Dot Precision
          - type: dot_recall
            value: 0.8649716946370549
            name: Dot Recall
          - type: dot_ap
            value: 0.8438654629805356
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.8568230725469341
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 46.94310760498047
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.8144082547946494
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 50.51482391357422
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.7656268427880646
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.8698288279234918
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.8636170591577621
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.8568849093472507
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 3.0017127990722656
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.8143016129285076
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 3.2429399490356445
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.7652309686542541
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.8700968076910194
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.8637642883474006
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.8683618194860125
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 46.94310760498047
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.8292439905343131
            name: Max F1
          - type: max_f1_threshold
            value: 50.51482391357422
            name: Max F1 Threshold
          - type: max_precision
            value: 0.7746589487768696
            name: Max Precision
          - type: max_recall
            value: 0.8921046460992195
            name: Max Recall
          - type: max_ap
            value: 0.8822291610822541
            name: Max Ap

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 on the sentence-transformers/quora-duplicates 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
Base model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Maximum Sequence Length: 128 tokens
Output Dimensionality: 384 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- sentence-transformers/quora-duplicates
Language: en

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': 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("DashReza7/paraphrase-multilingual-MiniLM-L12-v2_QuoraDuplicateDetection_FINETUNED")
# Run inference
sentences = [
    'Why do complementary angles have to be adjacent?',
    'Can two adjacent angles be complementary?',
    'How can I get rid of my bad habits?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Evaluation

Metrics

Binary Classification

Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.8684
cosine_accuracy_threshold	0.7981
cosine_f1	0.8292
cosine_f1_threshold	0.7599
cosine_precision	0.7747
cosine_recall	0.8921
cosine_ap	0.8822
dot_accuracy	0.836
dot_accuracy_threshold	17.1121
dot_f1	0.7914
dot_f1_threshold	16.0833
dot_precision	0.7294
dot_recall	0.865
dot_ap	0.8439
manhattan_accuracy	0.8568
manhattan_accuracy_threshold	46.9431
manhattan_f1	0.8144
manhattan_f1_threshold	50.5148
manhattan_precision	0.7656
manhattan_recall	0.8698
manhattan_ap	0.8636
euclidean_accuracy	0.8569
euclidean_accuracy_threshold	3.0017
euclidean_f1	0.8143
euclidean_f1_threshold	3.2429
euclidean_precision	0.7652
euclidean_recall	0.8701
euclidean_ap	0.8638
max_accuracy	0.8684
max_accuracy_threshold	46.9431
max_f1	0.8292
max_f1_threshold	50.5148
max_precision	0.7747
max_recall	0.8921
max_ap	0.8822

Training Details

Training Dataset

sentence-transformers/quora-duplicates

Dataset: sentence-transformers/quora-duplicates at 451a485
Size: 323,432 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 6 tokens
mean: 16.39 tokens
max: 80 tokens

min: 4 tokens
mean: 16.2 tokens
max: 71 tokens

0: ~62.10%
1: ~37.90%

	sentence1	sentence2	label
type	string	string	int
details	min: 6 tokens mean: 16.39 tokens max: 80 tokens	min: 4 tokens mean: 16.2 tokens max: 71 tokens	0: ~62.10% 1: ~37.90%

Samples:

sentence1	sentence2	label
`Which are the best compilers for C language (for Windows 10)?`	`Which is the best open source C/C++ compiler for Windows?`	`0`
`How much does YouTube pay per 1000 views in India?`	`How much does youtube pay per 1000 views?`	`0`
`What parts do I need to build my own PC?`	`I want to build a new computer. What parts do I need?`	`1`

Loss: OnlineContrastiveLoss

Evaluation Dataset

sentence-transformers/quora-duplicates

Dataset: sentence-transformers/quora-duplicates at 451a485
Size: 80,858 evaluation samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 6 tokens
mean: 16.48 tokens
max: 79 tokens

min: 6 tokens
mean: 16.76 tokens
max: 101 tokens

0: ~63.90%
1: ~36.10%

	sentence1	sentence2	label
type	string	string	int
details	min: 6 tokens mean: 16.48 tokens max: 79 tokens	min: 6 tokens mean: 16.76 tokens max: 101 tokens	0: ~63.90% 1: ~36.10%

Samples:

sentence1	sentence2	label
`How many stories got busted on Quora while being anonymous?`	`Can what I say on Quora anonymously be used against me legally?`	`0`
`What are innovative mechanical component designs?`	`What is the Innovation design?`	`0`
`What is the best way to learn phrasal verbs?`	`Why should I learn phrasal verbs?`	`1`

Loss: OnlineContrastiveLoss

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 256
per_device_eval_batch_size: 256
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
fp16: 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: 256
per_device_eval_batch_size: 256
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_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: 1
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: 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}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
dispatch_batches: None
split_batches: 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
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	max_ap
0.0791	100	-	8.0607	0.8164
0.1582	200	-	7.3012	0.8445
0.2373	300	-	6.9626	0.8582
0.3165	400	-	6.7901	0.8639
0.3956	500	7.5229	6.6498	0.8694
0.4747	600	-	6.5315	0.8736
0.5538	700	-	6.4686	0.8766
0.6329	800	-	6.4027	0.8787
0.7120	900	-	6.3108	0.8797
0.7911	1000	6.4636	6.2862	0.8812
0.8703	1100	-	6.2449	0.8818
0.9494	1200	-	6.2344	0.8822

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.42.4
PyTorch: 2.3.1+cu121
Accelerate: 0.32.1
Datasets: 2.21.0
Tokenizers: 0.19.1

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",
}