stsb-distilbert-base-ocl / README.md

tomaarsen HF Staff

Add new SentenceTransformer model.

3399e41 verified over 1 year ago

preview code

raw

history blame contribute delete

29.5 kB

metadata

language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - loss:OnlineContrastiveLoss
base_model: sentence-transformers/stsb-distilbert-base
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
  - average_precision
  - f1
  - precision
  - recall
  - threshold
  - 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
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
widget:
  - source_sentence: Why did he go MIA?
    sentences:
      - Why did Yahoo kill Konfabulator?
      - Why do people get angry with me?
      - What are the best waterproof guns?
  - source_sentence: Who is a soulmate?
    sentences:
      - Is she the “One”?
      - Who is Pakistan's biggest enemy?
      - Will smoking weed help with my anxiety?
  - source_sentence: Is this poem good?
    sentences:
      - Is my poem any good?
      - How can I become a good speaker?
      - What is feminism?
  - source_sentence: Who invented Yoga?
    sentences:
      - How was yoga invented?
      - Who owns this number 3152150252?
      - What is Dynamics CRM Services?
  - source_sentence: Is stretching bad?
    sentences:
      - Is stretching good for you?
      - If i=0; what will i=i++ do to i?
      - What is the Output of this C program ?
pipeline_tag: sentence-similarity
co2_eq_emissions:
  emissions: 15.707175691967695
  energy_consumed: 0.040409299905757354
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
  ram_total_size: 31.777088165283203
  hours_used: 0.202
  hardware_used: 1 x NVIDIA GeForce RTX 3090
model-index:
  - name: SentenceTransformer based on sentence-transformers/stsb-distilbert-base
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: quora duplicates
          type: quora-duplicates
        metrics:
          - type: cosine_accuracy
            value: 0.86
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.8104104995727539
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.8250591016548463
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.7247534394264221
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.7347368421052631
            name: Cosine Precision
          - type: cosine_recall
            value: 0.9407008086253369
            name: Cosine Recall
          - type: cosine_ap
            value: 0.887247904332921
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.828
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 157.35491943359375
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.7898550724637681
            name: Dot F1
          - type: dot_f1_threshold
            value: 145.7113037109375
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.7155361050328227
            name: Dot Precision
          - type: dot_recall
            value: 0.8814016172506739
            name: Dot Recall
          - type: dot_ap
            value: 0.8369433397850002
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.868
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 208.00347900390625
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.8307692307692308
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 208.00347900390625
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.7921760391198044
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.8733153638814016
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.8868217413983182
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.867
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 9.269388198852539
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.8301404853128991
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 9.525729179382324
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.7888349514563107
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.876010781671159
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.8884154240019244
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.868
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 208.00347900390625
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.8307692307692308
            name: Max F1
          - type: max_f1_threshold
            value: 208.00347900390625
            name: Max F1 Threshold
          - type: max_precision
            value: 0.7921760391198044
            name: Max Precision
          - type: max_recall
            value: 0.9407008086253369
            name: Max Recall
          - type: max_ap
            value: 0.8884154240019244
            name: Max Ap
      - task:
          type: paraphrase-mining
          name: Paraphrase Mining
        dataset:
          name: quora duplicates dev
          type: quora-duplicates-dev
        metrics:
          - type: average_precision
            value: 0.534436244125929
            name: Average Precision
          - type: f1
            value: 0.5447997274541295
            name: F1
          - type: precision
            value: 0.5311002514589362
            name: Precision
          - type: recall
            value: 0.5592246590398161
            name: Recall
          - type: threshold
            value: 0.8626040816307068
            name: Threshold
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.928
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9712
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9782
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9874
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.928
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.4151333333333334
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.26656
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.14166
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7993523853760618
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9341884771405065
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9560896250710075
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9766088525134997
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9516150309696244
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.9509392857142857
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.9390263696194139
            name: Cosine Map@100
          - type: dot_accuracy@1
            value: 0.8926
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.9518
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9658
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9768
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.8926
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.40273333333333333
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.26076
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.13882
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.7679620996617761
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.9105756956997251
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9402185219519044
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9623418143294613
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.9263520741106431
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.9243020634920638
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.9094019438194247
            name: Dot Map@100

SentenceTransformer based on sentence-transformers/stsb-distilbert-base

This is a sentence-transformers model finetuned from sentence-transformers/stsb-distilbert-base on the sentence-transformers/quora-duplicates dataset. 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: sentence-transformers/stsb-distilbert-base
Maximum Sequence Length: 128 tokens
Output Dimensionality: 768 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: DistilBertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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("tomaarsen/stsb-distilbert-base-ocl")
# Run inference
sentences = [
    'Is stretching bad?',
    'Is stretching good for you?',
    'If i=0; what will i=i++ do to i?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Binary Classification

Dataset: quora-duplicates
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.86
cosine_accuracy_threshold	0.8104
cosine_f1	0.8251
cosine_f1_threshold	0.7248
cosine_precision	0.7347
cosine_recall	0.9407
cosine_ap	0.8872
dot_accuracy	0.828
dot_accuracy_threshold	157.3549
dot_f1	0.7899
dot_f1_threshold	145.7113
dot_precision	0.7155
dot_recall	0.8814
dot_ap	0.8369
manhattan_accuracy	0.868
manhattan_accuracy_threshold	208.0035
manhattan_f1	0.8308
manhattan_f1_threshold	208.0035
manhattan_precision	0.7922
manhattan_recall	0.8733
manhattan_ap	0.8868
euclidean_accuracy	0.867
euclidean_accuracy_threshold	9.2694
euclidean_f1	0.8301
euclidean_f1_threshold	9.5257
euclidean_precision	0.7888
euclidean_recall	0.876
euclidean_ap	0.8884
max_accuracy	0.868
max_accuracy_threshold	208.0035
max_f1	0.8308
max_f1_threshold	208.0035
max_precision	0.7922
max_recall	0.9407
max_ap	0.8884

Paraphrase Mining

Dataset: quora-duplicates-dev
Evaluated with ParaphraseMiningEvaluator

Metric	Value
average_precision	0.5344
f1	0.5448
precision	0.5311
recall	0.5592
threshold	0.8626

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.928
cosine_accuracy@3	0.9712
cosine_accuracy@5	0.9782
cosine_accuracy@10	0.9874
cosine_precision@1	0.928
cosine_precision@3	0.4151
cosine_precision@5	0.2666
cosine_precision@10	0.1417
cosine_recall@1	0.7994
cosine_recall@3	0.9342
cosine_recall@5	0.9561
cosine_recall@10	0.9766
cosine_ndcg@10	0.9516
cosine_mrr@10	0.9509
cosine_map@100	0.939
dot_accuracy@1	0.8926
dot_accuracy@3	0.9518
dot_accuracy@5	0.9658
dot_accuracy@10	0.9768
dot_precision@1	0.8926
dot_precision@3	0.4027
dot_precision@5	0.2608
dot_precision@10	0.1388
dot_recall@1	0.768
dot_recall@3	0.9106
dot_recall@5	0.9402
dot_recall@10	0.9623
dot_ndcg@10	0.9264
dot_mrr@10	0.9243
dot_map@100	0.9094

Training Details

Training Dataset

sentence-transformers/quora-duplicates

Dataset: sentence-transformers/quora-duplicates at 451a485
Size: 100,000 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: 15.5 tokens
max: 45 tokens

min: 6 tokens
mean: 15.46 tokens
max: 78 tokens

0: ~64.10%
1: ~35.90%

	sentence1	sentence2	label
type	string	string	int
details	min: 6 tokens mean: 15.5 tokens max: 45 tokens	min: 6 tokens mean: 15.46 tokens max: 78 tokens	0: ~64.10% 1: ~35.90%

Samples:

sentence1	sentence2	label
`What are the best ecommerce blogs to do guest posts on about SEO to gain new clients?`	`Interested in being a guest blogger for an ecommerce marketing blog?`	`0`
`How do I learn Informatica online training?`	`What is Informatica online training?`	`0`
`What effects does marijuana use have on the flu?`	`What effects does Marijuana use have on the common cold?`	`0`

Loss: OnlineContrastiveLoss

Evaluation Dataset

sentence-transformers/quora-duplicates

Dataset: sentence-transformers/quora-duplicates at 451a485
Size: 1,000 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: 15.82 tokens
max: 46 tokens

min: 6 tokens
mean: 15.91 tokens
max: 72 tokens

0: ~62.90%
1: ~37.10%

	sentence1	sentence2	label
type	string	string	int
details	min: 6 tokens mean: 15.82 tokens max: 46 tokens	min: 6 tokens mean: 15.91 tokens max: 72 tokens	0: ~62.90% 1: ~37.10%

Samples:

sentence1	sentence2	label
`How should I prepare for JEE Mains 2017?`	`How do I prepare for the JEE 2016?`	`0`
`What is the gate exam?`	`What is the GATE exam in engineering?`	`0`
`Where do IRS officers get posted?`	`Does IRS Officers get posted abroad?`	`0`

Loss: OnlineContrastiveLoss

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: False
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
learning_rate: 5e-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
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: None
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_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	cosine_map@100	quora-duplicates-dev_average_precision	quora-duplicates_max_ap
0	0	-	-	0.9235	0.4200	0.7276
0.0640	100	2.5123	-	-	-	-
0.1280	200	2.0534	-	-	-	-
0.1599	250	-	1.7914	0.9127	0.4082	0.8301
0.1919	300	1.9505	-	-	-	-
0.2559	400	1.9836	-	-	-	-
0.3199	500	1.8462	1.5923	0.9190	0.4445	0.8688
0.3839	600	1.7734	-	-	-	-
0.4479	700	1.7918	-	-	-	-
0.4798	750	-	1.5461	0.9291	0.4943	0.8707
0.5118	800	1.6157	-	-	-	-
0.5758	900	1.7244	-	-	-	-
0.6398	1000	1.7322	1.5294	0.9309	0.5048	0.8808
0.7038	1100	1.6825	-	-	-	-
0.7678	1200	1.6823	-	-	-	-
0.7997	1250	-	1.4812	0.9351	0.5126	0.8865
0.8317	1300	1.5707	-	-	-	-
0.8957	1400	1.6145	-	-	-	-
0.9597	1500	1.5795	1.4705	0.9390	0.5344	0.8884

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.040 kWh
Carbon Emitted: 0.016 kg of CO2
Hours Used: 0.202 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3090
CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
RAM Size: 31.78 GB

Framework Versions

Python: 3.11.6
Sentence Transformers: 3.0.0.dev0
Transformers: 4.41.0.dev0
PyTorch: 2.3.0+cu121
Accelerate: 0.26.1
Datasets: 2.18.0
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",
}