SentenceTransformer based on sentence-transformers/multi-qa-mpnet-base-dot-v1
This is a sentence-transformers model finetuned from sentence-transformers/multi-qa-mpnet-base-dot-v1 on the PiC/phrase_similarity 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/multi-qa-mpnet-base-dot-v1
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 768 tokens
- Similarity Function: Dot Product
- Training Dataset:
- 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': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
(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})
)
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("Deehan1866/finetuned-sentence-transformers-multi-qa-mpnet-base-dot-v1")
# Run inference
sentences = [
"She wants to write about Keima but suffers a major case of writer's block.",
"She wants to write about Keima but suffers a huge occurrence of writer's block.",
'specific medical status of movement and the general condition of movement both are conditions under which contradictions can move.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
Evaluation
Metrics
Binary Classification
- Dataset:
quora-duplicates-dev
- Evaluated with
BinaryClassificationEvaluator
Metric | Value |
---|---|
cosine_accuracy | 0.681 |
cosine_accuracy_threshold | 0.8657 |
cosine_f1 | 0.7373 |
cosine_f1_threshold | 0.5984 |
cosine_precision | 0.6161 |
cosine_recall | 0.918 |
cosine_ap | 0.7183 |
dot_accuracy | 0.678 |
dot_accuracy_threshold | 35.8649 |
dot_f1 | 0.7362 |
dot_f1_threshold | 26.9072 |
dot_precision | 0.6145 |
dot_recall | 0.918 |
dot_ap | 0.6677 |
manhattan_accuracy | 0.682 |
manhattan_accuracy_threshold | 75.963 |
manhattan_f1 | 0.7362 |
manhattan_f1_threshold | 128.1774 |
manhattan_precision | 0.6182 |
manhattan_recall | 0.91 |
manhattan_ap | 0.7193 |
euclidean_accuracy | 0.682 |
euclidean_accuracy_threshold | 3.4474 |
euclidean_f1 | 0.7362 |
euclidean_f1_threshold | 6.0247 |
euclidean_precision | 0.6145 |
euclidean_recall | 0.918 |
euclidean_ap | 0.7195 |
max_accuracy | 0.682 |
max_accuracy_threshold | 75.963 |
max_f1 | 0.7373 |
max_f1_threshold | 128.1774 |
max_precision | 0.6182 |
max_recall | 0.918 |
max_ap | 0.7195 |
Training Details
Training Dataset
PiC/phrase_similarity
- Dataset: PiC/phrase_similarity at fc67ce7
- Size: 7,004 training samples
- Columns:
sentence1
,sentence2
, andlabel
- Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label type string string int details - min: 12 tokens
- mean: 26.35 tokens
- max: 57 tokens
- min: 12 tokens
- mean: 26.89 tokens
- max: 58 tokens
- 0: ~48.80%
- 1: ~51.20%
- Samples:
sentence1 sentence2 label newly formed camp is released from the membrane and diffuses across the intracellular space where it serves to activate pka.
recently made encampment is released from the membrane and diffuses across the intracellular space where it serves to activate pka.
0
According to one data, in 1910, on others – in 1915, the mansion became Natalya Dmitriyevna Shchuchkina's property.
According to a particular statistic, in 1910, on others – in 1915, the mansion became Natalya Dmitriyevna Shchuchkina's property.
1
Note that Fact 1 does not assume any particular structure on the set formula_65.
Note that Fact 1 does not assume any specific edifice on the set formula_65.
0
- Loss:
SoftmaxLoss
Evaluation Dataset
PiC/phrase_similarity
- Dataset: PiC/phrase_similarity at fc67ce7
- Size: 1,000 evaluation samples
- Columns:
sentence1
,sentence2
, andlabel
- Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label type string string int details - min: 9 tokens
- mean: 26.21 tokens
- max: 61 tokens
- min: 10 tokens
- mean: 26.8 tokens
- max: 61 tokens
- 0: ~50.00%
- 1: ~50.00%
- Samples:
sentence1 sentence2 label after theo's apparent death, she decides to leave first colony and ends up traveling with the apostles.
after theo's apparent death, she decides to leave original settlement and ends up traveling with the apostles.
0
The guard assigned to Vivian leaves her to prevent the robbery, allowing her to connect to the bank's network.
The guard assigned to Vivian leaves her to prevent the robbery, allowing her to connect to the bank's locations.
0
Two days later Louis XVI banished Necker by a "lettre de cachet" for his very public exchange of pamphlets.
Two days later Louis XVI banished Necker by a "lettre de cachet" for his very free forum of pamphlets.
0
- Loss:
SoftmaxLoss
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 16per_device_eval_batch_size
: 16learning_rate
: 2e-05num_train_epochs
: 5warmup_ratio
: 0.1load_best_model_at_end
: True
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 16per_device_eval_batch_size
: 16per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonelearning_rate
: 2e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 5max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.1warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Falsefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Trueignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Falsehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseeval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falseeval_on_start
: Falsebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | Training Loss | loss | quora-duplicates-dev_max_ap |
---|---|---|---|---|
0 | 0 | - | - | 0.6564 |
0.2283 | 100 | - | 0.6941 | 0.6565 |
0.4566 | 200 | - | 0.6899 | 0.6713 |
0.6849 | 300 | - | 0.6467 | 0.7247 |
0.9132 | 400 | - | 0.5957 | 0.7231 |
1.1416 | 500 | 0.6571 | 0.6093 | 0.7044 |
1.3699 | 600 | - | 0.5578 | 0.7195 |
1.5982 | 700 | - | 0.5626 | 0.7372 |
1.8265 | 800 | - | 0.5790 | 0.7413 |
2.0548 | 900 | - | 0.5648 | 0.7405 |
2.2831 | 1000 | 0.519 | 0.5820 | 0.7467 |
2.5114 | 1100 | - | 0.5976 | 0.7455 |
2.7397 | 1200 | - | 0.6026 | 0.7335 |
2.9680 | 1300 | - | 0.6231 | 0.7422 |
3.1963 | 1400 | - | 0.6514 | 0.7376 |
3.4247 | 1500 | 0.3903 | 0.6695 | 0.7379 |
3.6530 | 1600 | - | 0.6610 | 0.7339 |
3.8813 | 1700 | - | 0.6811 | 0.7318 |
4.1096 | 1800 | - | 0.7205 | 0.7274 |
4.3379 | 1900 | - | 0.7333 | 0.7332 |
4.5662 | 2000 | 0.3036 | 0.7353 | 0.7323 |
4.7945 | 2100 | - | 0.7293 | 0.7322 |
5.0 | 2190 | - | - | 0.7195 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.10.10
- Sentence Transformers: 3.0.1
- Transformers: 4.42.3
- PyTorch: 2.2.1+cu121
- Accelerate: 0.32.1
- Datasets: 2.20.0
- Tokenizers: 0.19.1
Citation
BibTeX
Sentence Transformers and SoftmaxLoss
@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",
}
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Deehan1866/finetuned-sentence-transformers-multi-qa-mpnet-base-dot-v1
Finetuned
this model
Dataset used to train Deehan1866/finetuned-sentence-transformers-multi-qa-mpnet-base-dot-v1
Evaluation results
- Cosine Accuracy on quora duplicates devself-reported0.681
- Cosine Accuracy Threshold on quora duplicates devself-reported0.866
- Cosine F1 on quora duplicates devself-reported0.737
- Cosine F1 Threshold on quora duplicates devself-reported0.598
- Cosine Precision on quora duplicates devself-reported0.616
- Cosine Recall on quora duplicates devself-reported0.918
- Cosine Ap on quora duplicates devself-reported0.718
- Dot Accuracy on quora duplicates devself-reported0.678
- Dot Accuracy Threshold on quora duplicates devself-reported35.865
- Dot F1 on quora duplicates devself-reported0.736