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. 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
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("philipp-zettl/MiniLM-amazon_massive_intent-similarity-small")
# Run inference
sentences = [
'Order a new winter coat',
'product query',
'product query',
]
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
Semantic Similarity
- Dataset:
MiniLM-dev
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | 0.6556 |
spearman_cosine | 0.6919 |
pearson_manhattan | 0.2992 |
spearman_manhattan | 0.283 |
pearson_euclidean | 0.3154 |
spearman_euclidean | 0.304 |
pearson_dot | 0.6662 |
spearman_dot | 0.7058 |
pearson_max | 0.6662 |
spearman_max | 0.7058 |
Semantic Similarity
- Dataset:
MiniLM-test
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | 0.4483 |
spearman_cosine | 0.4496 |
pearson_manhattan | 0.2897 |
spearman_manhattan | 0.2629 |
pearson_euclidean | 0.2773 |
spearman_euclidean | 0.2578 |
pearson_dot | 0.4609 |
spearman_dot | 0.4667 |
pearson_max | 0.4609 |
spearman_max | 0.4667 |
Training Details
Training Dataset
Unnamed Dataset
- Size: 508 training samples
- Columns:
sentence1
,sentence2
, andscore
- Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score type string string float details - min: 7 tokens
- mean: 11.19 tokens
- max: 19 tokens
- min: 5 tokens
- mean: 5.35 tokens
- max: 6 tokens
- min: 0.0
- mean: 0.49
- max: 1.0
- Samples:
sentence1 sentence2 score أريد أن أعرف أسعار الحقائب الجلدية
product query
1.0
Sende mir die neuesten Modetrends
product query
1.0
¿Cuánto tarda en llegar un envío internacional?
product query
0.0
- Loss:
CoSENTLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "pairwise_cos_sim" }
Evaluation Dataset
Unnamed Dataset
- Size: 64 evaluation samples
- Columns:
sentence1
,sentence2
, andscore
- Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score type string string float details - min: 7 tokens
- mean: 10.8 tokens
- max: 16 tokens
- min: 5 tokens
- mean: 5.3 tokens
- max: 6 tokens
- min: 0.0
- mean: 0.62
- max: 1.0
- Samples:
sentence1 sentence2 score Order a new pair of running shoes
faq query
0.0
Где ближайшая заправка?
general query
1.0
哪里有提供优惠的酒店?
product query
1.0
- Loss:
CoSENTLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "pairwise_cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 32per_device_eval_batch_size
: 32learning_rate
: 2e-05warmup_ratio
: 0.1fp16
: Truebatch_sampler
: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 32per_device_eval_batch_size
: 32per_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
: 3max_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
: Truefp16_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
: Falseignore_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
: Falsebatch_sampler
: no_duplicatesmulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | Training Loss | loss | MiniLM-dev_spearman_cosine | MiniLM-test_spearman_cosine |
---|---|---|---|---|---|
0.625 | 10 | 0.8435 | 0.5815 | 0.3774 | - |
1.25 | 20 | 1.5026 | 0.4236 | 0.5731 | - |
1.875 | 30 | 0.8919 | 0.2179 | 0.6796 | - |
2.5 | 40 | 0.2909 | 0.1763 | 0.6919 | - |
3.0 | 48 | - | - | - | 0.4496 |
Framework Versions
- Python: 3.10.14
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.3.1+cu121
- Accelerate: 0.33.0
- 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",
}
CoSENTLoss
@online{kexuefm-8847,
title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
author={Su Jianlin},
year={2022},
month={Jan},
url={https://kexue.fm/archives/8847},
}
- Downloads last month
- 4
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 philipp-zettl/MiniLM-amazon_massive_intent-similarity-small
Finetuned
this model
Evaluation results
- Pearson Cosine on MiniLM devself-reported0.656
- Spearman Cosine on MiniLM devself-reported0.692
- Pearson Manhattan on MiniLM devself-reported0.299
- Spearman Manhattan on MiniLM devself-reported0.283
- Pearson Euclidean on MiniLM devself-reported0.315
- Spearman Euclidean on MiniLM devself-reported0.304
- Pearson Dot on MiniLM devself-reported0.666
- Spearman Dot on MiniLM devself-reported0.706
- Pearson Max on MiniLM devself-reported0.666
- Spearman Max on MiniLM devself-reported0.706