base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 language:
- hu library_name: sentence-transformers license: apache-2.0 metrics:
- cosine_accuracy
- dot_accuracy
- manhattan_accuracy
- euclidean_accuracy
- max_accuracy pipeline_tag: sentence-similarity tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:857856
- loss:MultipleNegativesRankingLoss widget:
- source_sentence: Emberek várnak a lámpánál kerékpárral.
sentences:
- Az emberek piros lámpánál haladnak.
- Az emberek a kerékpárjukon vannak.
- Egy fekete kutya úszik a vízben egy teniszlabdával a szájában
- source_sentence: A kutya a vízben van.
sentences:
- Két férfi takarítja a havat a tetőről, az egyik egy emelőben ül, a másik pedig a tetőn.
- A macska a vízben van, és dühös.
- Egy kutya van a vízben, a szájában egy faág.
- source_sentence: A nő feketét visel.
sentences:
- Egy barna kutya fröcsköl, ahogy úszik a vízben.
- Egy tetoválással rendelkező nő, aki fekete tank tetején néz a földre.
- 'Egy kékbe öltözött nő intenzív arckifejezéssel üti a teniszlabdát. A képen:'
- source_sentence: Az emberek alszanak.
sentences:
- Három ember beszélget egy városi utcán.
- A nő fehéret visel.
- Egy apa és a fia ölelgeti alvás közben.
- source_sentence: Az emberek alszanak.
sentences:
- Egy feketébe öltözött nő cigarettát és bevásárlótáskát tart a kezében, miközben egy idősebb nő átmegy az utcán.
- Egy csoport ember ül egy nyitott, térszerű területen, mögötte nagy bokrok és egy sor viktoriánus stílusú épület, melyek közül sokat a kép jobb oldalán lévő erős elmosódás tesz kivehetetlenné.
- Egy apa és a fia ölelgeti alvás közben. model-index:
- name: paraphrase-multilingual-MiniLM-L12-hu-v1
results:
- task:
type: triplet
name: Triplet
dataset:
name: all nli dev
type: all-nli-dev
metrics:
- type: cosine_accuracy value: 0.992 name: Cosine Accuracy
- type: dot_accuracy value: 0.0108 name: Dot Accuracy
- type: manhattan_accuracy value: 0.9908 name: Manhattan Accuracy
- type: euclidean_accuracy value: 0.9908 name: Euclidean Accuracy
- type: max_accuracy value: 0.992 name: Max Accuracy
- task:
type: triplet
name: Triplet
dataset:
name: all nli test
type: all-nli-test
metrics:
- type: cosine_accuracy value: 0.9913636363636363 name: Cosine Accuracy
- type: dot_accuracy value: 0.013939393939393939 name: Dot Accuracy
- type: manhattan_accuracy value: 0.990909090909091 name: Manhattan Accuracy
- type: euclidean_accuracy value: 0.9910606060606061 name: Euclidean Accuracy
- type: max_accuracy value: 0.9913636363636363 name: Max Accuracy
- task:
type: triplet
name: Triplet
dataset:
name: all nli dev
type: all-nli-dev
metrics:
paraphrase-multilingual-MiniLM-L12-v2
This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 on the train 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:
- train
- Language: hu
- License: apache-2.0
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("karsar/paraphrase-multilingual-MiniLM-L12-hu_v1")
# Run inference
sentences = [
'Az emberek alszanak.',
'Egy apa és a fia ölelgeti alvás közben.',
'Egy csoport ember ül egy nyitott, térszerű területen, mögötte nagy bokrok és egy sor viktoriánus stílusú épület, melyek közül sokat a kép jobb oldalán lévő erős elmosódás tesz kivehetetlenné.',
]
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
Triplet
- Dataset:
all-nli-dev
- Evaluated with
TripletEvaluator
Metric | Value |
---|---|
cosine_accuracy | 0.992 |
dot_accuracy | 0.0108 |
manhattan_accuracy | 0.9908 |
euclidean_accuracy | 0.9908 |
max_accuracy | 0.992 |
Triplet
- Dataset:
all-nli-test
- Evaluated with
TripletEvaluator
Metric | Value |
---|---|
cosine_accuracy | 0.9914 |
dot_accuracy | 0.0139 |
manhattan_accuracy | 0.9909 |
euclidean_accuracy | 0.9911 |
max_accuracy | 0.9914 |
Training Details
Training Dataset
train
- Dataset: train
- Size: 857,856 training samples
- Columns:
anchor
,positive
, andnegative
- Approximate statistics based on the first 1000 samples:
anchor positive negative type string string string details - min: 7 tokens
- mean: 11.73 tokens
- max: 56 tokens
- min: 6 tokens
- mean: 15.24 tokens
- max: 47 tokens
- min: 7 tokens
- mean: 16.07 tokens
- max: 53 tokens
- Samples:
anchor positive negative Egy lóháton ülő ember átugrik egy lerombolt repülőgép felett.
Egy ember a szabadban, lóháton.
Egy ember egy étteremben van, és omlettet rendel.
Gyerekek mosolyogva és integetett a kamera
Gyermekek vannak jelen
A gyerekek homlokot rántanak
Egy fiú ugrál a gördeszkát a közepén egy piros híd.
A fiú gördeszkás trükköt csinál.
A fiú korcsolyázik a járdán.
- Loss:
MultipleNegativesRankingLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Evaluation Dataset
train
- Dataset: train
- Size: 5,000 evaluation samples
- Columns:
anchor
,positive
, andnegative
- Approximate statistics based on the first 1000 samples:
anchor positive negative type string string string details - min: 7 tokens
- mean: 11.73 tokens
- max: 56 tokens
- min: 6 tokens
- mean: 15.24 tokens
- max: 47 tokens
- min: 7 tokens
- mean: 16.07 tokens
- max: 53 tokens
- Samples:
anchor positive negative Egy lóháton ülő ember átugrik egy lerombolt repülőgép felett.
Egy ember a szabadban, lóháton.
Egy ember egy étteremben van, és omlettet rendel.
Gyerekek mosolyogva és integetett a kamera
Gyermekek vannak jelen
A gyerekek homlokot rántanak
Egy fiú ugrál a gördeszkát a közepén egy piros híd.
A fiú gördeszkás trükköt csinál.
A fiú korcsolyázik a járdán.
- Loss:
MultipleNegativesRankingLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 128per_device_eval_batch_size
: 128num_train_epochs
: 1warmup_ratio
: 0.1bf16
: Truebatch_sampler
: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 128per_device_eval_batch_size
: 128per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonetorch_empty_cache_steps
: Nonelearning_rate
: 5e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1.0num_train_epochs
: 1max_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
: Truefp16
: 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
: 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
: Falseeval_on_start
: Falseeval_use_gather_object
: Falsebatch_sampler
: no_duplicatesmulti_dataset_batch_sampler
: proportional
Training Logs
Epoch | Step | Training Loss | train loss | all-nli-dev_max_accuracy | all-nli-test_max_accuracy |
---|---|---|---|---|---|
0 | 0 | - | - | 0.7574 | - |
0.0149 | 100 | 2.5002 | - | - | - |
0.0298 | 200 | 1.9984 | - | - | - |
0.0448 | 300 | 1.8094 | - | - | - |
0.0597 | 400 | 1.6704 | - | - | - |
0.0746 | 500 | 1.5518 | - | - | - |
0.0895 | 600 | 1.449 | - | - | - |
0.1044 | 700 | 1.5998 | - | - | - |
0.1194 | 800 | 1.5725 | - | - | - |
0.1343 | 900 | 1.5341 | - | - | - |
0.1492 | 1000 | 1.3423 | - | - | - |
0.1641 | 1100 | 1.2485 | - | - | - |
0.1791 | 1200 | 1.1527 | - | - | - |
0.1940 | 1300 | 1.1672 | - | - | - |
0.2089 | 1400 | 1.2426 | - | - | - |
0.2238 | 1500 | 1.0948 | - | - | - |
0.2387 | 1600 | 1.0069 | - | - | - |
0.2537 | 1700 | 0.976 | - | - | - |
0.2686 | 1800 | 0.897 | - | - | - |
0.2835 | 1900 | 0.7825 | - | - | - |
0.2984 | 2000 | 0.9421 | 0.1899 | 0.9568 | - |
0.3133 | 2100 | 0.8651 | - | - | - |
0.3283 | 2200 | 0.8184 | - | - | - |
0.3432 | 2300 | 0.699 | - | - | - |
0.3581 | 2400 | 0.6704 | - | - | - |
0.3730 | 2500 | 0.6477 | - | - | - |
0.3879 | 2600 | 0.7077 | - | - | - |
0.4029 | 2700 | 0.7364 | - | - | - |
0.4178 | 2800 | 0.665 | - | - | - |
0.4327 | 2900 | 1.2512 | - | - | - |
0.4476 | 3000 | 1.3693 | - | - | - |
0.4625 | 3100 | 1.3959 | - | - | - |
0.4775 | 3200 | 1.4175 | - | - | - |
0.4924 | 3300 | 1.402 | - | - | - |
0.5073 | 3400 | 1.3832 | - | - | - |
0.5222 | 3500 | 1.3671 | - | - | - |
0.5372 | 3600 | 1.3666 | - | - | - |
0.5521 | 3700 | 1.3479 | - | - | - |
0.5670 | 3800 | 1.3272 | - | - | - |
0.5819 | 3900 | 1.3353 | - | - | - |
0.5968 | 4000 | 1.3177 | 0.0639 | 0.9902 | - |
0.6118 | 4100 | 1.3068 | - | - | - |
0.6267 | 4200 | 1.3054 | - | - | - |
0.6416 | 4300 | 1.3098 | - | - | - |
0.6565 | 4400 | 1.2839 | - | - | - |
0.6714 | 4500 | 1.2976 | - | - | - |
0.6864 | 4600 | 1.2669 | - | - | - |
0.7013 | 4700 | 1.208 | - | - | - |
0.7162 | 4800 | 1.194 | - | - | - |
0.7311 | 4900 | 1.1974 | - | - | - |
0.7460 | 5000 | 1.1834 | - | - | - |
0.7610 | 5100 | 1.1876 | - | - | - |
0.7759 | 5200 | 1.1743 | - | - | - |
0.7908 | 5300 | 1.1839 | - | - | - |
0.8057 | 5400 | 1.1778 | - | - | - |
0.8207 | 5500 | 1.1711 | - | - | - |
0.8356 | 5600 | 1.1809 | - | - | - |
0.8505 | 5700 | 1.1825 | - | - | - |
0.8654 | 5800 | 1.1795 | - | - | - |
0.8803 | 5900 | 1.1788 | - | - | - |
0.8953 | 6000 | 1.1819 | 0.0371 | 0.992 | - |
0.9102 | 6100 | 1.1741 | - | - | - |
0.9251 | 6200 | 1.1871 | - | - | - |
0.9400 | 6300 | 0.498 | - | - | - |
0.9549 | 6400 | 0.093 | - | - | - |
0.9699 | 6500 | 0.1597 | - | - | - |
0.9848 | 6600 | 0.2033 | - | - | - |
0.9997 | 6700 | 0.16 | - | - | - |
1.0 | 6702 | - | - | - | 0.9914 |
Framework Versions
- Python: 3.11.8
- Sentence Transformers: 3.1.1
- Transformers: 4.44.0
- PyTorch: 2.3.0.post101
- Accelerate: 0.33.0
- Datasets: 2.18.0
- Tokenizers: 0.19.0
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",
}
MultipleNegativesRankingLoss
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
- Downloads last month
- 146
Evaluation results
- main_score on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported77.865
- map_at_1 on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported67.333
- map_at_10 on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported74.404
- map_at_100 on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported74.802
- map_at_1000 on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported74.809
- map_at_20 on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported74.630
- map_at_3 on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported72.796
- map_at_5 on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported73.674
- mrr_at_1 on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported67.333
- mrr_at_10 on MTEB BelebeleRetrieval (hun_Latn-hun_Latn)test set self-reported74.404