metadata
base_model: indobenchmark/indobert-base-p1
datasets: []
language: []
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
- pearson_manhattan
- spearman_manhattan
- pearson_euclidean
- spearman_euclidean
- pearson_dot
- spearman_dot
- pearson_max
- spearman_max
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:12800
- loss:ContrastiveTensionLoss
widget:
- source_sentence: >-
Makalah ini diterbitkan dalam format online hanya oleh Metro
International.
sentences:
- >-
Liga ini berkembang dari tahun 1200 hingga 1500, dan terus menjadi
semakin penting setelahnya.
- >-
Ini dirancang oleh orang lain selain WL Bottomley / William Lawrence
Bottomley.
- >-
Lahan tersebut sekarang menjadi Cagar Alam Bentley Priory, sebuah Situs
Kepentingan Ilmiah Khusus.
- source_sentence: >-
Pengadilan menentang keputusan tahun 2010 dan kasus ini dilanjutkan sesuai
dengan manfaatnya.
sentences:
- Gunung itu berada di Front Allegheny.
- >-
Stasiun St Albans Abbey adalah stasiun dalam perjalanan jalur ganda dari
stasiun Watford Junction.
- >-
Pada tahun 2011, keluarga Penner tidak lagi menyebut rumah Habitatnya,
rumah.
- source_sentence: Aku tidak jahat dalam hal ini.
sentences:
- >-
Awalnya disetujui untuk onchocerciasis dan strongyloidiasis, Ivermectin
sekarang disetujui oleh FDA untuk pedikulosis.
- Lagu ini mencapai ARIA Singles Chart Top 100.
- >-
Bebaskan diri Anda dari permusuhan dan kemarahan untuk menunjukkan rasa
hormat terhadap tubuh dan kehidupan Anda.
- source_sentence: Waktu pengiriman sangat cepat.
sentences:
- Dia kemudian bermain untuk South West Ham.
- >-
Qatar, bagaimanapun, tidak diminta untuk mengibarkan bendera Trucial
yang ditentukan.
- Sepasang pintu ini juga meredam suara dari luar.
- source_sentence: >-
Dengan demikian, seorang model penutur harus mengolah representasi warna
dalam konteks dan menghasilkan ujaran yang dapat membedakan warna sasaran
dengan ujaran lainnya.
sentences:
- Dia bukan bagian dari American Institute of Architects.
- >-
Pada tahun 1975 VTL dibeli oleh Greyhound Lines, menjadi anak
perusahaan.
- Pada tanggal 24 April 2009, Forum Terbuka IBIS menyetujui versi 2.0.
model-index:
- name: SentenceTransformer based on indobenchmark/indobert-base-p1
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: str dev
type: str-dev
metrics:
- type: pearson_cosine
value: 0.47668991144701395
name: Pearson Cosine
- type: spearman_cosine
value: 0.48495339068233534
name: Spearman Cosine
- type: pearson_manhattan
value: 0.5041035764250676
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.49270037559673846
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.5059182139447496
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.4915516775931335
name: Spearman Euclidean
- type: pearson_dot
value: 0.2991963739133043
name: Pearson Dot
- type: spearman_dot
value: 0.2630042391245101
name: Spearman Dot
- type: pearson_max
value: 0.5059182139447496
name: Pearson Max
- type: spearman_max
value: 0.49270037559673846
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: str test
type: str-test
metrics:
- type: pearson_cosine
value: 0.47374249981827143
name: Pearson Cosine
- type: spearman_cosine
value: 0.5083479438750005
name: Spearman Cosine
- type: pearson_manhattan
value: 0.49828227586252527
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.4962152495999787
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.5006486050380166
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.49701891829828837
name: Spearman Euclidean
- type: pearson_dot
value: 0.2573207350736585
name: Pearson Dot
- type: spearman_dot
value: 0.24350607759185028
name: Spearman Dot
- type: pearson_max
value: 0.5006486050380166
name: Pearson Max
- type: spearman_max
value: 0.5083479438750005
name: Spearman Max
SentenceTransformer based on indobenchmark/indobert-base-p1
This is a sentence-transformers model finetuned from indobenchmark/indobert-base-p1. 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: indobenchmark/indobert-base-p1
- Maximum Sequence Length: 32 tokens
- Output Dimensionality: 768 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': 32, 'do_lower_case': False}) with Transformer model: BertModel
(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("damand2061/negasibert-ct")
# Run inference
sentences = [
'Dengan demikian, seorang model penutur harus mengolah representasi warna dalam konteks dan menghasilkan ujaran yang dapat membedakan warna sasaran dengan ujaran lainnya.',
'Pada tahun 1975 VTL dibeli oleh Greyhound Lines, menjadi anak perusahaan.',
'Pada tanggal 24 April 2009, Forum Terbuka IBIS menyetujui versi 2.0.',
]
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
Semantic Similarity
- Dataset:
str-dev
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | 0.4767 |
spearman_cosine | 0.485 |
pearson_manhattan | 0.5041 |
spearman_manhattan | 0.4927 |
pearson_euclidean | 0.5059 |
spearman_euclidean | 0.4916 |
pearson_dot | 0.2992 |
spearman_dot | 0.263 |
pearson_max | 0.5059 |
spearman_max | 0.4927 |
Semantic Similarity
- Dataset:
str-test
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | 0.4737 |
spearman_cosine | 0.5083 |
pearson_manhattan | 0.4983 |
spearman_manhattan | 0.4962 |
pearson_euclidean | 0.5006 |
spearman_euclidean | 0.497 |
pearson_dot | 0.2573 |
spearman_dot | 0.2435 |
pearson_max | 0.5006 |
spearman_max | 0.5083 |
Training Details
Training Dataset
Unnamed Dataset
- Size: 12,800 training samples
- Columns:
sentence_0
,sentence_1
, andlabel
- Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label type string string int details - min: 5 tokens
- mean: 14.81 tokens
- max: 32 tokens
- min: 5 tokens
- mean: 14.92 tokens
- max: 32 tokens
- 0: ~87.50%
- 1: ~12.50%
- Samples:
sentence_0 sentence_1 label Warnanya tercermin pada corak dan lambang universitas kota tersebut.
Warnanya tercermin pada corak dan lambang universitas kota tersebut.
1
Pada awal tahun 2008, Ikerbasque menolak menugaskan Enrique Zuazua.
Oh, ayolah, itu adil.
0
Pada tahun 2006, sebuah studi diselesaikan tentang prospek jalur Scarborough.
Jurnal Pendidikan Modern didirikan olehnya.
0
- Loss:
ContrastiveTensionLoss
Training Hyperparameters
Non-Default Hyperparameters
per_device_train_batch_size
: 64per_device_eval_batch_size
: 64num_train_epochs
: 5multi_dataset_batch_sampler
: round_robin
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: noprediction_loss_only
: Trueper_device_train_batch_size
: 64per_device_eval_batch_size
: 64per_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
: 1num_train_epochs
: 5max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.0warmup_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
: 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
: batch_samplermulti_dataset_batch_sampler
: round_robin
Training Logs
Epoch | Step | Training Loss | str-dev_spearman_max | str-test_spearman_max |
---|---|---|---|---|
1.0 | 200 | - | 0.5009 | 0.5084 |
2.0 | 400 | - | 0.4926 | 0.5025 |
2.5 | 500 | 2328.8573 | - | - |
3.0 | 600 | - | 0.4909 | 0.5058 |
4.0 | 800 | - | 0.4909 | 0.5064 |
5.0 | 1000 | 0.5625 | 0.4927 | 0.5083 |
Framework Versions
- Python: 3.10.14
- Sentence Transformers: 3.0.1
- Transformers: 4.44.0
- PyTorch: 2.4.0
- 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",
}
ContrastiveTensionLoss
@inproceedings{carlsson2021semantic,
title={Semantic Re-tuning with Contrastive Tension},
author={Fredrik Carlsson and Amaru Cuba Gyllensten and Evangelia Gogoulou and Erik Ylip{"a}{"a} Hellqvist and Magnus Sahlgren},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=Ov_sMNau-PF}
}