cassador/indobert-t3

SentenceTransformer based on indobenchmark/indobert-base-p2

This is a sentence-transformers model finetuned from indobenchmark/indobert-base-p2. 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-p2
• Maximum Sequence Length: 200 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': 200, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'Waduk wadaslintang sebenarnya terbagi menjadi dua kabupaten yaitu kabupaten kebumen dan kabupaten wonosobo.',
    'Kabupaten kebumen dan kabupaten wonosobo bertentaggaan.',
    'Musim ini di ajang PBL 2020 Hendra melawan tim Pune 7 aces.',
]
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: sts-dev
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	-0.0516
spearman_cosine	-0.0593
pearson_manhattan	-0.0643
spearman_manhattan	-0.066
pearson_euclidean	-0.0637
spearman_euclidean	-0.0653
pearson_dot	-0.0279
spearman_dot	-0.026
pearson_max	-0.0279
spearman_max	-0.026

Training Details

Training Dataset

Unnamed Dataset

• Size: 10,330 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	int
  details	min: 11 tokens mean: 29.14 tokens max: 179 tokens	min: 5 tokens mean: 11.95 tokens max: 41 tokens	0: ~36.30% 1: ~32.90% 2: ~30.80%

• Samples:

  sentence_0	sentence_1	label
  Pada tahun 1436, pulau Timor mempunyai 12 kota bandar namun tidak disebutkan namanya.	Pulau Timor memiliki 10 kota bandar.	2
  Komoditas pertanian yang ada di desa ini antara lain: bunga potong, sayur mayur, waluh (lejet) terutama Paprika (Capsicum annuum L.). Komoditas ini menjadi sumber perekonomian utama di desa ini karena harganya yang lumayan dibandingkan sayuran lain.	Komoditas pertanian di desa ini lebih mahal dibandingkan sayuran lain.	1
  Setelah batas waktu pencalonan pada tanggal 15 Juli 2003, sembilan kota telah mencalonkan diri untuk mengadakan Olimpiade 2012. Kota-kota tersebut adalah Havana, Istanbul, Leipzig, London, Madrid, Moskwa, New York City, Paris, dan Rio de Janeiro. Pada 18 Mei 2004, Komite Olimpiade Internasional (IOC), sebagai hasil penilaian teknis, mengurangi jumlah kota kandidat menjadi lima: London, Madrid, Moskwa, New York, dan Paris.	Jumlah kota kandidat tuan rumah olimpide bertambah pada 18 Mei 2004.	2

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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
• num_train_epochs: 3
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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
• restore_callback_states_from_checkpoint: 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: False
• 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: False
• 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_eval_metrics: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss	sts-dev_spearman_max
0.0991	32	-	-0.0592
0.1981	64	-	-0.0425
0.2972	96	-	-0.0467
0.3963	128	-	-0.0428
0.4954	160	-	-0.0512
0.5944	192	-	-0.0473
0.6935	224	-	-0.0412
0.7926	256	-	-0.0435
0.8916	288	-	-0.0405
0.9907	320	-	-0.0425
1.0	323	-	-0.0420
1.0898	352	-	-0.0346
1.1889	384	-	-0.0333
1.2879	416	-	-0.0325
1.3870	448	-	-0.0312
1.4861	480	-	-0.0316
1.5480	500	0.077	-
1.5851	512	-	-0.0260

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.3.0+cu121
• Accelerate: 0.31.0
• Datasets: 2.19.2
• 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",
}

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}
}