exp2_ep3_bs128_lr2e5

SentenceTransformer based on LazarusNLP/congen-indobert-lite-base

This is a sentence-transformers model finetuned from LazarusNLP/congen-indobert-lite-base. 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: LazarusNLP/congen-indobert-lite-base <!-- at revision e1f1ad81d3c620b317077edfaa5d1ce1b07b464b -->
• Maximum Sequence Length: 32 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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: AlbertModel 
  (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})
  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)

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("yosriku/exp2_ep3_bs128_lr2e5")
# Run inference
sentences = [
    '39641995 paraphrase Paraphrases Referensi',
    'persampahan. Direktorat Jenderal Cipta Karya. Jakarta. Anonim. 1995. Metode pengambilan dan pengukuran contoh timbulan dan komposisi sampah perkotaan (SNI 19-3964-1995). Badan Standar Nasional. Jakarta.',
    'Sampah orga nik yang akan diproses sebanyak 1.400,36 kg per hari. Kemudian diproses menjadi arang, sehingga didapatkan arang sampah organik sebanyak 205,91 kg per hari. Berdasarkan perhitungan didapatkan potensi energi listrik yang dihasilkan adalah 1.392,38 kWh',
]
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]

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Triplet

• Datasets: retrieval-validation and test
• Evaluated with <code>TripletEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

Unnamed Dataset

• Size: 6,399 training samples
• Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	<ul><li>min: 3 tokens</li><li>mean: 9.36 tokens</li><li>max: 31 tokens</li></ul>	<ul><li>min: 11 tokens</li><li>mean: 30.07 tokens</li><li>max: 32 tokens</li></ul>	<ul><li>min: 5 tokens</li><li>mean: 26.95 tokens</li><li>max: 32 tokens</li></ul>

• Samples:

  anchor	positive	negative
  <code>Bagaimana status UU 23 Tahun 1997?</code>	<code>yang baru berdasarkan Undang-Undang ini. Pasal - 70 - Pasal 125 Pada saat Undang-Undang ini mulai berlaku, Undang-Undang Nomor 23 Tahun 1997 tentang Pengelolaan Lingkungan Hidup (Lembaran Negara Republik Indonesia Tahun 1997 Nomor 68, Tambahan Lembaran Negara Republik Indonesia Nomor 3699) dicabut dan dinyatakan tidak berlaku.</code>	<code>Jumlah wisatawan pengunjung Pantai Parangtrit is yang mencapai 9.870 orang setiap hari adalah potensi yang besar untuk menghasilkan sampah. Sedangkan, setiap orang dalam 1 hari berpotensi menghasilkan sampah rata -rata 0,8 kg 3.</code>
  <code>kedua Bagian Kedua Masuk ke Bagian Pertama Bagian kedua kata</code>	<code>(3) Gugatan melalui pengadilan hanya dapat ditempuh apabila upaya penyelesaian sengketa di luar pengadilan yang dipilih dinyatakan tidak berhasil oleh salah satu atau para pihak yang bersengketa. Bagian Kedua - 53 - Bagian Kedua Penyelesaian Sengketa Lingkungan Hidup di Luar Pengadilan Pasal 85 (1) Penyelesaian sengketa lingkungan hidup di luar pengadilan dilakukan untuk mencapai kesepakatan mengenai: a. bentuk dan besarnya ganti rugi; b.</code>	<code>31. Masyarakat hukum adat adalah kelompok masyarakat yang secara turun temurun bermukim di wilayah geografis tertentu karena adanya ikatan pada asal usul leluhur, adanya hubungan yang kuat dengan lingkungan hidup, serta adanya sistem nilai yang menentukan pranata ekonomi, politik, sosial, dan hukum</code>
  <code>s Mengapa jumlah sarana yang banyak bisa percuma?</code>	<code>oleh penduduk setempat. Namun banyak atau tidaknya sarana dan prasarana pengelolaan sampah, jika tidak diikuti dengan kualitas yang baik dari sarana dan prasarana tersebut maka jumlah yang banyak tersebut akan percuma. Fungsi dari</code>	<code>udara rata-rata adalah 300C. Desa ini berjarak 4 km dari pusat Kecamatan Kretek dan 13 km dari ibukota kabupaten Bantul.</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 1,829 evaluation samples
• Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	<ul><li>min: 3 tokens</li><li>mean: 9.15 tokens</li><li>max: 27 tokens</li></ul>	<ul><li>min: 11 tokens</li><li>mean: 30.03 tokens</li><li>max: 32 tokens</li></ul>	<ul><li>min: 6 tokens</li><li>mean: 27.14 tokens</li><li>max: 32 tokens</li></ul>

• Samples:

  anchor	positive	negative
  <code>se Penjelasan Pasal 57 Ayat 4 Huruf b c</code>	<code>konsekuensi yang timbul akibat perubahan iklim dapat diatasi. Huruf b Cukup jelas. Huruf c Cukup jelas.</code>	<code>Jumlah pengunjung di Kawasan Wisata Pantai Parangtritis mencapai 9.870 orang/hari 1. Sedangkan, sampah yang dihasilkan oleh para wisatawan rata -rata 1,5 – 2,0 ton per hari pada hari biasa, dan bisa mencapai 20 ton sampah per hari pada saat liburan seperli libur lebaran 2.</code>
  <code>Apa kewajiban usaha yang tidak wajib UKLUPL?</code>	<code>(2) Gubernur atau bupati/walikota menetapkan jenis usaha dan/atau kegiatan yang wajib dilengkapi dengan UKL-UPL. Pasal 35 (1) Usaha dan/atau kegiatan yang tidak wajib dilengkapi UKL-UPL sebagaimana dimaksud dalam Pasal 34 ayat (2) wajib membuat surat pernyataan kesanggupan pengelolaan dan pemantauan lingkungan hidup.</code>	<code>Abstra ct Parangtritis Beach is a tourist attraction that is visited by many tourists. The number of tourists visiting during the 2018 holiday reached 9,870 people in one day.</code>
  <code>Siapa Tim Pelaksana?</code>	<code>Pasa l 8... Pasal 7 (1) Untuk membantu pelaksanaan tugas Tim Koordinasi Nasiona l, dibent uk Tim Pelaksana. (2) Susunan keanggotaan, tugas, dan tata kerja Tim Pelaksa na sebagaimana d imaksud pada ayat (1), ditetap kan oleh Menteri Koordinator Bidang Kemar itiman selaku Ketua Tim Koordinasi Nasional atas usulan Ketua Harian.</code>	<code>Bagaimana jika B3 telah kedaluwarsa?</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• learning_rate: 2e-05
• warmup_ratio: 0.1
• fp16: True
• load_best_model_at_end: True
• push_to_hub: True
• hub_model_id: yosriku/exp2_ep3_bs128_lr2e5
• hub_private_repo: True

All Hyperparameters

<details><summary>Click to expand</summary>

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 2e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 3
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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: True
• 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: True
• 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: True
• resume_from_checkpoint: None
• hub_model_id: yosriku/exp2_ep3_bs128_lr2e5
• hub_strategy: every_save
• hub_private_repo: True
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• 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
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

</details>

Training Logs

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 4.1.0
• Transformers: 4.53.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.9.0
• Datasets: 4.1.1
• Tokenizers: 0.21.2

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}
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->