esdm-finetune-1

ModernBERT Embed base Legal Matryoshka

This is a sentence-transformers model finetuned from nomic-ai/modernbert-embed-base on the json dataset. 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: nomic-ai/modernbert-embed-base <!-- at revision d556a88e332558790b210f7bdbe87da2fa94a8d8 -->
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json
• Language: en
• 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': 8192, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (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): Normalize()
)

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("meinantoyuriawan19/esdm-finetune-1")
# Run inference
sentences = [
    'Apa saja yang termasuk kegiatan usaha Minyak dan Gas Bumi menurut Pasal 5?',
    ' BAB III PENGUASAAN DAN PENGUSAHAAN Pasal 4 (1) Minyak dan Gas Bumi sebagai sumber daya alam strategis takterbarukan yang terkandung di dalam Wilayah Hukum Pertambangan Indonesia merupakan kekayaan nasional yang dikuasai oleh negara. (2) Penguasaan oleh negara sebagaimana dimaksud dalam ayat (1) diselenggarakan oleh Pemerin tah sebagai pemegang Kuasa Pertambangan. (3) Pemerintah sebagai pemegang Kuasa Pertambangan membentuk Badan Pelaksana sebagaimana dimaksud dalam Pasal 1 angka 23. Pasal 5 ... - - 8 - - - 8 - Pasal 5 Kegiatan usaha Minyak dan Gas Bumi terdiri atas: 1. Kegiatan Usaha Hulu yang mencakup: a. Eksplorasi; b. Eksploitasi. 2.',
    'i. peralatan pengaman;\nj. kesimpulan hasil Inspeksi Teknis;\nk. tanggal pelaksanaan Inspeksi Teknis dan\nPemeriksaan Keselamatan;\n1. masa berlaku; dan\nm. akurasi sistem alat ukur serah terima, apabila ada.\n(4) Dalam hal berdasarkan kesimpulan hasil Inspeksi Teknis\nsebagaimana dimaksud pada ayat (3) huruf j dinyatakan\ntidak layak, Kepala Teknik wajib menyusun rencana\ntindak lanjut.\nPasal 19\n(1) Kepala Teknik menyampaikan permohonan pelaksanaan\nPemeriksaan Keselamatan sebagaimana dimaksud dalam\nPasal 12 ayat (1) huruf b kepada Kepala Inspeksi.\n(2) Permohonan sebagaimana dimaksud pada ayat (1)\ndisampaikan secara tertulis disertai dengan melampirkan:\na. usulan rencana inspeksi [inspection and test plan)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.4648, -0.1300],
#         [ 0.4648,  1.0000, -0.0550],
#         [-0.1300, -0.0550,  1.0000]])

<!-- ### 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

Information Retrieval

• Dataset: dim_768
• Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 768
  }
  

Information Retrieval

• Dataset: dim_512
• Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 512
  }
  

Information Retrieval

• Dataset: dim_256
• Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 256
  }
  

Information Retrieval

• Dataset: dim_128
• Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 128
  }
  

Information Retrieval

• Dataset: dim_64
• Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 64
  }
  

<!-- ## 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

json

• Dataset: json
• Size: 4,924 training samples
• Columns: <code>positive</code> and <code>anchor</code>
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	<ul><li>min: 12 tokens</li><li>mean: 27.48 tokens</li><li>max: 58 tokens</li></ul>	<ul><li>min: 25 tokens</li><li>mean: 224.29 tokens</li><li>max: 317 tokens</li></ul>

• Samples:

  positive	anchor
  <code>Apa yang dimaksud dengan pertimbangan yang menyangkut peluang pasar?</code>	<code> Ayat (3) Cukup jelas Ayat (4) Cukup jelas Pasal47 Cukup jelas Pasal 48 Cukup jelas Pasal 49 Cukup jelas Pasal 50 Cukup jelas Ayat (2) Yang dimaksud dengan pertimbangan yang menyangkut cadangan dalam ketentuan ayat ini rneliputi, besar, spesifikasi Gas Rumi dan lokasi. Sedangkan yang dirnaksud dengan pertimbangan yang menyangkut peluang pasar dalam ketentuan ayat ini adalah meliputi kebutuhan pasar (volume dan spesifikasi Gas Bumi) dan lokasi pasar. r( Pasal 5 1 Cukup jelas Pasal 52 / Cukup jelas Pasal 53 Cukup jelas Pasal 54 ...</code>
  <code>Apakah kontraktor diperbolehkan memperoleh keuntungan dari penggunaan fasilitas?</code>	<code> (2) Dalarn ha1 fasilitas sebagairnana dirnaksud dalarn ayat (I) digunakan bersarna dengan pihak lain dengan rnernungut biaya atau sewa sehingga rnernperoleh keuntungan dan/atau laba, Kontraktor wajib rnernbentuk Badan Usaha Kegiatan Usaha Hilir yang terpisah dan wajib rnendapatkan Izin Usaha. BAB V e PEMANFAATAN MINYAK DAN GAS BUM1 UNTUK MEMENUHI KEBUTUHAN DALAM NEGERI Pasal 46 (I) Kontraktor bertanggungjawab untuk ikut serta rnernenuhi kebutuhan Minyak Burni dan/atau Gas Burni untuk keperluan dalarn negeri. (2) Bagian Kontraktor dalarn rnemenuhi keperluan dalarn negeri sebagairnana dirnaksud dalarn ayat (I), ditetapkan berdasarkan sistern prorata hasil produksi Minyak Bumi dan/atau Gas Bumi. (3) Besaran ...</code>
  <code>Dalam kondisi apa Gas Bumi diperoleh?</code>	<code>hidrokarbon yang dalam kondisi tekanan dan temperatur atmosfer berupa fasa cair atau padat, termasuk aspal, lilin mineral atau ozokerit, dan bitumen yang diperoleh dari proses penambangan, tetapi tidak termasuk batubara atau endapan hidrokarbon lain yang berbentuk padat yang diperoleh dari kegiatan yang tidak berkaitan dengan kegiatan usaha Minyak dan Gas Bumi. - 4 - 2. Gas Bumi adalah hasil proses alami berupa hidrokarbon yang dalam kondisi tekanan dan temperatur atmosfer berupa fasa gas yang diperoleh dari proses penambangan Minyak dan Gas Bumi. 3. Minyak dan Gas Bumi adalah Minyak Bumi dan Gas Bumi.</code>

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

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_eval_batch_size: 16
• gradient_accumulation_steps: 4
• learning_rate: 2e-05
• num_train_epochs: 4
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• fp16: True
• tf32: True
• load_best_model_at_end: True
• batch_sampler: no_duplicates

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 4
• 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: 4
• max_steps: -1
• lr_scheduler_type: cosine
• 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: True
• 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_fused
• 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: None
• 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: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.18
• Sentence Transformers: 5.1.0
• Transformers: 4.55.4
• PyTorch: 2.8.0+cu128
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.21.4

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

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.* -->