ModernBERT Embed Base Legal Fine-tuned

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: nomic-ai/modernbert-embed-base
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • legal-rag-positives-synthetic
• 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)

Evaluation

Metrics

Information Retrieval

• Dataset: ir_dim_768
• Evaluated with InformationRetrievalEvaluator with these parameters:
  json

  1{ 2 "truncate_dim": 768 3}

Information Retrieval

• Dataset: ir_dim_512
• Evaluated with InformationRetrievalEvaluator with these parameters:
  json

  1{ 2 "truncate_dim": 512 3}

Information Retrieval

• Dataset: ir_dim_256
• Evaluated with InformationRetrievalEvaluator with these parameters:
  json

  1{ 2 "truncate_dim": 256 3}

Information Retrieval

• Dataset: ir_dim_128
• Evaluated with InformationRetrievalEvaluator with these parameters:
  json

  1{ 2 "truncate_dim": 128 3}

Information Retrieval

• Dataset: ir_dim_64
• Evaluated with InformationRetrievalEvaluator with these parameters:
  json

  1{ 2 "truncate_dim": 64 3}

Training Details

Training Dataset

legal-rag-positives-synthetic

• Dataset: legal-rag-positives-synthetic at f11534a
• Size: 11,644 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 7 tokens mean: 57.45 tokens max: 160 tokens	min: 8 tokens mean: 57.77 tokens max: 157 tokens

• Samples:

  anchor	positive
  What kinds of issues are mentioned in connection with wrongdoing?	mismanagement, waste and wrongdoing – and that it has demonstrated more than a [object Object]credible basis from which the Court can infer possible mismanagement. It claims [object Object]DR’s management failed to follow corporate governance mechanics and made [object Object]critical business decisions without consulting with the Board or stockholders; [object Object]failed to act with due diligence related to undertaking an ICO and discontinuing
  Project, 504 F.2d at 248 n.15). [object Object]More, the requirement of “substantial” authority suggests that the entity should be at the [object Object]“center of gravity in the exercise of administrative power.” Id. at 882 (quoting Lombardo v. [object Object]Handler, 397 F. Supp. 792, 796 (D.D.C. 1975), aff’d, 546 F.2d 1043 (D.C. Cir. 1976)). On this	What page reference is given for the Lombardo v. Handler case in the aforementioned citation?
  Where can more detailed information regarding redactions be found?	parties specifically with respect to the FOIA request at issue in Count Eighteen of No. 11-444. This is likely [object Object]because the CIA has previously instituted a categorical policy of indicating the basis for redactions at a document [object Object]level, rather than a redaction level, as discussed above. See supra Part III.C.2. In light of the Court’s holding that

• Loss: MatryoshkaLoss with these parameters:
  json

  1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 768, 5 512, 6 256, 7 128, 8 64 9 ], 10 "matryoshka_weights": [ 11 1, 12 1, 13 1, 14 1, 15 1 16 ], 17 "n_dims_per_step": -1 18}

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• num_train_epochs: 4
• learning_rate: 2e-05
• lr_scheduler_type: cosine
• warmup_steps: 0.1
• optim: adamw_torch_fused
• gradient_accumulation_steps: 16
• bf16: True
• tf32: True
• eval_strategy: epoch
• per_device_eval_batch_size: 16
• load_best_model_at_end: True

All Hyperparameters

Training Logs

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.11
• Sentence Transformers: 5.3.0
• Transformers: 5.3.0
• PyTorch: 2.5.1+cu121
• Accelerate: 1.13.0
• Datasets: 4.8.2
• Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

MatryoshkaLoss

MultipleNegativesRankingLoss