all-MiniLM-L6-v2-ft-new

all_MiniLM_L6_v2 Finetuned on Data

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2 <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity

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

• 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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    "What is one action that may be included under 'mutual assistance' according to the text?",
    '1.Supervisory authorities shall provide each other with relevant information and mutual assistance in order to implement and apply this Regulation in a consistent manner, and shall put in place measures for effective cooperation with one another. Mutual assistance shall cover, in particular, information requests and supervisory measures, such as requests to carry out prior authorisations and consultations, inspections and investigations.\n2.Each supervisory authority shall take all appropriate measures required to reply to a request of another supervisory authority without undue delay and no later than one month after receiving the request. Such measures may include, in particular, the transmission of relevant information on the conduct of an investigation.\n3.Requests for assistance shall contain all the necessary information, including the purpose of and reasons for the request. Information exchanged shall be used only for the purpose for which it was requested.\n4.The requested supervisory authority shall not refuse to comply with the request unless: (a)  it is not competent for the subject-matter of the request or for the measures it is requested to execute; or (b)  compliance with the request would infringe this Regulation or Union or Member State law to which the supervisory authority receiving the request is subject.\n5.The requested supervisory authority shall inform the requesting supervisory authority of the results or, as the case may be, of the progress of the measures taken in order to respond to the request. The requested supervisory authority shall provide reasons for any refusal to comply with a request pursuant to paragraph 4\n6.Requested supervisory authorities shall, as a rule, supply the information requested by other supervisory authorities by electronic means, using a standardised format.\n7.Requested supervisory authorities shall not charge a fee for any action taken by them pursuant to a request for mutual assistance. Supervisory authorities may agree on rules to indemnify each other for specific expenditure arising from the provision of mutual assistance in exceptional circumstances.\n8.Where a supervisory authority does not provide the information referred to in paragraph 5 of this Article within one month of receiving the request of another supervisory authority, the requesting supervisory authority may adopt a provisional measure on the territory of its Member State in accordance with Article 55(1). In that case, the urgent need to act under Article 66(1) shall be presumed to be met and require an urgent binding decision from the Board pursuant to Article 66(2).\n9.The Commission may, by means of implementing acts, specify the format and procedures for mutual assistance referred to in this Article and the arrangements for the exchange of information by electronic means between supervisory authorities, and between supervisory authorities and the Board, in particular the standardised format referred to in paragraph 6 of this Article. Those implementing acts shall be adopted in accordance with the examination procedure referred to in Article 93(2).',
    "Any natural or legal person has the right to bring an action for annulment of decisions of the Board before the Court of Justice under the conditions provided for in Article 263 TFEU. As addressees of such decisions, the supervisory authorities concerned which wish to challenge them have to bring action within two months of being notified of them, in accordance with Article 263 TFEU. Where decisions of the Board are of direct and individual concern to a controller, processor or complainant, the latter may bring an action for annulment against those decisions within two months of their publication on the website of the Board, in accordance with Article 263 TFEU. Without prejudice to this right under Article 263 TFEU, each natural or legal person should have an effective judicial remedy before the competent national court against a decision of a supervisory authority which produces legal effects concerning that person. Such a decision concerns in particular the exercise of investigative, corrective and authorisation powers by the supervisory authority or the dismissal or rejection of complaints. However, the right to an effective judicial remedy does not encompass measures taken by supervisory authorities which are not legally binding, such as opinions issued by or advice provided by the supervisory authority. Proceedings against a supervisory authority should be brought before the courts of the Member State where the supervisory authority is established and should be conducted in accordance with that Member State's procedural law. Those courts should exercise full jurisdiction, which should include jurisdiction to examine all questions of fact and law relevant to the dispute before them. Where a complaint has been rejected or dismissed by a supervisory authority, the complainant may bring proceedings before the courts in the same Member State. In the context of judicial remedies relating to the application of this Regulation, national courts which consider a decision on the question necessary to enable them to give judgment, may, or in the case provided for in Article 267 TFEU, must, request the Court of Justice to give a preliminary ruling on the interpretation of Union law, including this Regulation. Furthermore, where a decision of a supervisory authority implementing a decision of the Board is challenged before a national court and the validity of the decision of the Board is at issue, that national court does not have the power to declare the Board's decision invalid but must refer the question of validity to the Court of Justice in accordance with Article 267 TFEU as interpreted by the Court of Justice, where it considers the decision invalid. However, a national court may not refer a question on the validity of the decision of the Board at the request of a natural or legal person which had the opportunity to bring an action for annulment of that decision, in particular if it was directly and individually concerned by that decision, but had not done so within the period laid down in Article 263 TFEU.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.4105, 0.0135],
#         [0.4105, 1.0000, 0.2998],
#         [0.0135, 0.2998, 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_384
• Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 384
  }
  

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

Unnamed Dataset

• Size: 1,627 training samples
• Columns: <code>anchor</code> and <code>positive</code>
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	<ul><li>min: 7 tokens</li><li>mean: 15.35 tokens</li><li>max: 34 tokens</li></ul>	<ul><li>min: 25 tokens</li><li>mean: 221.19 tokens</li><li>max: 256 tokens</li></ul>

• Samples:

  anchor	positive
  <code>What was the plaintiff asked to input first on the clone website?</code>	<code>Court (Civil/Criminal): Civil <br>Provisions: <br>Time of commission of the act: <br>Outcome (not guilty, guilty): <br>Reasoning: Partially accepts the lawsuit. <br>Facts: The plaintiff, who works as a lawyer, maintains a savings account with the defendant banking corporation under account number GR.............. Pursuant to a contract dated June 11, 2010, established in Thessaloniki between the defendant and the plaintiff, the plaintiff was granted access to the electronic banking system (e-banking) to conduct banking transactions remotely. On October 10, 2020, the plaintiff fell victim to electronic fraud through the "phishing" method, whereby an unknown perpetrator managed to extract and transfer €3,000.00 from the plaintiff’s account to another account of the same bank. Specifically, on that day at 6:51 a.m., the plaintiff received an email from the sender ".........", with the address ..........., informing him that his debit card had been suspended and that online p...</code>
  <code>At what time did the defendant send the first message to the plaintiff's mobile phone?</code>	<code>**Court (Civil/Criminal): Civil <br>Provisions: <br>Time of commission of the act: <br>Outcome (not guilty, guilty): Rejects the lawsuit. <br>Reasoning: <br>Facts: The plaintiff holds account number ....................... at the defendant bank. Following the application/contract dated January 9, 2019, the plaintiff became a subscriber to the alternative service networks provided by the defendant bank through online banking (.........................). In the aforementioned application, the plaintiff stated that her mobile phone (number .................) would be used by the defendant to send additional security codes for the approval of her transactions via .......................... It is noted that the plaintiff received subscriber code .................., thus enabling her to conduct transactions without her physical presence at the branches of the defendant bank, from fixed or mobile devices (computers, smartphones, tablets), by entering her username and password to access her personal acc...</code>
  <code>How should the lead supervisory authority and other supervisory authorities exchange information under this Article?</code>	<code>1.The lead supervisory authority shall cooperate with the other supervisory authorities concerned in accordance with this Article in an endeavour to reach consensus. The lead supervisory authority and the supervisory authorities concerned shall exchange all relevant information with each other.<br>2.The lead supervisory authority may request at any time other supervisory authorities concerned to provide mutual assistance pursuant to Article 61 and may conduct joint operations pursuant to Article 62, in particular for carrying out investigations or for monitoring the implementation of a measure concerning a controller or processor established in another Member State.<br>3.The lead supervisory authority shall, without delay, communicate the relevant information on the matter to the other supervisory authorities concerned. It shall without delay submit a draft decision to the other supervisory authorities concerned for their opinion and take due account of their views.<br>4.Where any of the other ...</code>

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

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          384,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• gradient_accumulation_steps: 2
• learning_rate: 2e-05
• num_train_epochs: 10
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• bf16: True
• tf32: True
• load_best_model_at_end: True
• optim: adamw_torch_fused
• 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: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 2
• 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: 10
• 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: True
• fp16: False
• 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}
• tp_size: 0
• 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
• 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
• 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

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

The model card is truncated. Read the rest on Hugging Face.