RishuD7/bge-base-en-v1.5-41-keys-phase-4-exp_v1

BGE base En v1.5 Phase 4

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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: BAAI/bge-base-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• 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': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("RishuD7/bge-base-en-v1.5-41-keys-phase-4-exp_v1")
# Run inference
sentences = [
    'Telstra International HK Limited Waiver of rights 15.8 A condition of this Agreement, or a right created by it, may only be waived by a party by giving notice and the failure to exercise or any delay In exercising a right or remedy provided by this Agreement or by law does not constitute a waiver of the right or remedy. 15.9 A waiver of a breach of this Agreement does not waive any other breach. Warranties 15.10 Each party warrants to the other that entering into and performing its obligations under this Agreement does not breach any of its contractual obligations to any other person. 15.11 You warrant that you have not relied on any representations or warranties by us other than those expressly provided in this Agreement. Assignment 15.12 Neither party may assign its rights or novate any rights or obligations under this Agreement without the prior consent of the other, which will not be unreasonably withheld. Agency 15.13 You may appoint a third party to act on your behalf in relation to this Agreement only if and for so long as we consent to you doing so. We may impose conditions on the giving of our consent and may withdraw our consent at any time. 15.14 If we consent to you appointing a third party to act on your behalf in relation to this Agreement, you agree to indemnify us against all direct and indirect loss, damage, liability, costs or expenses incurred by us (including to a fourth party) resulting from the appointment of the third party to act on your behalf including, but not limited to, any intentional or negligent act or omission by the third party, whether within or outside the scope of that appointment, such as a misuse of our confidential information.\n15.15 Nothing in clauses 1 5 . 1 3 and 1 5 . 1 4 is intended to waive any rights or obligations of us or you under this Agreement or to create any rights or impose any obligations on the third party appointed to act on your behalf under this Agreement. You remain liable for all of your obligations under this Agreement, including the payment of all charges for Services, and acknowledge that we may deal with you or with the third party (or both) in relation to matters arising under this Agreement. Force majeure 15.16 Neither party is liable for not performing an obligation in whole or in part, or for not performing it on time (except an obligation to pay money), because of a Force Majeure Event. 15.17 If a Force Majeure Event occurs, that party must: (a) give the other party notice of the event promptly and an estimate of the non-performance and delay; (b) take all reasonable steps to overcome the effects of the event (but this does not require the settlement of industrial disputes or other claims on unreasonable terms); and (c) resume compliance as soon as practicable after the event no longer affects that party. Compliance with laws 15.18 In carrying out its obligations under this Agreement, each party must comply with any relevant statutes, regulations and by-laws which apply in Hong Kong and the requirements of any government body with authority in Hong Kong. Third party rights 15.19 A person who is not a party to this Agreement has no rights under any applicable legislation to enforce any term or condition in this Agreement..\n                                                                              Telstra International HK Limited\n.\n                                                                                                                      I\n16 Definitions\n.\n   In this Agreement, unless otherwise indicated:\n.\n   Act - means the Telecommunications Act 1997 (Cth).\n.\n   Availability· means the number of minutes in a month during which a Global Service is not\n.\n   Unavailable.\n.\n   Business Day - means any day other than a Saturday, Sunday or recognised public holiday in Hong\n.\n   Kong.\n',
    'Assignment',
    'Counterparty Name',
]
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

Information Retrieval

• Dataset: dim_768
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.0063
cosine_accuracy@3	0.0222
cosine_accuracy@5	0.0338
cosine_accuracy@10	0.0622
cosine_precision@1	0.0063
cosine_precision@3	0.0074
cosine_precision@5	0.0068
cosine_precision@10	0.0062
cosine_recall@1	0.0063
cosine_recall@3	0.0222
cosine_recall@5	0.0338
cosine_recall@10	0.0622
cosine_ndcg@10	0.0289
cosine_mrr@10	0.0189
cosine_map@100	0.0327

Training Details

Training Dataset

Unnamed Dataset

• Size: 5,086 training samples
• Columns: positive and anchor
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	min: 123 tokens mean: 352.74 tokens max: 512 tokens	min: 3 tokens mean: 5.52 tokens max: 11 tokens

• Samples:

  positive	anchor
  In no event shall CBRE, Client, or their respective affiliates incur liability under this agreement or otherwise relating to the Services beyond the insurance proceeds available with respect to the particular matter under the Insurance Policies required to be carried by CBRE AND Client under Article 6 above including, if applicable, proceeds of self-insurance. Each party shall and shall cause its affiliates to look solely to such insurance proceeds (and any such proceeds paid through self-insurance) to satisfy its claims against the released parties and agrees that it shall have no right of recovery beyond such proceeds; provided, however, that if insurance proceeds under such policies are not paid because a party has failed to maintain such policies, comply with policy requirements or, in the case of self-insurance, unreasonably denied a claim, such party shall be liable for the amounts that otherwise would have been payable under such policies had such party maintained such policies,...	Absolute Maximum Amount of Liability
  4. Rent. 4.01 From and after the Commencement Date, Tenant shall pay Landlord, without any setoff or deduction, unless expressly set forth in this Lease, all Base Rent and Additional Rent due for the Term (collectively referred to as "Rent"). "Additional Rent" means all sums (exclusive of Base Rent) that Tenant is required to pay Landlord under this Lease. Tenant shall pay and be liable for all rental, sales and use taxes (but excluding income taxes), if any, imposed upon or measured by Rent. Base Rent and recurring monthly charges of Additional Rent shall be due and payable in advance on the first day of each calendar month without notice or demand, provided that the installment of Base Rent attributable to the first (1st) full calendar month of the Term following the Abatement Period shall be due concurrently with the execution of this Lease by Tenant. All other items of Rent shall be due and payable on or before thirty (30) days after billing by Landlord. Rent shall be made payable...	Late Payment Charges
  Term This Agreement shall come into force and shall last unlimited from such date. Either Party may however terminate this Agreement at any time by giving upon thirty (30) days' written notice to the other Party. The Receiving Party's obligations contained in this Agreement to keep confidential and restrict use of the Disclosing Party's Confidential Information shall sur- vive for a period of five (5) years from the date of its termination for any reason whatsoever. lX. Contractual penalty For the purposes of this Non-Disclosure Agreement, " Confidential Information" includes all technical and/or commercial and/or financial information in the field designated in section 1., which a contracting Party (hereinafter referred to as the "EQ€i1gPedy") makes, or has made, accessible to the other contracting Party (hereinafter referred to as the ".&eiyi!g Partv") in oral, written, tangible or other form (e.9. disk, data carrier) directly or indirectly, in- cluding but not limited to, drawings, ...	Termination for Convenience

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 16
• gradient_accumulation_steps: 16
• learning_rate: 2e-05
• num_train_epochs: 30
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• tf32: False
• load_best_model_at_end: True
• optim: adamw_torch_fused
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 16
• eval_accumulation_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: 30
• 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: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: False
• 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: 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
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_768_cosine_ndcg@10
1.0063	10	2.1725	-
2.0126	20	0.3731	-
3.0189	30	0.0406	-
4.0252	40	0.0	-
4.8302	48	-	0.0230
1.0063	10	1.6101	-
2.0126	20	0.055	-
3.0189	30	0.0016	-
4.0252	40	0.0	-
4.8302	48	-	0.0242
1.1761	50	0.2904	-
2.1824	60	0.8168	-
3.1887	70	0.0161	-
4.1950	80	0.004	-
5.2013	90	0.0	-
5.8050	96	-	0.0280
2.3522	100	0.4037	-
3.3585	110	0.3704	-
4.3648	120	0.0017	-
5.3711	130	0.0003	-
6.3774	140	0.0	-
6.7799	144	-	0.0293
3.5283	150	0.4189	-
4.5346	160	0.1746	-
5.5409	170	0.0004	-
6.5472	180	0.0	-
7.5535	190	0.0	-
7.8553	193	-	0.0278
4.7044	200	0.421	-
5.7107	210	0.0661	-
6.7170	220	0.0001	-
7.7233	230	0.0	-
8.7296	240	0.0	-
8.8302	241	-	0.0287
5.8805	250	0.41	-
6.8868	260	0.0111	-
7.8931	270	0.0001	0.0289

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.3.0
• Transformers: 4.41.2
• PyTorch: 2.1.2+cu121
• Accelerate: 1.1.1
• Datasets: 2.19.1
• 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}
}