metadata

base_model: BAAI/bge-large-en
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:453
  - loss:CosineSimilarityLoss
widget:
  - source_sentence: Termination notice
    sentences:
      - "having value more than Rs 20 crore and original period of completion 12 months or more, when there is no reduction in original scope of work by more than 10%, and no extension granted on either railway or Contractor\x92s account,"
      - >-
        Special Conditions might exist in the contract and supersede the
        Standard General Conditions.
      - >-
        Subject to the provisions of the aforesaid Arbitration and Conciliation
        Act 1996 and the rules thereunder and relevant para of General
        Conditions of Contract
  - source_sentence: Impact of breach of terms by subcontracting.
    sentences:
      - >-
        The contractor shall commence the works within 15 days after the receipt
        by him of an order in wirting to this effect from the Engineer and shall
        proceed with the same with due expection and without delay.
      - >-
        Railway may, if satisfied that the works can be completed by the
        Contractor within reasonable short time thereafter, allow the Contractor
        for further extension of time (Proforma at Annexure-VII) as the Engineer
        may decide
      - >-
        On first occasion of noticing exaggerated/ false measurement, Engineer
        shall recover liquidated damages equal to 10% of claimed gross bill
        value.
  - source_sentence: >-
      Place of Arbitration: The place of arbitration would be within the
      geographical limits of the Division of the Railway
    sentences:
      - >-
        the Railway may grant such extension or extensions of the completion
        date as may be considered reasonable.
      - Location for dispute resolution
      - >-
        Any item of work carried out by the Contractor on the instructions of
        the Engineer which is not included in the accepted Schedules of Rates
        shall be executed at the rates set forth in the Schedule of Rates of
        Railway.
  - source_sentence: "\_ \_ \_ \_ Special Conditions of Contract must be referred to while executing the contract"
    sentences:
      - >-
        a penal interest of 12% per annum shall be charged for the delay beyond
        21(Twenty one) days, i.e. from 22nd day after the date of issue of LOA.
        Further, if the 60th day happens to be a declared holiday in the
        concerned office of the Railway, submission of PG can be accepted on the
        next working day.
      - "\_ \_ \_ \_ Contractor should finish the works according to Special conditions of Contract."
      - This explains the impact of breaching terms in subcontracting part.
  - source_sentence: >-
      Additional documents involve General Conditions of Contract, Regulations
      for Tenders and Contracts and Special Conditions of Contract.
    sentences:
      - "At the final stage of completion and commissioning of work, in case the contractor\x92s failure is limited to only some of the works costing not more than 2% of the original contract value,"
      - "\_ \_ \_ \_ Any material found during excavation should be reported to the engineer."
      - "\_If the Contractor shall be dissatisfied by reason of any decision of the Engineer's representative, he shall be entitled to refer the matter to the Engineer who shall there upon confirm or vary such decision."

SentenceTransformer based on BAAI/bge-large-en

This is a sentence-transformers model finetuned from BAAI/bge-large-en. It maps sentences & paragraphs to a 1024-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-large-en
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 tokens
Similarity Function: Cosine Similarity

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': 1024, '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("Ananthu357/Ananthus-BAAI-for-contracts5.0")
# Run inference
sentences = [
    'Additional documents involve General Conditions of Contract, Regulations for Tenders and Contracts and Special Conditions of Contract.',
    "\xa0If the Contractor shall be dissatisfied by reason of any decision of the Engineer's representative, he shall be entitled to refer the matter to the Engineer who shall there upon confirm or vary such decision.",
    'At the final stage of completion and commissioning of work, in case the contractor\x92s failure is limited to only some of the works costing not more than 2% of the original contract value,',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 25
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
learning_rate: 5e-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: 25
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: False
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: 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
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss
3.3448	100	0.06	0.0540
6.6897	200	0.0084	0.0568
10.0345	300	0.0035	0.0548
13.3448	400	0.0018	0.0536
16.6897	500	0.0011	0.0548
20.0345	600	0.001	0.0553
23.3448	700	0.0009	0.0556
3.3448	100	0.0014	0.0578
6.6897	200	0.0038	0.0582
10.0345	300	0.0025	0.0623
13.3448	400	0.0014	0.0579
16.6897	500	0.0008	0.0582
20.0345	600	0.0006	0.0579
23.3448	700	0.0006	0.0585
3.3448	100	0.0029	0.0640
6.6897	200	0.0048	0.0561
10.0345	300	0.0018	0.0524
13.3448	400	0.001	0.0522
16.6897	500	0.0007	0.0514
20.0345	600	0.0005	0.0519
23.3448	700	0.0005	0.0522

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.3.0+cu121
Accelerate: 0.31.0
Datasets: 2.20.0
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",
}