metadata

base_model: sentence-transformers/all-MiniLM-L6-v2
datasets: []
language: []
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:458
  - loss:CosineSimilarityLoss
widget:
  - source_sentence: What does the document say about GST ?
    sentences:
      - >-
        If any ambiguity arises as to the meaning and intent of any portion of
        the Specifications and Drawings or as to execution or quality of any
        work or material, or as to the measurements of the works the decision of
        the Engineer thereon shall be final subject to the appeal
      - >-
        For tenders costing more than Rs 20 crore wherein eligibility criteria
        includes bid capacity also, the tenderer will be qualified only if its
        available bid capacity is equal to or more than the total bid value of
        the present tender. The available bid capacity shall be calculated.
      - >-
        Tenderers will examine the various provisions of The Central Goods and
        Services Tax Act, 2017(CGST)/ Integrated Goods and Services Tax Act,
        2017(IGST)/ Union Territory Goods and Services Tax Act, 2017(UTGST)/
  - source_sentence: What is the deadline to submit the proposed project schedule?
    sentences:
      - >-
        The Contractor who has been awarded the work shall as soon as possible
        but not later than 30 days after the date of receipt of the acceptance
        letter
      - "\_ \_ \_ \_ Special Conditions can modify the Standard General Conditions."
      - >-
        Limited Tenders shall mean tenders invited from all or some contractors
        on the approved or select list of contractors with the Railway
  - source_sentence: >-
      These Regulations for Tenders and Contracts shall be read in conjunction
      with the Standard General Conditions of Contract which are referred to
      herein and shall be subject to modifications additions or suppression by
      Special Conditions of Contract and/or Special Specifications, if any,
      annexed to the Tender Forms.
    sentences:
      - >-
        unless the Contractor has made a claim in writing in respect thereof
        before the issue of the Maintenance Certificate under this clause.
      - There shall be no modification expected.
      - Indemnification clause
  - source_sentence: No claim certificate
    sentences:
      - >-
        Subcontracting will in no way relieve the Contractor to execute the work
        as per terms of the contract.
      - Final Supplementary Agreement
      - Client can transfer the liability to the contractor
  - source_sentence: What is the deadline to submit the proposed project schedule?
    sentences:
      - "\_ \_ \_ \_ The Contractor shall at his own expense provide with sheds, storehouses and yards in such situations and in such numbers"
      - >-
        This clause defines the Contractor's responsibility for subcontractor
        performance.
      - >-
        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.

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

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
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 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': 256, 'do_lower_case': False}) with Transformer model: 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("Ananthu357/Ananthus-Transformers-for-contracts")
# Run inference
sentences = [
    'What is the deadline to submit the proposed project schedule?',
    '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.',
    '\xa0 \xa0 \xa0 \xa0 The Contractor shall at his own expense provide with sheds, storehouses and yards in such situations and in such numbers',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# 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
eval_on_start: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss
3.3448	100	0.1154	0.0756
6.6897	200	0.0204	0.0675
10.0345	300	0.0123	0.0767
13.3448	400	0.0048	0.0650
16.6897	500	0.0031	0.0633
20.0345	600	0.0026	0.0647
23.3448	700	0.0025	0.0649

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.42.4
PyTorch: 2.3.1+cu121
Accelerate: 0.32.1
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",
}